Index: llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp =================================================================== --- llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp +++ llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp @@ -6758,17 +6758,14 @@ return false; } +// Both bound_ctrl:0 and bound_ctrl:1 are encoded as 1. +// This is intentional and ensures compatibility with sp3. +// See bug 35397 for details. static bool ConvertBoundCtrl(int64_t &BoundCtrl) { - if (BoundCtrl == 0) { + if (BoundCtrl == 0 || BoundCtrl == 1) { BoundCtrl = 1; return true; } - - if (BoundCtrl == -1) { - BoundCtrl = 0; - return true; - } - return false; } Index: llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp =================================================================== --- llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp +++ llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp @@ -892,7 +892,7 @@ raw_ostream &O) { unsigned Imm = MI->getOperand(OpNo).getImm(); if (Imm) { - O << " bound_ctrl:0"; // XXX - this syntax is used in sp3 + O << " bound_ctrl:1"; } } Index: llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.mov.dpp.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.mov.dpp.ll +++ llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.mov.dpp.ll @@ -14,7 +14,7 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, s0 ; GFX8-NEXT: v_mov_b32_e32 v1, s3 ; GFX8-NEXT: s_nop 0 -; GFX8-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 +; GFX8-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 ; GFX8-NEXT: flat_store_dword v[0:1], v2 ; GFX8-NEXT: s_endpgm ; @@ -26,7 +26,7 @@ ; GFX10-NEXT: v_mov_b32_e32 v1, 0 ; encoding: [0x80,0x02,0x02,0x7e] ; GFX10-NEXT: s_waitcnt lgkmcnt(0) ; encoding: [0x7f,0xc0,0x8c,0xbf] ; GFX10-NEXT: v_mov_b32_e32 v0, s4 ; encoding: [0x04,0x02,0x00,0x7e] -; GFX10-NEXT: v_mov_b32_dpp v0, v0 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x01,0x08,0x11] +; GFX10-NEXT: v_mov_b32_dpp v0, v0 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x01,0x08,0x11] ; GFX10-NEXT: global_store_dword v1, v0, s[2:3] ; encoding: [0x00,0x80,0x70,0xdc,0x01,0x00,0x02,0x00] ; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf] %tmp0 = call i32 @llvm.amdgcn.mov.dpp.i32(i32 %in, i32 1, i32 1, i32 1, i1 true) #0 Index: llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wqm.demote.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wqm.demote.ll +++ llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wqm.demote.ll @@ -672,9 +672,9 @@ ; SI-NEXT: v_cndmask_b32_e64 v0, 1.0, 0, s[4:5] ; SI-NEXT: v_mov_b32_e32 v1, v0 ; SI-NEXT: s_nop 1 -; SI-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; SI-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; SI-NEXT: s_nop 1 -; SI-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; SI-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; SI-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; SI-NEXT: s_and_b64 exec, exec, s[0:1] ; SI-NEXT: v_cmp_eq_f32_e32 vcc, 0, v0 @@ -718,9 +718,9 @@ ; GFX9-NEXT: v_cndmask_b32_e64 v0, 1.0, 0, s[2:3] ; GFX9-NEXT: v_mov_b32_e32 v1, v0 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX9-NEXT: s_and_b64 exec, exec, s[0:1] ; GFX9-NEXT: v_cmp_eq_f32_e32 vcc, 0, v0 @@ -763,8 +763,8 @@ ; GFX10-32-NEXT: s_mov_b32 s1, s0 ; GFX10-32-NEXT: v_cndmask_b32_e64 v0, 1.0, 0, s1 ; GFX10-32-NEXT: v_mov_b32_e32 v1, v0 -; GFX10-32-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX10-32-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX10-32-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX10-32-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX10-32-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX10-32-NEXT: s_and_b32 exec_lo, exec_lo, s0 ; GFX10-32-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v0 @@ -807,8 +807,8 @@ ; GFX10-64-NEXT: s_mov_b64 s[2:3], s[0:1] ; GFX10-64-NEXT: v_cndmask_b32_e64 v0, 1.0, 0, s[2:3] ; GFX10-64-NEXT: v_mov_b32_e32 v1, v0 -; GFX10-64-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX10-64-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX10-64-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX10-64-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX10-64-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX10-64-NEXT: s_and_b64 exec, exec, s[0:1] ; GFX10-64-NEXT: v_cmp_eq_f32_e32 vcc, 0, v0 @@ -908,9 +908,9 @@ ; SI-NEXT: v_cndmask_b32_e64 v2, v0, 0, s[6:7] ; SI-NEXT: v_mov_b32_e32 v3, v2 ; SI-NEXT: s_nop 1 -; SI-NEXT: v_mov_b32_dpp v3, v3 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; SI-NEXT: v_mov_b32_dpp v3, v3 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; SI-NEXT: s_nop 1 -; SI-NEXT: v_subrev_f32_dpp v2, v2, v3 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; SI-NEXT: v_subrev_f32_dpp v2, v2, v3 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; SI-NEXT: ; kill: def $vgpr2 killed $vgpr2 killed $exec ; SI-NEXT: v_cmp_eq_f32_e32 vcc, 0, v2 ; SI-NEXT: s_and_b64 s[6:7], s[0:1], vcc @@ -973,9 +973,9 @@ ; GFX9-NEXT: v_cndmask_b32_e64 v2, v0, 0, s[4:5] ; GFX9-NEXT: v_mov_b32_e32 v3, v2 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_mov_b32_dpp v3, v3 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_mov_b32_dpp v3, v3 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_subrev_f32_dpp v2, v2, v3 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_subrev_f32_dpp v2, v2, v3 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: ; kill: def $vgpr2 killed $vgpr2 killed $exec ; GFX9-NEXT: v_cmp_eq_f32_e32 vcc, 0, v2 ; GFX9-NEXT: s_and_b64 s[4:5], s[0:1], vcc @@ -1036,8 +1036,8 @@ ; GFX10-32-NEXT: s_mov_b32 s2, s0 ; GFX10-32-NEXT: v_cndmask_b32_e64 v2, v0, 0, s2 ; GFX10-32-NEXT: v_mov_b32_e32 v3, v2 -; GFX10-32-NEXT: v_mov_b32_dpp v3, v3 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX10-32-NEXT: v_subrev_f32_dpp v2, v2, v3 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX10-32-NEXT: v_mov_b32_dpp v3, v3 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX10-32-NEXT: v_subrev_f32_dpp v2, v2, v3 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX10-32-NEXT: ; kill: def $vgpr2 killed $vgpr2 killed $exec ; GFX10-32-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v2 ; GFX10-32-NEXT: s_and_b32 s2, s0, vcc_lo @@ -1099,8 +1099,8 @@ ; GFX10-64-NEXT: s_mov_b64 s[4:5], s[0:1] ; GFX10-64-NEXT: v_cndmask_b32_e64 v2, v0, 0, s[4:5] ; GFX10-64-NEXT: v_mov_b32_e32 v3, v2 -; GFX10-64-NEXT: v_mov_b32_dpp v3, v3 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX10-64-NEXT: v_subrev_f32_dpp v2, v2, v3 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX10-64-NEXT: v_mov_b32_dpp v3, v3 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX10-64-NEXT: v_subrev_f32_dpp v2, v2, v3 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX10-64-NEXT: ; kill: def $vgpr2 killed $vgpr2 killed $exec ; GFX10-64-NEXT: v_cmp_eq_f32_e32 vcc, 0, v2 ; GFX10-64-NEXT: s_and_b64 s[4:5], s[0:1], vcc Index: llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll +++ llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll @@ -367,13 +367,13 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, 0 ; GFX8-NEXT: s_not_b64 exec, exec ; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 ; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX8-NEXT: s_nop 1 @@ -418,13 +418,13 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, 0 ; GFX9-NEXT: s_not_b64 exec, exec ; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 ; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX9-NEXT: s_nop 1 @@ -462,11 +462,11 @@ ; GFX1064-NEXT: v_mov_b32_e32 v1, 0 ; GFX1064-NEXT: s_not_b64 exec, exec ; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v3, 0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v2, v1 ; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf @@ -524,10 +524,10 @@ ; GFX1032-NEXT: v_mov_b32_e32 v1, 0 ; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo ; GFX1032-NEXT: s_or_saveexec_b32 s2, -1 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v2, v1 ; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1032-NEXT: s_mov_b32 exec_lo, s2 @@ -603,13 +603,13 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, 0 ; GFX8-NEXT: s_not_b64 exec, exec ; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 ; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX8-NEXT: s_nop 1 @@ -654,13 +654,13 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, 0 ; GFX9-NEXT: s_not_b64 exec, exec ; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 ; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX9-NEXT: s_nop 1 @@ -698,11 +698,11 @@ ; GFX1064-NEXT: v_mov_b32_e32 v1, 0 ; GFX1064-NEXT: s_not_b64 exec, exec ; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v3, 0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v2, v1 ; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf @@ -760,10 +760,10 @@ ; GFX1032-NEXT: v_mov_b32_e32 v1, 0 ; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo ; GFX1032-NEXT: s_or_saveexec_b32 s2, -1 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v2, v1 ; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1032-NEXT: s_mov_b32 exec_lo, s2 @@ -839,13 +839,13 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, 0 ; GFX8-NEXT: s_not_b64 exec, exec ; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 ; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX8-NEXT: s_nop 1 @@ -890,13 +890,13 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, 0 ; GFX9-NEXT: s_not_b64 exec, exec ; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 ; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX9-NEXT: s_nop 1 @@ -934,11 +934,11 @@ ; GFX1064-NEXT: v_mov_b32_e32 v1, 0 ; GFX1064-NEXT: s_not_b64 exec, exec ; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v3, 0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v2, v1 ; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf @@ -996,10 +996,10 @@ ; GFX1032-NEXT: v_mov_b32_e32 v1, 0 ; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo ; GFX1032-NEXT: s_or_saveexec_b32 s2, -1 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v2, v1 ; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1032-NEXT: s_mov_b32 exec_lo, s2 @@ -1879,13 +1879,13 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, 0 ; GFX8-NEXT: s_not_b64 exec, exec ; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 ; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX8-NEXT: s_nop 1 @@ -1930,13 +1930,13 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, 0 ; GFX9-NEXT: s_not_b64 exec, exec ; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 ; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX9-NEXT: s_nop 1 @@ -1974,11 +1974,11 @@ ; GFX1064-NEXT: v_mov_b32_e32 v1, 0 ; GFX1064-NEXT: s_not_b64 exec, exec ; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v3, 0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v2, v1 ; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf @@ -2036,10 +2036,10 @@ ; GFX1032-NEXT: v_mov_b32_e32 v1, 0 ; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo ; GFX1032-NEXT: s_or_saveexec_b32 s2, -1 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v2, v1 ; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1032-NEXT: s_mov_b32 exec_lo, s2 @@ -2832,13 +2832,13 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, 0 ; GFX8-NEXT: s_not_b64 exec, exec ; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 ; GFX8-NEXT: v_or_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX8-NEXT: s_nop 1 @@ -2883,13 +2883,13 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, 0 ; GFX9-NEXT: s_not_b64 exec, exec ; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 ; GFX9-NEXT: v_or_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX9-NEXT: s_nop 1 @@ -2927,11 +2927,11 @@ ; GFX1064-NEXT: v_mov_b32_e32 v1, 0 ; GFX1064-NEXT: s_not_b64 exec, exec ; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX1064-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v3, 0 -; GFX1064-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v2, v1 ; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1064-NEXT: v_or_b32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf @@ -2989,10 +2989,10 @@ ; GFX1032-NEXT: v_mov_b32_e32 v1, 0 ; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo ; GFX1032-NEXT: s_or_saveexec_b32 s2, -1 -; GFX1032-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_or_b32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v2, v1 ; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1032-NEXT: s_mov_b32 exec_lo, s2 @@ -3068,13 +3068,13 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, 0 ; GFX8-NEXT: s_not_b64 exec, exec ; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 ; GFX8-NEXT: v_xor_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX8-NEXT: s_nop 1 @@ -3119,13 +3119,13 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, 0 ; GFX9-NEXT: s_not_b64 exec, exec ; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 ; GFX9-NEXT: v_xor_b32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX9-NEXT: s_nop 1 @@ -3163,11 +3163,11 @@ ; GFX1064-NEXT: v_mov_b32_e32 v1, 0 ; GFX1064-NEXT: s_not_b64 exec, exec ; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX1064-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v3, 0 -; GFX1064-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v2, v1 ; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1064-NEXT: v_xor_b32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf @@ -3225,10 +3225,10 @@ ; GFX1032-NEXT: v_mov_b32_e32 v1, 0 ; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo ; GFX1032-NEXT: s_or_saveexec_b32 s2, -1 -; GFX1032-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_xor_b32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v2, v1 ; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1032-NEXT: s_mov_b32 exec_lo, s2 @@ -4142,13 +4142,13 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, 0 ; GFX8-NEXT: s_not_b64 exec, exec ; GFX8-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 ; GFX8-NEXT: v_max_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX8-NEXT: s_nop 1 @@ -4193,13 +4193,13 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, 0 ; GFX9-NEXT: s_not_b64 exec, exec ; GFX9-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 ; GFX9-NEXT: v_max_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX9-NEXT: s_nop 1 @@ -4237,11 +4237,11 @@ ; GFX1064-NEXT: v_mov_b32_e32 v1, 0 ; GFX1064-NEXT: s_not_b64 exec, exec ; GFX1064-NEXT: s_or_saveexec_b64 s[2:3], -1 -; GFX1064-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v3, 0 -; GFX1064-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v2, v1 ; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1064-NEXT: v_max_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf @@ -4299,10 +4299,10 @@ ; GFX1032-NEXT: v_mov_b32_e32 v1, 0 ; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo ; GFX1032-NEXT: s_or_saveexec_b32 s2, -1 -; GFX1032-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_max_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v2, v1 ; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1032-NEXT: s_mov_b32 exec_lo, s2 Index: llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll +++ llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll @@ -222,13 +222,13 @@ ; GFX8-NEXT: v_mov_b32_e32 v2, 0 ; GFX8-NEXT: s_not_b64 exec, exec ; GFX8-NEXT: s_or_saveexec_b64 s[10:11], -1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 -; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX8-NEXT: s_nop 1 ; GFX8-NEXT: v_add_u32_dpp v2, vcc, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX8-NEXT: s_nop 1 @@ -278,13 +278,13 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, 0 ; GFX9-NEXT: s_not_b64 exec, exec ; GFX9-NEXT: s_or_saveexec_b64 s[10:11], -1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 ; GFX9-NEXT: v_add_u32_dpp v2, v2, v2 row_bcast:15 row_mask:0xa bank_mask:0xf ; GFX9-NEXT: s_nop 1 @@ -329,11 +329,11 @@ ; GFX1064-NEXT: v_mov_b32_e32 v1, 0 ; GFX1064-NEXT: s_not_b64 exec, exec ; GFX1064-NEXT: s_or_saveexec_b64 s[10:11], -1 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v3, 0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1064-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1064-NEXT: v_mov_b32_e32 v2, v1 ; GFX1064-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1064-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf @@ -392,11 +392,11 @@ ; GFX1032-NEXT: v_mov_b32_e32 v1, 0 ; GFX1032-NEXT: s_not_b32 exec_lo, exec_lo ; GFX1032-NEXT: s_or_saveexec_b32 s9, -1 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:1 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v3, 0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:2 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:4 row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX1032-NEXT: v_add_nc_u32_dpp v1, v1, v1 row_shr:8 row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX1032-NEXT: v_mov_b32_e32 v2, v1 ; GFX1032-NEXT: v_permlanex16_b32 v2, v2, -1, -1 ; GFX1032-NEXT: v_add_nc_u32_dpp v1, v2, v1 quad_perm:[0,1,2,3] row_mask:0xa bank_mask:0xf Index: llvm/test/CodeGen/AMDGPU/dpp_combine.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/dpp_combine.ll +++ llvm/test/CodeGen/AMDGPU/dpp_combine.ll @@ -3,7 +3,7 @@ ; GCN-LABEL: {{^}}dpp_add: ; GCN: global_load_dword [[V:v[0-9]+]], -; GCN: v_add_{{(nc_)?}}u32_dpp [[V]], [[V]], [[V]] quad_perm:[1,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0{{$}} +; GCN: v_add_{{(nc_)?}}u32_dpp [[V]], [[V]], [[V]] quad_perm:[1,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1{{$}} define amdgpu_kernel void @dpp_add(i32 addrspace(1)* %arg) { %id = tail call i32 @llvm.amdgcn.workitem.id.x() %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %id @@ -16,7 +16,7 @@ ; GCN-LABEL: {{^}}dpp_ceil: ; GCN: global_load_dword [[V:v[0-9]+]], -; GCN: v_ceil_f32_dpp [[V]], [[V]] quad_perm:[1,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0{{$}} +; GCN: v_ceil_f32_dpp [[V]], [[V]] quad_perm:[1,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1{{$}} define amdgpu_kernel void @dpp_ceil(i32 addrspace(1)* %arg) { %id = tail call i32 @llvm.amdgcn.workitem.id.x() %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %id @@ -31,7 +31,7 @@ ; GCN-LABEL: {{^}}dpp_fadd: ; GCN: global_load_dword [[V:v[0-9]+]], -; GCN: v_add_f32_dpp [[V]], [[V]], [[V]] quad_perm:[1,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0{{$}} +; GCN: v_add_f32_dpp [[V]], [[V]], [[V]] quad_perm:[1,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1{{$}} define amdgpu_kernel void @dpp_fadd(i32 addrspace(1)* %arg) { %id = tail call i32 @llvm.amdgcn.workitem.id.x() %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %id Index: llvm/test/CodeGen/AMDGPU/dpp_combine.mir =================================================================== --- llvm/test/CodeGen/AMDGPU/dpp_combine.mir +++ llvm/test/CodeGen/AMDGPU/dpp_combine.mir @@ -2,7 +2,7 @@ --- # old is undefined: only combine when masks are fully enabled and -# bound_ctrl:0 is set, otherwise the result of DPP VALU op can be undefined. +# bound_ctrl:1 is set, otherwise the result of DPP VALU op can be undefined. # GCN-LABEL: name: old_is_undef # GCN: %2:vgpr_32 = IMPLICIT_DEF # VOP2: @@ -56,20 +56,20 @@ # GCN-LABEL: name: old_is_0 # VOP2: -# case 1: old is zero, masks are fully enabled, bound_ctrl:0 is on: +# case 1: old is zero, masks are fully enabled, bound_ctrl:1 is on: # the DPP mov result would be either zero ({src lane disabled}|{src lane is # out of range}) or active src lane result - can combine with old = undef. # undef is preffered as it makes life easier for the regalloc. # GCN: [[U1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF # GCN: %4:vgpr_32 = V_ADD_U32_dpp [[U1]], %0, %1, 1, 15, 15, 1, implicit $exec -# case 2: old is zero, masks are fully enabled, bound_ctrl:0 is off: +# case 2: old is zero, masks are fully enabled, bound_ctrl:1 is off: # as the DPP mov old is zero this case is no different from case 1 - combine it -# setting bound_ctrl0 on for the combined DPP VALU op to make old undefined +# setting bound_ctrl:1 on for the combined DPP VALU op to make old undefined # GCN: [[U2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF # GCN: %6:vgpr_32 = V_ADD_U32_dpp [[U2]], %0, %1, 1, 15, 15, 1, implicit $exec -# case 3: masks are partialy disabled, bound_ctrl:0 is on: +# case 3: masks are partialy disabled, bound_ctrl:1 is on: # the DPP mov result would be either zero ({src lane disabled}|{src lane is # out of range} or {the DPP mov's dest VGPR write is disabled by masks}) or # active src lane result - can combine with old = src1 of the VALU op. @@ -79,7 +79,7 @@ # here but let's make it off to keep the combiner's logic simpler. # GCN: %8:vgpr_32 = V_ADD_U32_dpp %1, %0, %1, 1, 14, 15, 0, implicit $exec -# case 4: masks are partialy disabled, bound_ctrl:0 is off: +# case 4: masks are partialy disabled, bound_ctrl:1 is off: # the DPP mov result would be either zero ({src lane disabled}|{src lane is # out of range} or {the DPP mov's dest VGPR write is disabled by masks}) or # active src lane result - can combine with old = src1 of the VALU op. @@ -137,7 +137,7 @@ # old is nonzero identity cases: -# old is nonzero identity, masks are fully enabled, bound_ctrl:0 is off: +# old is nonzero identity, masks are fully enabled, bound_ctrl:1 is off: # the DPP mov result would be either identity ({src lane disabled}|{out of # range}) or src lane result - can combine with old = src1 of the VALU op # The DPP VALU op should have the same masks (and bctrl) as DPP mov as they @@ -174,7 +174,7 @@ %13:vgpr_32 = V_MIN_I32_e32 %12, %1, implicit $exec ... -# old is nonzero identity, masks are partially enabled, bound_ctrl:0 is off: +# old is nonzero identity, masks are partially enabled, bound_ctrl:1 is off: # the DPP mov result would be either identity ({src lane disabled}|{src lane is # out of range} or {the DPP mov's dest VGPR write is disabled by masks}) or # active src lane result - can combine with old = src1 of the VALU op. @@ -212,7 +212,7 @@ %13:vgpr_32 = V_MIN_I32_e32 %12, %1, implicit $exec ... -# old is nonzero identity, masks are partially enabled, bound_ctrl:0 is on: +# old is nonzero identity, masks are partially enabled, bound_ctrl:1 is on: # the DPP mov result may have 3 different values: # 1. the active src lane result # 2. 0 if the src lane is disabled|out of range @@ -435,7 +435,7 @@ %4:vgpr_32 = V_ADD_U32_e32 %3, %0, implicit $exec ... -# old reg def is in diff BB but bound_ctrl:0 - can combine +# old reg def is in diff BB but bound_ctrl:1 - can combine # GCN-LABEL: name: old_in_diff_bb_bctrl_zero # GCN: %4:vgpr_32 = V_ADD_U32_dpp {{%[0-9]}}, %0, %1, 1, 15, 15, 1, implicit $exec Index: llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll +++ llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll @@ -8,8 +8,8 @@ ; VI: v_mov_b32_e32 v0, s{{[0-9]+}} ; VI-NOOPT: v_mov_b32_e32 v1, s{{[0-9]+}} ; PREGFX10: s_nop 1 -; VI-OPT: v_mov_b32_dpp v0, v0 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x01,0x08,0x11] -; VI-NOOPT: v_mov_b32_dpp v0, v1 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x01,0x01,0x08,0x11] +; VI-OPT: v_mov_b32_dpp v0, v0 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x01,0x08,0x11] +; VI-NOOPT: v_mov_b32_dpp v0, v1 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x01,0x01,0x08,0x11] define amdgpu_kernel void @dpp_test(i32 addrspace(1)* %out, i32 %in) { %tmp0 = call i32 @llvm.amdgcn.mov.dpp.i32(i32 %in, i32 1, i32 1, i32 1, i1 1) #0 store i32 %tmp0, i32 addrspace(1)* %out @@ -20,11 +20,11 @@ ; VI-NOOPT: v_mov_b32_e32 [[VGPR1:v[0-9]+]], s{{[0-9]+}} ; VI: v_mov_b32_e32 [[VGPR0:v[0-9]+]], s{{[0-9]+}} ; PREGFX10: s_nop 1 -; VI-OPT: v_mov_b32_dpp [[VGPR0]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 +; VI-OPT: v_mov_b32_dpp [[VGPR0]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 ; VI-NOOPT: v_mov_b32_dpp [[VGPR1]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl: ; PREGFX10: s_nop 1 -; VI-OPT: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 -; VI-NOOPT: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR1]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 +; VI-OPT: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 +; VI-NOOPT: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR1]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 define amdgpu_kernel void @dpp_wait_states(i32 addrspace(1)* %out, i32 %in) { %tmp0 = call i32 @llvm.amdgcn.mov.dpp.i32(i32 %in, i32 1, i32 1, i32 1, i1 1) #0 %tmp1 = call i32 @llvm.amdgcn.mov.dpp.i32(i32 %tmp0, i32 1, i32 1, i32 1, i1 1) #0 @@ -36,12 +36,12 @@ ; VI: ; %endif ; PREGFX10-NOOPT: s_waitcnt ; PREGFX10-NOOPT: v_mov_b32_e32 -; VI: v_mov_b32_dpp [[VGPR0:v[0-9]+]], v{{[0-9]+}} quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 +; VI: v_mov_b32_dpp [[VGPR0:v[0-9]+]], v{{[0-9]+}} quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 ; PREGFX10-OPT: s_mov_b32 ; PREGFX10-OPT: s_mov_b32 -; VI: v_mov_b32_dpp [[VGPR1:v[0-9]+]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 +; VI: v_mov_b32_dpp [[VGPR1:v[0-9]+]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 ; PREGFX10: s_nop 1 -; VI: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR1]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 +; VI: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR1]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1 define amdgpu_kernel void @dpp_first_in_bb(float addrspace(1)* %out, float addrspace(1)* %in, float %cond, float %a, float %b) { %cmp = fcmp oeq float %cond, 0.0 br i1 %cmp, label %if, label %else Index: llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll +++ llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll @@ -17,7 +17,7 @@ ; GCN: v_mov_b32_e32 [[DST:v[0-9]+]], s{{[0-9]+}} ; GCN: v_mov_b32_e32 [[SRC:v[0-9]+]], s{{[0-9]+}} ; GFX8: s_nop 1 -; GCN: v_mov_b32_dpp [[DST]], [[SRC]] quad_perm:[2,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0{{$}} +; GCN: v_mov_b32_dpp [[DST]], [[SRC]] quad_perm:[2,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:1{{$}} define amdgpu_kernel void @dpp_test_bc(i32 addrspace(1)* %out, i32 %in1, i32 %in2) { %tmp0 = call i32 @llvm.amdgcn.update.dpp.i32(i32 %in1, i32 %in2, i32 2, i32 1, i32 1, i1 1) #0 store i32 %tmp0, i32 addrspace(1)* %out Index: llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll +++ llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll @@ -672,9 +672,9 @@ ; SI-NEXT: v_mov_b32_e32 v1, v0 ; SI-NEXT: s_xor_b64 s[2:3], s[0:1], -1 ; SI-NEXT: s_nop 0 -; SI-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; SI-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; SI-NEXT: s_nop 1 -; SI-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; SI-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; SI-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; SI-NEXT: s_and_b64 exec, exec, s[0:1] ; SI-NEXT: v_cmp_neq_f32_e32 vcc, 0, v0 @@ -718,9 +718,9 @@ ; GFX9-NEXT: v_mov_b32_e32 v1, v0 ; GFX9-NEXT: s_xor_b64 s[2:3], s[0:1], -1 ; GFX9-NEXT: s_nop 0 -; GFX9-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX9-NEXT: s_and_b64 exec, exec, s[0:1] ; GFX9-NEXT: v_cmp_neq_f32_e32 vcc, 0, v0 @@ -762,8 +762,8 @@ ; GFX10-32-NEXT: s_mov_b32 s1, s0 ; GFX10-32-NEXT: v_cndmask_b32_e64 v0, 1.0, 0, s1 ; GFX10-32-NEXT: v_mov_b32_e32 v1, v0 -; GFX10-32-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX10-32-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX10-32-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX10-32-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX10-32-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX10-32-NEXT: s_and_b32 exec_lo, exec_lo, s0 ; GFX10-32-NEXT: v_cmp_neq_f32_e32 vcc_lo, 0, v0 @@ -806,8 +806,8 @@ ; GFX10-64-NEXT: s_mov_b64 s[2:3], s[0:1] ; GFX10-64-NEXT: v_cndmask_b32_e64 v0, 1.0, 0, s[2:3] ; GFX10-64-NEXT: v_mov_b32_e32 v1, v0 -; GFX10-64-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX10-64-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX10-64-NEXT: v_mov_b32_dpp v1, v1 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX10-64-NEXT: v_subrev_f32_dpp v0, v0, v1 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX10-64-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX10-64-NEXT: s_and_b64 exec, exec, s[0:1] ; GFX10-64-NEXT: v_cmp_neq_f32_e32 vcc, 0, v0 @@ -901,9 +901,9 @@ ; SI-NEXT: v_mov_b32_e32 v2, v0 ; SI-NEXT: s_xor_b64 s[6:7], s[0:1], -1 ; SI-NEXT: s_nop 0 -; SI-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; SI-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; SI-NEXT: s_nop 1 -; SI-NEXT: v_subrev_f32_dpp v0, v0, v2 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; SI-NEXT: v_subrev_f32_dpp v0, v0, v2 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; SI-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; SI-NEXT: v_cmp_neq_f32_e32 vcc, 0, v0 ; SI-NEXT: s_or_b64 s[6:7], s[6:7], vcc @@ -966,9 +966,9 @@ ; GFX9-NEXT: v_mov_b32_e32 v2, v0 ; GFX9-NEXT: s_xor_b64 s[6:7], s[0:1], -1 ; GFX9-NEXT: s_nop 0 -; GFX9-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: s_nop 1 -; GFX9-NEXT: v_subrev_f32_dpp v0, v0, v2 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX9-NEXT: v_subrev_f32_dpp v0, v0, v2 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX9-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX9-NEXT: v_cmp_neq_f32_e32 vcc, 0, v0 ; GFX9-NEXT: s_or_b64 s[6:7], s[6:7], vcc @@ -1029,8 +1029,8 @@ ; GFX10-32-NEXT: v_cndmask_b32_e64 v0, s2, 0, s3 ; GFX10-32-NEXT: s_xor_b32 s3, s0, -1 ; GFX10-32-NEXT: v_mov_b32_e32 v2, v0 -; GFX10-32-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX10-32-NEXT: v_subrev_f32_dpp v0, v0, v2 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX10-32-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX10-32-NEXT: v_subrev_f32_dpp v0, v0, v2 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX10-32-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX10-32-NEXT: v_cmp_neq_f32_e32 vcc_lo, 0, v0 ; GFX10-32-NEXT: s_or_b32 s3, s3, vcc_lo @@ -1091,8 +1091,8 @@ ; GFX10-64-NEXT: v_cndmask_b32_e64 v0, s2, 0, s[6:7] ; GFX10-64-NEXT: s_xor_b64 s[6:7], s[0:1], -1 ; GFX10-64-NEXT: v_mov_b32_e32 v2, v0 -; GFX10-64-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 -; GFX10-64-NEXT: v_subrev_f32_dpp v0, v0, v2 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:0 +; GFX10-64-NEXT: v_mov_b32_dpp v2, v2 quad_perm:[1,1,1,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 +; GFX10-64-NEXT: v_subrev_f32_dpp v0, v0, v2 quad_perm:[0,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; GFX10-64-NEXT: ; kill: def $vgpr0 killed $vgpr0 killed $exec ; GFX10-64-NEXT: v_cmp_neq_f32_e32 vcc, 0, v0 ; GFX10-64-NEXT: s_or_b64 s[6:7], s[6:7], vcc Index: llvm/test/MC/AMDGPU/gfx10_asm_dpp16.s =================================================================== --- llvm/test/MC/AMDGPU/gfx10_asm_dpp16.s +++ llvm/test/MC/AMDGPU/gfx10_asm_dpp16.s @@ -72,6 +72,9 @@ v_mov_b32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 // GFX10: [0xfa,0x02,0x0a,0x7e,0x01,0x1b,0x08,0x00] +v_mov_b32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 +// GFX10: [0xfa,0x02,0x0a,0x7e,0x01,0x1b,0x08,0x00] + v_cvt_f32_i32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 // GFX10: [0xfa,0x0a,0x0a,0x7e,0x01,0x1b,0x00,0x00] @@ -660,6 +663,9 @@ v_add_nc_u32_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 // GFX10: [0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x08,0x00] +v_add_nc_u32_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 +// GFX10: [0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x08,0x00] + v_add_nc_u32_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 fi:1 // GFX10: [0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x04,0x00] Index: llvm/test/MC/AMDGPU/vop_dpp.s =================================================================== --- llvm/test/MC/AMDGPU/vop_dpp.s +++ llvm/test/MC/AMDGPU/vop_dpp.s @@ -60,13 +60,33 @@ v_mov_b32 v0, v0 row_bcast:31 //===----------------------------------------------------------------------===// -// Check optional fields +// Check bound_control modifier. +// Both bound_ctrl:0 and bound_ctrl:1 are legal and encoded as 1. +// See bug 35397 for details. //===----------------------------------------------------------------------===// // NOSICI: error: not a valid operand. -// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xa1] +// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xa1] v_mov_b32 v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:0 +// NOSICI: error: not a valid operand. +// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xa1] +v_mov_b32 v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:1 + +// NOSICI: error: not a valid operand. +// NOGFX9: error: invalid bound_ctrl value. +// NOVI: error: invalid bound_ctrl value. +v_mov_b32 v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:-1 + +// NOSICI: error: not a valid operand. +// NOGFX9: error: invalid bound_ctrl value. +// NOVI: error: invalid bound_ctrl value. +v_mov_b32 v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:2 + +//===----------------------------------------------------------------------===// +// Check optional fields +//===----------------------------------------------------------------------===// + // NOSICI: error: not a valid operand. // VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0xf ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x00,0xaf] v_mov_b32 v0, v0 quad_perm:[1,3,0,1] row_mask:0xa @@ -76,7 +96,7 @@ v_mov_b32 v0, v0 quad_perm:[1,3,0,1] bank_mask:0x1 // NOSICI: error: not a valid operand. -// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xff] +// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xff] v_mov_b32 v0, v0 quad_perm:[1,3,0,1] bound_ctrl:0 // NOSICI: error: not a valid operand. @@ -84,11 +104,11 @@ v_mov_b32 v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 // NOSICI: error: not a valid operand. -// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0xf bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xaf] +// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0xf bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xaf] v_mov_b32 v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xf1] +// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xf1] v_mov_b32 v0, v0 quad_perm:[1,3,0,1] bank_mask:0x1 bound_ctrl:0 //===----------------------------------------------------------------------===// @@ -96,19 +116,19 @@ //===----------------------------------------------------------------------===// // NOSICI: error: not a valid operand. -// VI9: v_add_f32_dpp v0, -v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x19,0xa1] +// VI9: v_add_f32_dpp v0, -v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x19,0xa1] v_add_f32 v0, -v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_add_f32_dpp v0, v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x89,0xa1] +// VI9: v_add_f32_dpp v0, v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x89,0xa1] v_add_f32 v0, v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_add_f32_dpp v0, -v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x99,0xa1] +// VI9: v_add_f32_dpp v0, -v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x99,0xa1] v_add_f32 v0, -v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_add_f32_dpp v0, |v0|, -v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x69,0xa1] +// VI9: v_add_f32_dpp v0, |v0|, -v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x69,0xa1] v_add_f32 v0, |v0|, -v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 //===----------------------------------------------------------------------===// @@ -121,221 +141,221 @@ v_nop row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_u32_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x0e,0x00,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_u32_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x0e,0x00,0x7e,0x00,0x01,0x09,0xa1] v_cvt_u32_f32 v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_fract_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x36,0x00,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_fract_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x36,0x00,0x7e,0x00,0x01,0x09,0xa1] v_fract_f32 v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_sin_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x52,0x00,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_sin_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x52,0x00,0x7e,0x00,0x01,0x09,0xa1] v_sin_f32 v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_mov_b32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_mov_b32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x02,0x7e,0x00,0x01,0x09,0xa1] v_mov_b32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_f32_i32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x0a,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f32_i32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x0a,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f32_i32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_f32_u32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x0c,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f32_u32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x0c,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f32_u32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_i32_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x10,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_i32_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x10,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_i32_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_f16_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x14,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f16_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x14,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f16_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_f32_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x16,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f32_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x16,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f32_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_rpi_i32_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x18,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_rpi_i32_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x18,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_rpi_i32_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_flr_i32_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x1a,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_flr_i32_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x1a,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_flr_i32_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_off_f32_i4_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x1c,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_off_f32_i4_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x1c,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_off_f32_i4 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_f32_ubyte0_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x22,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f32_ubyte0_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x22,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f32_ubyte0 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_f32_ubyte1_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x24,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f32_ubyte1_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x24,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f32_ubyte1 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_f32_ubyte2_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x26,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f32_ubyte2_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x26,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f32_ubyte2 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cvt_f32_ubyte3_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x28,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f32_ubyte3_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x28,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f32_ubyte3 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_trunc_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x38,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_trunc_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x38,0x02,0x7e,0x00,0x01,0x09,0xa1] v_trunc_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_ceil_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x3a,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_ceil_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x3a,0x02,0x7e,0x00,0x01,0x09,0xa1] v_ceil_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_rndne_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x3c,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_rndne_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x3c,0x02,0x7e,0x00,0x01,0x09,0xa1] v_rndne_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_floor_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x3e,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_floor_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x3e,0x02,0x7e,0x00,0x01,0x09,0xa1] v_floor_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_exp_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x40,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_exp_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x40,0x02,0x7e,0x00,0x01,0x09,0xa1] v_exp_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_log_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x42,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_log_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x42,0x02,0x7e,0x00,0x01,0x09,0xa1] v_log_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_rcp_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x44,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_rcp_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x44,0x02,0x7e,0x00,0x01,0x09,0xa1] v_rcp_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_rcp_iflag_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x46,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_rcp_iflag_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x46,0x02,0x7e,0x00,0x01,0x09,0xa1] v_rcp_iflag_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_rsq_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x48,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_rsq_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x48,0x02,0x7e,0x00,0x01,0x09,0xa1] v_rsq_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_sqrt_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x4e,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_sqrt_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x4e,0x02,0x7e,0x00,0x01,0x09,0xa1] v_sqrt_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_cos_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x54,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cos_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x54,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cos_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_not_b32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x56,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_not_b32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x56,0x02,0x7e,0x00,0x01,0x09,0xa1] v_not_b32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_bfrev_b32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x58,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_bfrev_b32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x58,0x02,0x7e,0x00,0x01,0x09,0xa1] v_bfrev_b32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_ffbh_u32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x5a,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_ffbh_u32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x5a,0x02,0x7e,0x00,0x01,0x09,0xa1] v_ffbh_u32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_ffbl_b32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x5c,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_ffbl_b32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x5c,0x02,0x7e,0x00,0x01,0x09,0xa1] v_ffbl_b32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_ffbh_i32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x5e,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_ffbh_i32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x5e,0x02,0x7e,0x00,0x01,0x09,0xa1] v_ffbh_i32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_frexp_exp_i32_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x66,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_frexp_exp_i32_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x66,0x02,0x7e,0x00,0x01,0x09,0xa1] v_frexp_exp_i32_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_frexp_mant_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x68,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_frexp_mant_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x68,0x02,0x7e,0x00,0x01,0x09,0xa1] v_frexp_mant_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 -// VI9: v_log_legacy_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x98,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_log_legacy_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x98,0x02,0x7e,0x00,0x01,0x09,0xa1] // NOSI: error: instruction not supported on this GPU // NOCI: error: not a valid operand. v_log_legacy_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 -// VI9: v_exp_legacy_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x96,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_exp_legacy_f32_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x96,0x02,0x7e,0x00,0x01,0x09,0xa1] // NOSI: error: instruction not supported on this GPU // NOCI: error: not a valid operand. v_exp_legacy_f32 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_cvt_f16_u16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x72,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f16_u16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x72,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f16_u16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_cvt_f16_i16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x74,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_f16_i16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x74,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_f16_i16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_cvt_u16_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x76,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_u16_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x76,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_u16_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_cvt_i16_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x78,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cvt_i16_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x78,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cvt_i16_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_rcp_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x7a,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_rcp_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x7a,0x02,0x7e,0x00,0x01,0x09,0xa1] v_rcp_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_sqrt_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x7c,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_sqrt_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x7c,0x02,0x7e,0x00,0x01,0x09,0xa1] v_sqrt_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_rsq_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x7e,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_rsq_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x7e,0x02,0x7e,0x00,0x01,0x09,0xa1] v_rsq_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_log_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x80,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_log_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x80,0x02,0x7e,0x00,0x01,0x09,0xa1] v_log_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_exp_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x82,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_exp_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x82,0x02,0x7e,0x00,0x01,0x09,0xa1] v_exp_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_frexp_mant_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x84,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_frexp_mant_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x84,0x02,0x7e,0x00,0x01,0x09,0xa1] v_frexp_mant_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_frexp_exp_i16_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x86,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_frexp_exp_i16_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x86,0x02,0x7e,0x00,0x01,0x09,0xa1] v_frexp_exp_i16_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_floor_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x88,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_floor_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x88,0x02,0x7e,0x00,0x01,0x09,0xa1] v_floor_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_ceil_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x8a,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_ceil_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x8a,0x02,0x7e,0x00,0x01,0x09,0xa1] v_ceil_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_trunc_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x8c,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_trunc_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x8c,0x02,0x7e,0x00,0x01,0x09,0xa1] v_trunc_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_rndne_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x8e,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_rndne_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x8e,0x02,0x7e,0x00,0x01,0x09,0xa1] v_rndne_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_fract_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x90,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_fract_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x90,0x02,0x7e,0x00,0x01,0x09,0xa1] v_fract_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_sin_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x92,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_sin_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x92,0x02,0x7e,0x00,0x01,0x09,0xa1] v_sin_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_cos_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x94,0x02,0x7e,0x00,0x01,0x09,0xa1] +// VI9: v_cos_f16_dpp v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x94,0x02,0x7e,0x00,0x01,0x09,0xa1] v_cos_f16 v1, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // GFX9: v_cvt_norm_i16_f16_dpp v5, |v1| quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x9a,0x0a,0x7e,0x01,0xe4,0x20,0x00] @@ -355,7 +375,7 @@ // NOSICI: error: instruction not supported on this GPU // NOVI: error: instruction not supported on this GPU -// GFX9: v_screen_partition_4se_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x6e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +// GFX9: v_screen_partition_4se_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x6e,0x0a,0x7e,0x01,0xe4,0x08,0x00] v_screen_partition_4se_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 //===----------------------------------------------------------------------===// @@ -372,223 +392,223 @@ v_mac_f32 v0, v0, v0 row_shr:0xf // NOSICI: error: not a valid operand. -// VI9: v_mac_f32_dpp v0, v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0xf bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x2c,0x00,0x4d,0x08,0xaf] +// VI9: v_mac_f32_dpp v0, v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0xf bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x2c,0x00,0x4d,0x08,0xaf] v_mac_f32 v0, v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_add_f32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x09,0xa1] +// VI9: v_add_f32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x09,0xa1] v_add_f32 v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_min_f32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x14,0x00,0x01,0x09,0xa1] +// VI9: v_min_f32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x14,0x00,0x01,0x09,0xa1] v_min_f32 v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_and_b32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x26,0x00,0x01,0x09,0xa1] +// VI9: v_and_b32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x26,0x00,0x01,0x09,0xa1] v_and_b32 v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_mul_i32_i24_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x0c,0x02,0x01,0x09,0xa1] +// VI9: v_mul_i32_i24_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x0c,0x02,0x01,0x09,0xa1] v_mul_i32_i24 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_sub_f32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x04,0x02,0x01,0x09,0xa1] +// VI9: v_sub_f32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x04,0x02,0x01,0x09,0xa1] v_sub_f32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_subrev_f32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x06,0x02,0x01,0x09,0xa1] +// VI9: v_subrev_f32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x06,0x02,0x01,0x09,0xa1] v_subrev_f32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_mul_f32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x0a,0x02,0x01,0x09,0xa1] +// VI9: v_mul_f32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x0a,0x02,0x01,0x09,0xa1] v_mul_f32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_mul_hi_i32_i24_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x0e,0x02,0x01,0x09,0xa1] +// VI9: v_mul_hi_i32_i24_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x0e,0x02,0x01,0x09,0xa1] v_mul_hi_i32_i24 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_mul_u32_u24_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x10,0x02,0x01,0x09,0xa1] +// VI9: v_mul_u32_u24_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x10,0x02,0x01,0x09,0xa1] v_mul_u32_u24 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_mul_hi_u32_u24_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x12,0x02,0x01,0x09,0xa1] +// VI9: v_mul_hi_u32_u24_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x12,0x02,0x01,0x09,0xa1] v_mul_hi_u32_u24 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_max_f32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x16,0x02,0x01,0x09,0xa1] +// VI9: v_max_f32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x16,0x02,0x01,0x09,0xa1] v_max_f32 v1, v2 v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_min_i32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x18,0x02,0x01,0x09,0xa1] +// VI9: v_min_i32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x18,0x02,0x01,0x09,0xa1] v_min_i32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_max_i32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x1a,0x02,0x01,0x09,0xa1] +// VI9: v_max_i32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x1a,0x02,0x01,0x09,0xa1] v_max_i32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_min_u32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x1c,0x02,0x01,0x09,0xa1] +// VI9: v_min_u32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x1c,0x02,0x01,0x09,0xa1] v_min_u32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_max_u32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x1e,0x02,0x01,0x09,0xa1] +// VI9: v_max_u32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x1e,0x02,0x01,0x09,0xa1] v_max_u32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_lshrrev_b32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x20,0x02,0x01,0x09,0xa1] +// VI9: v_lshrrev_b32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x20,0x02,0x01,0x09,0xa1] v_lshrrev_b32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_ashrrev_i32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x22,0x02,0x01,0x09,0xa1] +// VI9: v_ashrrev_i32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x22,0x02,0x01,0x09,0xa1] v_ashrrev_i32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_lshlrev_b32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x24,0x02,0x01,0x09,0xa1] +// VI9: v_lshlrev_b32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x24,0x02,0x01,0x09,0xa1] v_lshlrev_b32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_or_b32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x28,0x02,0x01,0x09,0xa1] +// VI9: v_or_b32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x28,0x02,0x01,0x09,0xa1] v_or_b32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. -// VI9: v_xor_b32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x2a,0x02,0x01,0x09,0xa1] +// VI9: v_xor_b32_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x2a,0x02,0x01,0x09,0xa1] v_xor_b32 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_add_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x3e,0x02,0x01,0x09,0xa1] +// VI9: v_add_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x3e,0x02,0x01,0x09,0xa1] v_add_f16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_sub_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x40,0x02,0x01,0x09,0xa1] +// VI9: v_sub_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x40,0x02,0x01,0x09,0xa1] v_sub_f16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_subrev_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x42,0x02,0x01,0x09,0xa1] +// VI9: v_subrev_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x42,0x02,0x01,0x09,0xa1] v_subrev_f16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_mul_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x44,0x02,0x01,0x09,0xa1] +// VI9: v_mul_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x44,0x02,0x01,0x09,0xa1] v_mul_f16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_mac_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x46,0x02,0x01,0x09,0xa1] +// VI9: v_mac_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x46,0x02,0x01,0x09,0xa1] v_mac_f16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_add_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x4c,0x02,0x01,0x09,0xa1] +// VI9: v_add_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x4c,0x02,0x01,0x09,0xa1] v_add_u16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_sub_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x4e,0x02,0x01,0x09,0xa1] +// VI9: v_sub_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x4e,0x02,0x01,0x09,0xa1] v_sub_u16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_subrev_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x50,0x02,0x01,0x09,0xa1] +// VI9: v_subrev_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x50,0x02,0x01,0x09,0xa1] v_subrev_u16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_mul_lo_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x52,0x02,0x01,0x09,0xa1] +// VI9: v_mul_lo_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x52,0x02,0x01,0x09,0xa1] v_mul_lo_u16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_lshlrev_b16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x54,0x02,0x01,0x09,0xa1] +// VI9: v_lshlrev_b16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x54,0x02,0x01,0x09,0xa1] v_lshlrev_b16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_lshrrev_b16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x56,0x02,0x01,0x09,0xa1] +// VI9: v_lshrrev_b16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x56,0x02,0x01,0x09,0xa1] v_lshrrev_b16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_ashrrev_i16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x58,0x02,0x01,0x09,0xa1] +// VI9: v_ashrrev_i16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x58,0x02,0x01,0x09,0xa1] v_ashrrev_i16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_max_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x5a,0x02,0x01,0x09,0xa1] +// VI9: v_max_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x5a,0x02,0x01,0x09,0xa1] v_max_f16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_min_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x5c,0x02,0x01,0x09,0xa1] +// VI9: v_min_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x5c,0x02,0x01,0x09,0xa1] v_min_f16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_max_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x5e,0x02,0x01,0x09,0xa1] +// VI9: v_max_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x5e,0x02,0x01,0x09,0xa1] v_max_u16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_max_i16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x60,0x02,0x01,0x09,0xa1] +// VI9: v_max_i16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x60,0x02,0x01,0x09,0xa1] v_max_i16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_min_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x62,0x02,0x01,0x09,0xa1] +// VI9: v_min_u16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x62,0x02,0x01,0x09,0xa1] v_min_u16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_min_i16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x64,0x02,0x01,0x09,0xa1] +// VI9: v_min_i16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x64,0x02,0x01,0x09,0xa1] v_min_i16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU -// VI9: v_ldexp_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x66,0x02,0x01,0x09,0xa1] +// VI9: v_ldexp_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x66,0x02,0x01,0x09,0xa1] v_ldexp_f16 v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU // NOGFX9: error: not a valid operand. -// VI: v_add_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x32,0x02,0x01,0x09,0xa1] +// VI: v_add_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x32,0x02,0x01,0x09,0xa1] v_add_u32 v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU // NOGFX9: error: not a valid operand. -// VI: v_sub_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x34,0x02,0x01,0x09,0xa1] +// VI: v_sub_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x34,0x02,0x01,0x09,0xa1] v_sub_u32 v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU // NOGFX9: error: not a valid operand. -// VI: v_subrev_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x36,0x02,0x01,0x09,0xa1] +// VI: v_subrev_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x36,0x02,0x01,0x09,0xa1] v_subrev_u32 v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. // NOGFX9: error: instruction not supported on this GPU -// VI: v_addc_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x38,0x02,0x01,0x09,0xa1] +// VI: v_addc_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x38,0x02,0x01,0x09,0xa1] v_addc_u32 v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. // NOGFX9: error: instruction not supported on this GPU -// VI: v_subb_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x3a,0x02,0x01,0x09,0xa1] +// VI: v_subb_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x3a,0x02,0x01,0x09,0xa1] v_subb_u32 v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. // NOGFX9: error: instruction not supported on this GPU -// VI: v_subbrev_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x3c,0x02,0x01,0x09,0xa1] +// VI: v_subbrev_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x3c,0x02,0x01,0x09,0xa1] v_subbrev_u32 v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. // NOVI: error: instruction not supported on this GPU -// GFX9: v_add_co_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x32,0x02,0x01,0x09,0xa1] +// GFX9: v_add_co_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x32,0x02,0x01,0x09,0xa1] v_add_co_u32 v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. // NOVI: error: instruction not supported on this GPU -// GFX9: v_sub_co_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x34,0x02,0x01,0x09,0xa1] +// GFX9: v_sub_co_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x34,0x02,0x01,0x09,0xa1] v_sub_co_u32 v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. // NOVI: error: instruction not supported on this GPU -// GFX9: v_subrev_co_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x36,0x02,0x01,0x09,0xa1] +// GFX9: v_subrev_co_u32_dpp v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x36,0x02,0x01,0x09,0xa1] v_subrev_co_u32 v1, vcc, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU // NOVI: error: instruction not supported on this GPU -// GFX9: v_addc_co_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x38,0x02,0x01,0x09,0xa1] +// GFX9: v_addc_co_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x38,0x02,0x01,0x09,0xa1] v_addc_co_u32 v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU // NOVI: error: instruction not supported on this GPU -// GFX9: v_subb_co_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x3a,0x02,0x01,0x09,0xa1] +// GFX9: v_subb_co_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x3a,0x02,0x01,0x09,0xa1] v_subb_co_u32 v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: instruction not supported on this GPU // NOVI: error: instruction not supported on this GPU -// GFX9: v_subbrev_co_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x3c,0x02,0x01,0x09,0xa1] +// GFX9: v_subbrev_co_u32_dpp v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x3c,0x02,0x01,0x09,0xa1] v_subbrev_co_u32 v1, vcc, v2, v3, vcc row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 // NOSICI: error: not a valid operand. Index: llvm/test/MC/AMDGPU/vop_dpp_expr.s =================================================================== --- llvm/test/MC/AMDGPU/vop_dpp_expr.s +++ llvm/test/MC/AMDGPU/vop_dpp_expr.s @@ -33,4 +33,4 @@ // VI9: v_mov_b32_dpp v0, v0 row_bcast:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x42,0x01,0xff] v_mov_b32 v0, v0 quad_perm:[one,two+one,zero,2-one] row_mask:2*5 bank_mask:0x2-one bound_ctrl:1-1 -// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xa1] +// VI9: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xa1] Index: llvm/test/MC/Disassembler/AMDGPU/dl-insts.txt =================================================================== --- llvm/test/MC/Disassembler/AMDGPU/dl-insts.txt +++ llvm/test/MC/Disassembler/AMDGPU/dl-insts.txt @@ -259,7 +259,7 @@ # CHECK: v_fmac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x76,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x76,0x01,0xe4,0x00,0x0f -# CHECK: v_fmac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x76,0x01,0xe4,0x08,0x00] +# CHECK: v_fmac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x76,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x76,0x01,0xe4,0x08,0x00 # CHECK: v_fmac_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x76,0x01,0xe4,0x10,0x00] Index: llvm/test/MC/Disassembler/AMDGPU/dpp_vi.txt =================================================================== --- llvm/test/MC/Disassembler/AMDGPU/dpp_vi.txt +++ llvm/test/MC/Disassembler/AMDGPU/dpp_vi.txt @@ -36,7 +36,7 @@ # VI: v_mov_b32_dpp v0, v0 row_bcast:31 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x43,0x01,0xff] 0xfa 0x02 0x00 0x7e 0x00 0x43 0x01 0xff -# VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xa1] +# VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xa1] 0xfa 0x02 0x00 0x7e 0x00 0x4d 0x08 0xa1 # VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0xf ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x00,0xaf] @@ -45,52 +45,52 @@ # VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0x1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x00,0xf1] 0xfa 0x02 0x00 0x7e 0x00 0x4d 0x00 0xf1 -# VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0xf bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xff] +# VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0xf bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xff] 0xfa 0x02 0x00 0x7e 0x00 0x4d 0x08 0xff # VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0x1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x00,0xa1] 0xfa 0x02 0x00 0x7e 0x00 0x4d 0x00 0xa1 -# VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0xf bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xaf] +# VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xa bank_mask:0xf bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xaf] 0xfa 0x02 0x00 0x7e 0x00 0x4d 0x08 0xaf -# VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xf1] +# VI: v_mov_b32_dpp v0, v0 quad_perm:[1,3,0,1] row_mask:0xf bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x4d,0x08,0xf1] 0xfa 0x02 0x00 0x7e 0x00 0x4d 0x08 0xf1 -# VI: v_cvt_u32_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x0e,0x00,0x7e,0x00,0x01,0x09,0xa1] +# VI: v_cvt_u32_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x0e,0x00,0x7e,0x00,0x01,0x09,0xa1] 0xfa 0x0e 0x00 0x7e 0x00 0x01 0x09 0xa1 -# VI: v_fract_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x36,0x00,0x7e,0x00,0x01,0x09,0xa1] +# VI: v_fract_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x36,0x00,0x7e,0x00,0x01,0x09,0xa1] 0xfa 0x36 0x00 0x7e 0x00 0x01 0x09 0xa1 -# VI: v_sin_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x52,0x00,0x7e,0x00,0x01,0x09,0xa1] +# VI: v_sin_f32_dpp v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x52,0x00,0x7e,0x00,0x01,0x09,0xa1] 0xfa 0x52 0x00 0x7e 0x00 0x01 0x09 0xa1 -# VI: v_add_f32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x09,0xa1] +# VI: v_add_f32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x09,0xa1] 0xfa 0x00 0x00 0x02 0x00 0x01 0x09 0xa1 -# VI: v_min_f32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x14,0x00,0x01,0x09,0xa1] +# VI: v_min_f32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x14,0x00,0x01,0x09,0xa1] 0xfa 0x00 0x00 0x14 0x00 0x01 0x09 0xa1 -# VI: v_and_b32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x26,0x00,0x01,0x09,0xa1] +# VI: v_and_b32_dpp v0, v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x26,0x00,0x01,0x09,0xa1] 0xfa 0x00 0x00 0x26 0x00 0x01 0x09 0xa1 -# VI: v_add_f32_dpp v0, -v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x19,0xa1] +# VI: v_add_f32_dpp v0, -v0, v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x19,0xa1] 0xfa 0x00 0x00 0x02 0x00 0x01 0x19 0xa1 -# VI: v_add_f32_dpp v0, v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x89,0xa1] +# VI: v_add_f32_dpp v0, v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x89,0xa1] 0xfa 0x00 0x00 0x02 0x00 0x01 0x89 0xa1 -# VI: v_add_f32_dpp v0, -v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x99,0xa1] +# VI: v_add_f32_dpp v0, -v0, |v0| row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x99,0xa1] 0xfa 0x00 0x00 0x02 0x00 0x01 0x99 0xa1 -# VI: v_add_f32_dpp v0, |v0|, -v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x69,0xa1] +# VI: v_add_f32_dpp v0, |v0|, -v0 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x00,0x00,0x02,0x00,0x01,0x69,0xa1] 0xfa 0x00 0x00 0x02 0x00 0x01 0x69 0xa1 # VI: v_mac_f32_dpp v76, v76, v114 quad_perm:[2,3,0,1] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xe4,0x98,0x2c,0x4c,0x4e,0x00,0xff] 0xfa 0xe4 0x98 0x2c 0x4c 0x4e 0x00 0xff -# VI: v_mac_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x06,0x02,0x46,0x02,0x01,0x09,0xa1] +# VI: v_mac_f16_dpp v1, v2, v3 row_shl:1 row_mask:0xa bank_mask:0x1 bound_ctrl:1 ; encoding: [0xfa,0x06,0x02,0x46,0x02,0x01,0x09,0xa1] 0xfa 0x06 0x02 0x46 0x02 0x01 0x09 0xa1 # VI: v_cndmask_b32_dpp v5, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x00,0x01,0xe4,0x00,0x00] Index: llvm/test/MC/Disassembler/AMDGPU/gfx10_dasm_all.txt =================================================================== --- llvm/test/MC/Disassembler/AMDGPU/gfx10_dasm_all.txt +++ llvm/test/MC/Disassembler/AMDGPU/gfx10_dasm_all.txt @@ -20207,7 +20207,7 @@ # GFX10: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x64,0x01,0xe4,0x00,0x00 -# GFX10: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00] +# GFX10: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00 # GFX10: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x00,0x01] @@ -20546,7 +20546,7 @@ # GFX10: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x06,0x01,0xe4,0x00,0x00 -# GFX10: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00] +# GFX10: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00 # GFX10: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x00,0x01] @@ -21767,7 +21767,7 @@ # GFX10: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x36,0x01,0xe4,0x00,0x00 -# GFX10: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00] +# GFX10: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00 # GFX10: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x00,0x01] @@ -22262,7 +22262,7 @@ # GFX10: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x30,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x30,0x01,0xe4,0x00,0x00 -# GFX10: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x30,0x01,0xe4,0x08,0x00] +# GFX10: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x30,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x30,0x01,0xe4,0x08,0x00 # GFX10: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x30,0x01,0xe4,0x00,0x01] @@ -23174,7 +23174,7 @@ # GFX10: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x70,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x70,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x70,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x70,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x70,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x70,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -23411,7 +23411,7 @@ # GFX10: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xb8,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xb8,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xb8,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xb8,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xb8,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xb8,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -23660,7 +23660,7 @@ # GFX10: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -63474,7 +63474,7 @@ # GFX10: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -63723,7 +63723,7 @@ # GFX10: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x6c,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x6c,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x6c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x6c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x6c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x6c,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -64629,7 +64629,7 @@ # GFX10: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -64899,7 +64899,7 @@ # GFX10: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xa2,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xa2,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xa2,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xa2,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xa2,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xa2,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -65139,7 +65139,7 @@ # GFX10: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xa0,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xa0,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xa0,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xa0,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xa0,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xa0,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -65379,7 +65379,7 @@ # GFX10: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -65736,7 +65736,7 @@ # GFX10: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -65997,7 +65997,7 @@ # GFX10: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -66258,7 +66258,7 @@ # GFX10: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -66519,7 +66519,7 @@ # GFX10: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -66780,7 +66780,7 @@ # GFX10: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -67041,7 +67041,7 @@ # GFX10: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -67623,7 +67623,7 @@ # GFX10: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -67875,7 +67875,7 @@ # GFX10: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xa6,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xa6,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xa6,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xa6,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xa6,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xa6,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -68124,7 +68124,7 @@ # GFX10: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -68466,7 +68466,7 @@ # GFX10: v_cvt_norm_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xc6,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xc6,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_norm_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xc6,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_norm_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xc6,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xc6,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_norm_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc6,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -68715,7 +68715,7 @@ # GFX10: v_cvt_norm_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xc8,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xc8,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_norm_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xc8,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_norm_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xc8,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xc8,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_norm_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc8,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -68964,7 +68964,7 @@ # GFX10: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -70107,7 +70107,7 @@ # GFX10: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -70359,7 +70359,7 @@ # GFX10: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xa4,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xa4,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xa4,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xa4,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xa4,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xa4,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -70608,7 +70608,7 @@ # GFX10: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -71615,7 +71615,7 @@ # GFX10: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xb0,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xb0,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xb0,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xb0,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xb0,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xb0,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -71864,7 +71864,7 @@ # GFX10: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x4a,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x4a,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x4a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x4a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x4a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x4a,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -72134,7 +72134,7 @@ # GFX10: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -72374,7 +72374,7 @@ # GFX10: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -72614,7 +72614,7 @@ # GFX10: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -72851,7 +72851,7 @@ # GFX10: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xb6,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xb6,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xb6,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xb6,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xb6,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xb6,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -73100,7 +73100,7 @@ # GFX10: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -74207,7 +74207,7 @@ # GFX10: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xbe,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xbe,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xbe,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xbe,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xbe,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xbe,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -74456,7 +74456,7 @@ # GFX10: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -74822,7 +74822,7 @@ # GFX10: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xb4,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xb4,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xb4,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xb4,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xb4,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xb4,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -75071,7 +75071,7 @@ # GFX10: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -75413,7 +75413,7 @@ # GFX10: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xb2,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xb2,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xb2,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xb2,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xb2,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xb2,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -75662,7 +75662,7 @@ # GFX10: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -76103,7 +76103,7 @@ # GFX10: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x76,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x76,0x01,0xe4,0x00,0x00 -# GFX10: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x76,0x01,0xe4,0x08,0x00] +# GFX10: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x76,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x76,0x01,0xe4,0x08,0x00 # GFX10: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x76,0x01,0xe4,0x00,0x01] @@ -76739,7 +76739,7 @@ # GFX10: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xae,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xae,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xae,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xae,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xae,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xae,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -76988,7 +76988,7 @@ # GFX10: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -77564,7 +77564,7 @@ # GFX10: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x34,0x01,0xe4,0x00,0x00 -# GFX10: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00] +# GFX10: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00 # GFX10: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x00,0x01] @@ -78017,7 +78017,7 @@ # GFX10: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x00,0x00 -# GFX10: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00] +# GFX10: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00 # GFX10: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x00,0x01] @@ -80775,7 +80775,7 @@ # GFX10: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x72,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x72,0x01,0xe4,0x00,0x00 -# GFX10: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x72,0x01,0xe4,0x08,0x00] +# GFX10: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x72,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x72,0x01,0xe4,0x08,0x00 # GFX10: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x72,0x01,0xe4,0x00,0x01] @@ -81114,7 +81114,7 @@ # GFX10: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x20,0x01,0xe4,0x00,0x00 -# GFX10: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00] +# GFX10: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00 # GFX10: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x00,0x01] @@ -81651,7 +81651,7 @@ # GFX10: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x24,0x01,0xe4,0x00,0x00 -# GFX10: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00] +# GFX10: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00 # GFX10: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x00,0x01] @@ -82035,7 +82035,7 @@ # GFX10: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x28,0x01,0xe4,0x00,0x00 -# GFX10: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00] +# GFX10: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00 # GFX10: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x00,0x01] @@ -84159,7 +84159,7 @@ # GFX10: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x74,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x74,0x01,0xe4,0x00,0x00 -# GFX10: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x74,0x01,0xe4,0x08,0x00] +# GFX10: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x74,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x74,0x01,0xe4,0x08,0x00 # GFX10: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x74,0x01,0xe4,0x00,0x01] @@ -84498,7 +84498,7 @@ # GFX10: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x00,0x00 -# GFX10: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00] +# GFX10: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00 # GFX10: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x00,0x01] @@ -85035,7 +85035,7 @@ # GFX10: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x22,0x01,0xe4,0x00,0x00 -# GFX10: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00] +# GFX10: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00 # GFX10: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x00,0x01] @@ -85419,7 +85419,7 @@ # GFX10: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x26,0x01,0xe4,0x00,0x00 -# GFX10: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00] +# GFX10: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00 # GFX10: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x00,0x01] @@ -85725,7 +85725,7 @@ # GFX10: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -86376,7 +86376,7 @@ # GFX10: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x00,0x00 -# GFX10: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x08,0x00] +# GFX10: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x08,0x00 # GFX10: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x00,0x01] @@ -86715,7 +86715,7 @@ # GFX10: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x10,0x01,0xe4,0x00,0x00 -# GFX10: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00] +# GFX10: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00 # GFX10: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x00,0x01] @@ -87258,7 +87258,7 @@ # GFX10: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x14,0x01,0xe4,0x00,0x00 -# GFX10: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00] +# GFX10: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00 # GFX10: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x00,0x01] @@ -87648,7 +87648,7 @@ # GFX10: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x18,0x01,0xe4,0x00,0x00 -# GFX10: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00] +# GFX10: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00 # GFX10: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x00,0x01] @@ -87954,7 +87954,7 @@ # GFX10: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x12,0x01,0xe4,0x00,0x00 -# GFX10: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00] +# GFX10: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00 # GFX10: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x00,0x01] @@ -88269,7 +88269,7 @@ # GFX10: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x00,0x00 -# GFX10: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00] +# GFX10: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00 # GFX10: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x00,0x01] @@ -88785,7 +88785,7 @@ # GFX10: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x16,0x01,0xe4,0x00,0x00 -# GFX10: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00] +# GFX10: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00 # GFX10: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x00,0x01] @@ -89256,7 +89256,7 @@ # GFX10: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x6e,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x6e,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x6e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x6e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x6e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x6e,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -89607,7 +89607,7 @@ # GFX10: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x38,0x01,0xe4,0x00,0x00 -# GFX10: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00] +# GFX10: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00 # GFX10: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x00,0x01] @@ -90486,7 +90486,7 @@ # GFX10: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xa8,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xa8,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xa8,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xa8,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xa8,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xa8,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -90735,7 +90735,7 @@ # GFX10: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -91104,7 +91104,7 @@ # GFX10: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -91410,7 +91410,7 @@ # GFX10: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xbc,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xbc,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xbc,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xbc,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xbc,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xbc,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -91659,7 +91659,7 @@ # GFX10: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -92022,7 +92022,7 @@ # GFX10: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xac,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xac,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xac,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xac,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xac,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xac,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -92271,7 +92271,7 @@ # GFX10: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -93132,7 +93132,7 @@ # GFX10: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xc0,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xc0,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xc0,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xc0,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xc0,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc0,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -93381,7 +93381,7 @@ # GFX10: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x6a,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x6a,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x6a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x6a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x6a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x6a,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -93651,7 +93651,7 @@ # GFX10: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xaa,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xaa,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xaa,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xaa,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xaa,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xaa,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -93900,7 +93900,7 @@ # GFX10: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -94596,7 +94596,7 @@ # GFX10: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x66,0x01,0xe4,0x00,0x00 -# GFX10: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00] +# GFX10: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00 # GFX10: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x00,0x01] @@ -94935,7 +94935,7 @@ # GFX10: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x08,0x01,0xe4,0x00,0x00 -# GFX10: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00] +# GFX10: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00 # GFX10: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x00,0x01] @@ -96093,7 +96093,7 @@ # GFX10: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x68,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x68,0x01,0xe4,0x00,0x00 -# GFX10: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x68,0x01,0xe4,0x08,0x00] +# GFX10: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x68,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x68,0x01,0xe4,0x08,0x00 # GFX10: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x68,0x01,0xe4,0x00,0x01] @@ -96432,7 +96432,7 @@ # GFX10: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x00,0x00 -# GFX10: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00] +# GFX10: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00 # GFX10: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x00,0x01] @@ -97131,7 +97131,7 @@ # GFX10: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0xba,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0xba,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -97380,7 +97380,7 @@ # GFX10: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x00,0x00] 0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x00,0x00 -# GFX10: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# GFX10: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00 # GFX10: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x00,0x01] @@ -97890,7 +97890,7 @@ # GFX10: v_xnor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x00,0x00 -# GFX10: v_xnor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00] +# GFX10: v_xnor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00 # GFX10: v_xnor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x00,0x01] @@ -98316,7 +98316,7 @@ # GFX10: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x00,0x00] 0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x00,0x00 -# GFX10: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00] +# GFX10: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00 # GFX10: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x00,0x01] Index: llvm/test/MC/Disassembler/AMDGPU/gfx10_dasm_dpp16.txt =================================================================== --- llvm/test/MC/Disassembler/AMDGPU/gfx10_dasm_dpp16.txt +++ llvm/test/MC/Disassembler/AMDGPU/gfx10_dasm_dpp16.txt @@ -67,7 +67,7 @@ # GFX10: v_mov_b32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0x1b,0x00,0x0f] 0xfa,0x02,0x0a,0x7e,0x01,0x1b,0x00,0x0f -# GFX10: v_mov_b32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0x1b,0x08,0x00] +# GFX10: v_mov_b32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0x1b,0x08,0x00] 0xfa,0x02,0x0a,0x7e,0x01,0x1b,0x08,0x00 # GFX10: v_mov_b32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 fi:1 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0x1b,0x04,0x00] @@ -639,7 +639,7 @@ # GFX10: v_add_nc_u32_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x00,0x00] 0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x00,0x00 -# GFX10: v_add_nc_u32_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x08,0x00] +# GFX10: v_add_nc_u32_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x08,0x00] 0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x08,0x00 # GFX10: v_add_nc_u32_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0x0 bank_mask:0x0 fi:1 ; encoding: [0xfa,0x04,0x0a,0x4a,0x01,0x1b,0x04,0x00] Index: llvm/test/MC/Disassembler/AMDGPU/gfx8_dasm_all.txt =================================================================== --- llvm/test/MC/Disassembler/AMDGPU/gfx8_dasm_all.txt +++ llvm/test/MC/Disassembler/AMDGPU/gfx8_dasm_all.txt @@ -94176,7 +94176,7 @@ # CHECK: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_i32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x0a,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -94308,7 +94308,7 @@ # CHECK: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_u32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x0c,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -94440,7 +94440,7 @@ # CHECK: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_u32_f32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x0e,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -94572,7 +94572,7 @@ # CHECK: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_u32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -94710,7 +94710,7 @@ # CHECK: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_i32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -94851,7 +94851,7 @@ # CHECK: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f16_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -94992,7 +94992,7 @@ # CHECK: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -95130,7 +95130,7 @@ # CHECK: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_rpi_i32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -95268,7 +95268,7 @@ # CHECK: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_flr_i32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -95406,7 +95406,7 @@ # CHECK: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_ubyte0_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x22,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -95538,7 +95538,7 @@ # CHECK: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_ubyte1_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x24,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -95670,7 +95670,7 @@ # CHECK: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_ubyte2_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x26,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -95802,7 +95802,7 @@ # CHECK: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_ubyte3_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x28,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -95934,7 +95934,7 @@ # CHECK: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_fract_f32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x36,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -96069,7 +96069,7 @@ # CHECK: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_fract_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -96210,7 +96210,7 @@ # CHECK: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_trunc_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -96351,7 +96351,7 @@ # CHECK: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ceil_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -96492,7 +96492,7 @@ # CHECK: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rndne_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -96633,7 +96633,7 @@ # CHECK: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_floor_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -96774,7 +96774,7 @@ # CHECK: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_exp_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -96915,7 +96915,7 @@ # CHECK: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_log_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -97056,7 +97056,7 @@ # CHECK: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rcp_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -97197,7 +97197,7 @@ # CHECK: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rcp_iflag_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -97338,7 +97338,7 @@ # CHECK: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rsq_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -97479,7 +97479,7 @@ # CHECK: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_sqrt_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -97620,7 +97620,7 @@ # CHECK: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_sin_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -97761,7 +97761,7 @@ # CHECK: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cos_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -97896,7 +97896,7 @@ # CHECK: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_bfrev_b32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x58,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -98025,7 +98025,7 @@ # CHECK: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ffbh_u32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x5a,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -98154,7 +98154,7 @@ # CHECK: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ffbl_b32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x5c,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -98283,7 +98283,7 @@ # CHECK: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ffbh_i32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x5e,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -98412,7 +98412,7 @@ # CHECK: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_exp_i32_f32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x66,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -98544,7 +98544,7 @@ # CHECK: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_exp_i32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -98685,7 +98685,7 @@ # CHECK: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_mant_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -98823,7 +98823,7 @@ # CHECK: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f16_i16_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x74,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -98955,7 +98955,7 @@ # CHECK: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_u16_f16_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x76,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -99087,7 +99087,7 @@ # CHECK: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_u16_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -99225,7 +99225,7 @@ # CHECK: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_i16_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -99366,7 +99366,7 @@ # CHECK: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rcp_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -99507,7 +99507,7 @@ # CHECK: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_sqrt_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -99648,7 +99648,7 @@ # CHECK: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rsq_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -99789,7 +99789,7 @@ # CHECK: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_log_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -99930,7 +99930,7 @@ # CHECK: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_exp_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -100071,7 +100071,7 @@ # CHECK: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_mant_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -100209,7 +100209,7 @@ # CHECK: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_exp_i16_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -100350,7 +100350,7 @@ # CHECK: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_floor_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -100491,7 +100491,7 @@ # CHECK: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ceil_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -100632,7 +100632,7 @@ # CHECK: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_trunc_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -100773,7 +100773,7 @@ # CHECK: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rndne_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -100914,7 +100914,7 @@ # CHECK: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_fract_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -101055,7 +101055,7 @@ # CHECK: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_sin_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -101196,7 +101196,7 @@ # CHECK: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cos_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -101337,7 +101337,7 @@ # CHECK: v_exp_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_exp_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_exp_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_exp_legacy_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -101478,7 +101478,7 @@ # CHECK: v_log_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_log_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_log_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_log_legacy_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -101649,7 +101649,7 @@ # CHECK: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x02,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x02,0x01,0xe4,0x00,0x0f -# CHECK: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x02,0x01,0xe4,0x08,0x00] +# CHECK: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x02,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x02,0x01,0xe4,0x08,0x00 # CHECK: v_add_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x02,0x01,0xe4,0x10,0x00] @@ -101826,7 +101826,7 @@ # CHECK: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x04,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00 # CHECK: v_sub_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x10,0x00] @@ -102003,7 +102003,7 @@ # CHECK: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x06,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x10,0x00] @@ -102180,7 +102180,7 @@ # CHECK: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x08,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00 # CHECK: v_mul_legacy_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x10,0x00] @@ -102357,7 +102357,7 @@ # CHECK: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00 # CHECK: v_mul_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x10,0x00] @@ -102528,7 +102528,7 @@ # CHECK: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x08,0x00 # CHECK: v_mul_hi_i32_i24_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x0e,0x01,0x06,0x06,0x06] @@ -102684,7 +102684,7 @@ # CHECK: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00 # CHECK: v_mul_u32_u24_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x10,0x01,0x06,0x06,0x06] @@ -102843,7 +102843,7 @@ # CHECK: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x10,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00 # CHECK: v_mul_hi_u32_u24_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x12,0x01,0x06,0x06,0x06] @@ -102999,7 +102999,7 @@ # CHECK: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x12,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00 # CHECK: v_min_f32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x14,0x01,0x06,0x06,0x06] @@ -103164,7 +103164,7 @@ # CHECK: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x14,0x01,0xe4,0x00,0x0f -# CHECK: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00] +# CHECK: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00 # CHECK: v_min_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x10,0x00] @@ -103341,7 +103341,7 @@ # CHECK: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x16,0x01,0xe4,0x00,0x0f -# CHECK: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00] +# CHECK: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00 # CHECK: v_max_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x10,0x00] @@ -103509,7 +103509,7 @@ # CHECK: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x18,0x01,0xe4,0x00,0x0f -# CHECK: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00] +# CHECK: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00 # CHECK: v_max_i32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x1a,0x01,0x06,0x06,0x06] @@ -103665,7 +103665,7 @@ # CHECK: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x00,0x0f -# CHECK: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00] +# CHECK: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00 # CHECK: v_min_u32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x1c,0x01,0x06,0x06,0x06] @@ -103821,7 +103821,7 @@ # CHECK: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x00,0x0f -# CHECK: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x08,0x00] +# CHECK: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x08,0x00 # CHECK: v_max_u32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x1e,0x01,0x06,0x06,0x06] @@ -103977,7 +103977,7 @@ # CHECK: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x00,0x0f -# CHECK: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00] +# CHECK: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00 # CHECK: v_lshrrev_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x20,0x01,0x06,0x06,0x06] @@ -104133,7 +104133,7 @@ # CHECK: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x20,0x01,0xe4,0x00,0x0f -# CHECK: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00] +# CHECK: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00 # CHECK: v_ashrrev_i32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x22,0x01,0x06,0x06,0x06] @@ -104289,7 +104289,7 @@ # CHECK: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x22,0x01,0xe4,0x00,0x0f -# CHECK: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00] +# CHECK: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00 # CHECK: v_lshlrev_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x24,0x01,0x06,0x06,0x06] @@ -104445,7 +104445,7 @@ # CHECK: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x24,0x01,0xe4,0x00,0x0f -# CHECK: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00] +# CHECK: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00 # CHECK: v_and_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x26,0x01,0x06,0x06,0x06] @@ -104601,7 +104601,7 @@ # CHECK: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x26,0x01,0xe4,0x00,0x0f -# CHECK: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00] +# CHECK: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00 # CHECK: v_or_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x28,0x01,0x06,0x06,0x06] @@ -104757,7 +104757,7 @@ # CHECK: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x28,0x01,0xe4,0x00,0x0f -# CHECK: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00] +# CHECK: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00 # CHECK: v_xor_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x2a,0x01,0x06,0x06,0x06] @@ -104913,7 +104913,7 @@ # CHECK: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x00,0x0f -# CHECK: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x08,0x00] +# CHECK: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x08,0x00 # CHECK: v_mac_f32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x2c,0x01,0x06,0x06,0x06] @@ -105060,7 +105060,7 @@ # CHECK: v_mac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x00,0x0f -# CHECK: v_mac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00] +# CHECK: v_mac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00 # CHECK: v_mac_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x10,0x00] @@ -105231,7 +105231,7 @@ # CHECK: v_add_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x32,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x32,0x01,0xe4,0x00,0x0f -# CHECK: v_add_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x32,0x01,0xe4,0x08,0x00] +# CHECK: v_add_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x32,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x32,0x01,0xe4,0x08,0x00 # CHECK: v_sub_u32_sdwa v5, vcc, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x34,0x01,0x06,0x06,0x06] @@ -105390,7 +105390,7 @@ # CHECK: v_sub_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x34,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_u32_sdwa v5, vcc, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x36,0x01,0x06,0x06,0x06] @@ -105549,7 +105549,7 @@ # CHECK: v_subrev_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x36,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00 # CHECK: v_addc_u32_sdwa v5, vcc, v1, v2, vcc dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x38,0x01,0x06,0x06,0x06] @@ -105708,7 +105708,7 @@ # CHECK: v_addc_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x38,0x01,0xe4,0x00,0x0f -# CHECK: v_addc_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00] +# CHECK: v_addc_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00 # CHECK: v_subb_u32_sdwa v5, vcc, v1, v2, vcc dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x3a,0x01,0x06,0x06,0x06] @@ -105867,7 +105867,7 @@ # CHECK: v_subb_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x00,0x0f -# CHECK: v_subb_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00] +# CHECK: v_subb_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00 # CHECK: v_subbrev_u32_sdwa v5, vcc, v1, v2, vcc dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x3c,0x01,0x06,0x06,0x06] @@ -106026,7 +106026,7 @@ # CHECK: v_subbrev_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x00,0x0f -# CHECK: v_subbrev_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00] +# CHECK: v_subbrev_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00 # CHECK: v_add_f16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x3e,0x01,0x06,0x06,0x06] @@ -106191,7 +106191,7 @@ # CHECK: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x00,0x0f -# CHECK: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x08,0x00] +# CHECK: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x08,0x00 # CHECK: v_add_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x10,0x00] @@ -106368,7 +106368,7 @@ # CHECK: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x40,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x40,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x40,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x40,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x40,0x01,0xe4,0x08,0x00 # CHECK: v_sub_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x40,0x01,0xe4,0x10,0x00] @@ -106545,7 +106545,7 @@ # CHECK: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x42,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x42,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x42,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x42,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x42,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x42,0x01,0xe4,0x10,0x00] @@ -106722,7 +106722,7 @@ # CHECK: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x44,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x44,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x44,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x44,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x44,0x01,0xe4,0x08,0x00 # CHECK: v_mul_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x44,0x01,0xe4,0x10,0x00] @@ -106881,7 +106881,7 @@ # CHECK: v_mac_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x46,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x46,0x01,0xe4,0x00,0x0f -# CHECK: v_mac_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x46,0x01,0xe4,0x08,0x00] +# CHECK: v_mac_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x46,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x46,0x01,0xe4,0x08,0x00 # CHECK: v_mac_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x46,0x01,0xe4,0x10,0x00] @@ -107052,7 +107052,7 @@ # CHECK: v_add_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x00,0x0f -# CHECK: v_add_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x08,0x00] +# CHECK: v_add_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x08,0x00 # CHECK: v_sub_u16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x4e,0x01,0x06,0x06,0x06] @@ -107211,7 +107211,7 @@ # CHECK: v_sub_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_u16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x50,0x01,0x06,0x06,0x06] @@ -107370,7 +107370,7 @@ # CHECK: v_subrev_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x50,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x50,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x50,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x50,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x50,0x01,0xe4,0x08,0x00 # CHECK: v_mul_lo_u16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x52,0x01,0x06,0x06,0x06] @@ -107526,7 +107526,7 @@ # CHECK: v_mul_lo_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x52,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x52,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_lo_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x52,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_lo_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x52,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x52,0x01,0xe4,0x08,0x00 # CHECK: v_lshlrev_b16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x54,0x01,0x06,0x06,0x06] @@ -107682,7 +107682,7 @@ # CHECK: v_lshlrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x54,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x54,0x01,0xe4,0x00,0x0f -# CHECK: v_lshlrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x54,0x01,0xe4,0x08,0x00] +# CHECK: v_lshlrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x54,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x54,0x01,0xe4,0x08,0x00 # CHECK: v_lshrrev_b16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x56,0x01,0x06,0x06,0x06] @@ -107838,7 +107838,7 @@ # CHECK: v_lshrrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x56,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x56,0x01,0xe4,0x00,0x0f -# CHECK: v_lshrrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x56,0x01,0xe4,0x08,0x00] +# CHECK: v_lshrrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x56,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x56,0x01,0xe4,0x08,0x00 # CHECK: v_ashrrev_i16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x58,0x01,0x06,0x06,0x06] @@ -107994,7 +107994,7 @@ # CHECK: v_ashrrev_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x58,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x58,0x01,0xe4,0x00,0x0f -# CHECK: v_ashrrev_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x58,0x01,0xe4,0x08,0x00] +# CHECK: v_ashrrev_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x58,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x58,0x01,0xe4,0x08,0x00 # CHECK: v_max_f16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x5a,0x01,0x06,0x06,0x06] @@ -108159,7 +108159,7 @@ # CHECK: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x00,0x0f -# CHECK: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x08,0x00] +# CHECK: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x08,0x00 # CHECK: v_max_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x10,0x00] @@ -108336,7 +108336,7 @@ # CHECK: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x00,0x0f -# CHECK: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x08,0x00] +# CHECK: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x08,0x00 # CHECK: v_min_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x10,0x00] @@ -108504,7 +108504,7 @@ # CHECK: v_max_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x00,0x0f -# CHECK: v_max_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x08,0x00] +# CHECK: v_max_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x08,0x00 # CHECK: v_max_i16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x60,0x01,0x06,0x06,0x06] @@ -108660,7 +108660,7 @@ # CHECK: v_max_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x60,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x60,0x01,0xe4,0x00,0x0f -# CHECK: v_max_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x60,0x01,0xe4,0x08,0x00] +# CHECK: v_max_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x60,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x60,0x01,0xe4,0x08,0x00 # CHECK: v_min_u16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x62,0x01,0x06,0x06,0x06] @@ -108816,7 +108816,7 @@ # CHECK: v_min_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x62,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x62,0x01,0xe4,0x00,0x0f -# CHECK: v_min_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x62,0x01,0xe4,0x08,0x00] +# CHECK: v_min_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x62,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x62,0x01,0xe4,0x08,0x00 # CHECK: v_min_i16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x64,0x01,0x06,0x06,0x06] @@ -108972,7 +108972,7 @@ # CHECK: v_min_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x64,0x01,0xe4,0x00,0x0f -# CHECK: v_min_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00] +# CHECK: v_min_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00 # CHECK: v_ldexp_f16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x66,0x01,0x06,0x06,0x06] @@ -109134,7 +109134,7 @@ # CHECK: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x66,0x01,0xe4,0x00,0x0f -# CHECK: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00] +# CHECK: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00 # CHECK: v_ldexp_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x10,0x00] Index: llvm/test/MC/Disassembler/AMDGPU/gfx9_dasm_all.txt =================================================================== --- llvm/test/MC/Disassembler/AMDGPU/gfx9_dasm_all.txt +++ llvm/test/MC/Disassembler/AMDGPU/gfx9_dasm_all.txt @@ -82485,7 +82485,7 @@ # CHECK: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_mov_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x02,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_i32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x0a,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -82665,7 +82665,7 @@ # CHECK: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_u32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x0c,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -82845,7 +82845,7 @@ # CHECK: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_u32_f32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x0e,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -83019,7 +83019,7 @@ # CHECK: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_u32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_u32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x0e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -83199,7 +83199,7 @@ # CHECK: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_i32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x10,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -83388,7 +83388,7 @@ # CHECK: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f16_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f16_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x14,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -83577,7 +83577,7 @@ # CHECK: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x16,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -83754,7 +83754,7 @@ # CHECK: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_rpi_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_rpi_i32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x18,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -83931,7 +83931,7 @@ # CHECK: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_flr_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_flr_i32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x1a,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -84117,7 +84117,7 @@ # CHECK: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_off_f32_i4_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x1c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_ubyte0_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x22,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -84297,7 +84297,7 @@ # CHECK: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_ubyte0_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x22,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_ubyte1_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x24,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -84477,7 +84477,7 @@ # CHECK: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_ubyte1_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x24,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_ubyte2_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x26,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -84657,7 +84657,7 @@ # CHECK: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_ubyte2_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x26,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f32_ubyte3_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x28,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -84837,7 +84837,7 @@ # CHECK: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f32_ubyte3_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x28,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_fract_f32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x36,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -85020,7 +85020,7 @@ # CHECK: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_fract_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_fract_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x36,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -85209,7 +85209,7 @@ # CHECK: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_trunc_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_trunc_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x38,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -85398,7 +85398,7 @@ # CHECK: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ceil_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ceil_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x3a,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -85587,7 +85587,7 @@ # CHECK: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rndne_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rndne_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x3c,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -85776,7 +85776,7 @@ # CHECK: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_floor_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_floor_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x3e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -85965,7 +85965,7 @@ # CHECK: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_exp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_exp_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x40,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -86154,7 +86154,7 @@ # CHECK: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_log_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_log_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -86343,7 +86343,7 @@ # CHECK: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rcp_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rcp_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x44,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -86532,7 +86532,7 @@ # CHECK: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rcp_iflag_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rcp_iflag_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x46,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -86721,7 +86721,7 @@ # CHECK: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rsq_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rsq_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x48,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -86910,7 +86910,7 @@ # CHECK: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_sqrt_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_sqrt_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x4e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -87099,7 +87099,7 @@ # CHECK: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_sin_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_sin_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x52,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -87288,7 +87288,7 @@ # CHECK: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cos_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cos_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x54,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -87462,7 +87462,7 @@ # CHECK: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_not_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x56,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_bfrev_b32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x58,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -87630,7 +87630,7 @@ # CHECK: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_bfrev_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x58,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ffbh_u32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x5a,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -87798,7 +87798,7 @@ # CHECK: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ffbh_u32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x5a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ffbl_b32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x5c,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -87966,7 +87966,7 @@ # CHECK: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ffbl_b32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x5c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ffbh_i32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x5e,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -88134,7 +88134,7 @@ # CHECK: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ffbh_i32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x5e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_exp_i32_f32_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x66,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -88305,7 +88305,7 @@ # CHECK: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_frexp_exp_i32_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_exp_i32_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x66,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -88494,7 +88494,7 @@ # CHECK: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_frexp_mant_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_mant_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x68,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -88665,7 +88665,7 @@ # CHECK: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f16_u16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x72,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_f16_i16_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x74,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -88830,7 +88830,7 @@ # CHECK: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_f16_i16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x74,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_u16_f16_sdwa v5, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD ; encoding: [0xf9,0x76,0x0a,0x7e,0x01,0x06,0x06,0x00] @@ -89004,7 +89004,7 @@ # CHECK: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_u16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_u16_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x76,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -89184,7 +89184,7 @@ # CHECK: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cvt_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cvt_i16_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x78,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -89364,7 +89364,7 @@ # CHECK: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rcp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rcp_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x7a,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -89544,7 +89544,7 @@ # CHECK: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_sqrt_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_sqrt_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x7c,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -89724,7 +89724,7 @@ # CHECK: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rsq_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rsq_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x7e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -89904,7 +89904,7 @@ # CHECK: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_log_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_log_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x80,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -90084,7 +90084,7 @@ # CHECK: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_exp_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_exp_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x82,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -90264,7 +90264,7 @@ # CHECK: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_frexp_mant_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_mant_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x84,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -90441,7 +90441,7 @@ # CHECK: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_frexp_exp_i16_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_frexp_exp_i16_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x86,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -90621,7 +90621,7 @@ # CHECK: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_floor_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_floor_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x88,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -90801,7 +90801,7 @@ # CHECK: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_ceil_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_ceil_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x8a,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -90981,7 +90981,7 @@ # CHECK: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_trunc_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x8c,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -91161,7 +91161,7 @@ # CHECK: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_rndne_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_rndne_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x8e,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -91341,7 +91341,7 @@ # CHECK: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_fract_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_fract_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x90,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -91521,7 +91521,7 @@ # CHECK: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_sin_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_sin_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x92,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -91701,7 +91701,7 @@ # CHECK: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_cos_f16_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x94,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -91890,7 +91890,7 @@ # CHECK: v_exp_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_exp_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_exp_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_exp_legacy_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x96,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -92079,7 +92079,7 @@ # CHECK: v_log_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x00,0x0f] 0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x00,0x0f -# CHECK: v_log_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x08,0x00] +# CHECK: v_log_legacy_f32_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x08,0x00] 0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x08,0x00 # CHECK: v_log_legacy_f32_dpp v5, -v1 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x98,0x0a,0x7e,0x01,0xe4,0x10,0x00] @@ -92298,7 +92298,7 @@ # CHECK: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x02,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x02,0x01,0xe4,0x00,0x0f -# CHECK: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x02,0x01,0xe4,0x08,0x00] +# CHECK: v_add_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x02,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x02,0x01,0xe4,0x08,0x00 # CHECK: v_add_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x02,0x01,0xe4,0x10,0x00] @@ -92523,7 +92523,7 @@ # CHECK: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x04,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00 # CHECK: v_sub_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x10,0x00] @@ -92748,7 +92748,7 @@ # CHECK: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x06,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x06,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x06,0x01,0xe4,0x10,0x00] @@ -92973,7 +92973,7 @@ # CHECK: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x08,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_legacy_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x08,0x01,0xe4,0x08,0x00 # CHECK: v_mul_legacy_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x08,0x01,0xe4,0x10,0x00] @@ -93198,7 +93198,7 @@ # CHECK: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x08,0x00 # CHECK: v_mul_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x0a,0x01,0xe4,0x10,0x00] @@ -93408,7 +93408,7 @@ # CHECK: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x0c,0x01,0xe4,0x08,0x00 # CHECK: v_mul_hi_i32_i24_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x0e,0x01,0x06,0x06,0x06] @@ -93603,7 +93603,7 @@ # CHECK: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_hi_i32_i24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x0e,0x01,0xe4,0x08,0x00 # CHECK: v_mul_u32_u24_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x10,0x01,0x06,0x06,0x06] @@ -93801,7 +93801,7 @@ # CHECK: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x10,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x10,0x01,0xe4,0x08,0x00 # CHECK: v_mul_hi_u32_u24_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x12,0x01,0x06,0x06,0x06] @@ -93996,7 +93996,7 @@ # CHECK: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x12,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_hi_u32_u24_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x12,0x01,0xe4,0x08,0x00 # CHECK: v_min_f32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x14,0x01,0x06,0x06,0x06] @@ -94209,7 +94209,7 @@ # CHECK: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x14,0x01,0xe4,0x00,0x0f -# CHECK: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00] +# CHECK: v_min_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x14,0x01,0xe4,0x08,0x00 # CHECK: v_min_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x14,0x01,0xe4,0x10,0x00] @@ -94434,7 +94434,7 @@ # CHECK: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x16,0x01,0xe4,0x00,0x0f -# CHECK: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00] +# CHECK: v_max_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x16,0x01,0xe4,0x08,0x00 # CHECK: v_max_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x16,0x01,0xe4,0x10,0x00] @@ -94641,7 +94641,7 @@ # CHECK: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x18,0x01,0xe4,0x00,0x0f -# CHECK: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00] +# CHECK: v_min_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x18,0x01,0xe4,0x08,0x00 # CHECK: v_max_i32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x1a,0x01,0x06,0x06,0x06] @@ -94836,7 +94836,7 @@ # CHECK: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x00,0x0f -# CHECK: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00] +# CHECK: v_max_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00 # CHECK: v_min_u32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x1c,0x01,0x06,0x06,0x06] @@ -95031,7 +95031,7 @@ # CHECK: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x00,0x0f -# CHECK: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x08,0x00] +# CHECK: v_min_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x1c,0x01,0xe4,0x08,0x00 # CHECK: v_max_u32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x1e,0x01,0x06,0x06,0x06] @@ -95226,7 +95226,7 @@ # CHECK: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x00,0x0f -# CHECK: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00] +# CHECK: v_max_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x1e,0x01,0xe4,0x08,0x00 # CHECK: v_lshrrev_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x20,0x01,0x06,0x06,0x06] @@ -95421,7 +95421,7 @@ # CHECK: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x20,0x01,0xe4,0x00,0x0f -# CHECK: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00] +# CHECK: v_lshrrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x20,0x01,0xe4,0x08,0x00 # CHECK: v_ashrrev_i32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x22,0x01,0x06,0x06,0x06] @@ -95616,7 +95616,7 @@ # CHECK: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x22,0x01,0xe4,0x00,0x0f -# CHECK: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00] +# CHECK: v_ashrrev_i32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x22,0x01,0xe4,0x08,0x00 # CHECK: v_lshlrev_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x24,0x01,0x06,0x06,0x06] @@ -95811,7 +95811,7 @@ # CHECK: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x24,0x01,0xe4,0x00,0x0f -# CHECK: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00] +# CHECK: v_lshlrev_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x24,0x01,0xe4,0x08,0x00 # CHECK: v_and_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x26,0x01,0x06,0x06,0x06] @@ -96006,7 +96006,7 @@ # CHECK: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x26,0x01,0xe4,0x00,0x0f -# CHECK: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00] +# CHECK: v_and_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x26,0x01,0xe4,0x08,0x00 # CHECK: v_or_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x28,0x01,0x06,0x06,0x06] @@ -96201,7 +96201,7 @@ # CHECK: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x28,0x01,0xe4,0x00,0x0f -# CHECK: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00] +# CHECK: v_or_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x28,0x01,0xe4,0x08,0x00 # CHECK: v_xor_b32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x2a,0x01,0x06,0x06,0x06] @@ -96396,7 +96396,7 @@ # CHECK: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x00,0x0f -# CHECK: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x08,0x00] +# CHECK: v_xor_b32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x2a,0x01,0xe4,0x08,0x00 # CHECK: v_mac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x00,0x00] @@ -96474,7 +96474,7 @@ # CHECK: v_mac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x00,0x0f -# CHECK: v_mac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00] +# CHECK: v_mac_f32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x08,0x00 # CHECK: v_mac_f32_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x2c,0x01,0xe4,0x10,0x00] @@ -96684,7 +96684,7 @@ # CHECK: v_add_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x32,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x32,0x01,0xe4,0x00,0x0f -# CHECK: v_add_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x32,0x01,0xe4,0x08,0x00] +# CHECK: v_add_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x32,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x32,0x01,0xe4,0x08,0x00 # CHECK: v_sub_co_u32_sdwa v5, vcc, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x34,0x01,0x06,0x06,0x06] @@ -96882,7 +96882,7 @@ # CHECK: v_sub_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x34,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x34,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_co_u32_sdwa v5, vcc, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x36,0x01,0x06,0x06,0x06] @@ -97080,7 +97080,7 @@ # CHECK: v_subrev_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x36,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_co_u32_dpp v5, vcc, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x36,0x01,0xe4,0x08,0x00 # CHECK: v_addc_co_u32_sdwa v5, vcc, v1, v2, vcc dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x38,0x01,0x06,0x06,0x06] @@ -97251,7 +97251,7 @@ # CHECK: v_addc_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x38,0x01,0xe4,0x00,0x0f -# CHECK: v_addc_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00] +# CHECK: v_addc_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x38,0x01,0xe4,0x08,0x00 # CHECK: v_subb_co_u32_sdwa v5, vcc, v1, v2, vcc dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x3a,0x01,0x06,0x06,0x06] @@ -97422,7 +97422,7 @@ # CHECK: v_subb_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x00,0x0f -# CHECK: v_subb_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00] +# CHECK: v_subb_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x3a,0x01,0xe4,0x08,0x00 # CHECK: v_subbrev_co_u32_sdwa v5, vcc, v1, v2, vcc dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x3c,0x01,0x06,0x06,0x06] @@ -97593,7 +97593,7 @@ # CHECK: v_subbrev_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x00,0x0f -# CHECK: v_subbrev_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00] +# CHECK: v_subbrev_co_u32_dpp v5, vcc, v1, v2, vcc quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x3c,0x01,0xe4,0x08,0x00 # CHECK: v_add_f16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x3e,0x01,0x06,0x06,0x06] @@ -97797,7 +97797,7 @@ # CHECK: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x00,0x0f -# CHECK: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x08,0x00] +# CHECK: v_add_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x08,0x00 # CHECK: v_add_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x3e,0x01,0xe4,0x10,0x00] @@ -98013,7 +98013,7 @@ # CHECK: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x40,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x40,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x40,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x40,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x40,0x01,0xe4,0x08,0x00 # CHECK: v_sub_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x40,0x01,0xe4,0x10,0x00] @@ -98229,7 +98229,7 @@ # CHECK: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x42,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x42,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x42,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x42,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x42,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x42,0x01,0xe4,0x10,0x00] @@ -98445,7 +98445,7 @@ # CHECK: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x44,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x44,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x44,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x44,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x44,0x01,0xe4,0x08,0x00 # CHECK: v_mul_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x44,0x01,0xe4,0x10,0x00] @@ -98535,7 +98535,7 @@ # CHECK: v_mac_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x46,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x46,0x01,0xe4,0x00,0x0f -# CHECK: v_mac_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x46,0x01,0xe4,0x08,0x00] +# CHECK: v_mac_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x46,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x46,0x01,0xe4,0x08,0x00 # CHECK: v_mac_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x46,0x01,0xe4,0x10,0x00] @@ -98739,7 +98739,7 @@ # CHECK: v_add_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x00,0x0f -# CHECK: v_add_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x08,0x00] +# CHECK: v_add_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x4c,0x01,0xe4,0x08,0x00 # CHECK: v_sub_u16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x4e,0x01,0x06,0x06,0x06] @@ -98931,7 +98931,7 @@ # CHECK: v_sub_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x4e,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_u16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x50,0x01,0x06,0x06,0x06] @@ -99123,7 +99123,7 @@ # CHECK: v_subrev_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x50,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x50,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x50,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x50,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x50,0x01,0xe4,0x08,0x00 # CHECK: v_mul_lo_u16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x52,0x01,0x06,0x06,0x06] @@ -99312,7 +99312,7 @@ # CHECK: v_mul_lo_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x52,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x52,0x01,0xe4,0x00,0x0f -# CHECK: v_mul_lo_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x52,0x01,0xe4,0x08,0x00] +# CHECK: v_mul_lo_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x52,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x52,0x01,0xe4,0x08,0x00 # CHECK: v_lshlrev_b16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x54,0x01,0x06,0x06,0x06] @@ -99501,7 +99501,7 @@ # CHECK: v_lshlrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x54,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x54,0x01,0xe4,0x00,0x0f -# CHECK: v_lshlrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x54,0x01,0xe4,0x08,0x00] +# CHECK: v_lshlrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x54,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x54,0x01,0xe4,0x08,0x00 # CHECK: v_lshrrev_b16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x56,0x01,0x06,0x06,0x06] @@ -99690,7 +99690,7 @@ # CHECK: v_lshrrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x56,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x56,0x01,0xe4,0x00,0x0f -# CHECK: v_lshrrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x56,0x01,0xe4,0x08,0x00] +# CHECK: v_lshrrev_b16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x56,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x56,0x01,0xe4,0x08,0x00 # CHECK: v_ashrrev_i16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x58,0x01,0x06,0x06,0x06] @@ -99879,7 +99879,7 @@ # CHECK: v_ashrrev_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x58,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x58,0x01,0xe4,0x00,0x0f -# CHECK: v_ashrrev_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x58,0x01,0xe4,0x08,0x00] +# CHECK: v_ashrrev_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x58,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x58,0x01,0xe4,0x08,0x00 # CHECK: v_max_f16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x5a,0x01,0x06,0x06,0x06] @@ -100083,7 +100083,7 @@ # CHECK: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x00,0x0f -# CHECK: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x08,0x00] +# CHECK: v_max_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x08,0x00 # CHECK: v_max_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x5a,0x01,0xe4,0x10,0x00] @@ -100299,7 +100299,7 @@ # CHECK: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x00,0x0f -# CHECK: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x08,0x00] +# CHECK: v_min_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x08,0x00 # CHECK: v_min_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x5c,0x01,0xe4,0x10,0x00] @@ -100500,7 +100500,7 @@ # CHECK: v_max_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x00,0x0f -# CHECK: v_max_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x08,0x00] +# CHECK: v_max_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x5e,0x01,0xe4,0x08,0x00 # CHECK: v_max_i16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x60,0x01,0x06,0x06,0x06] @@ -100689,7 +100689,7 @@ # CHECK: v_max_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x60,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x60,0x01,0xe4,0x00,0x0f -# CHECK: v_max_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x60,0x01,0xe4,0x08,0x00] +# CHECK: v_max_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x60,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x60,0x01,0xe4,0x08,0x00 # CHECK: v_min_u16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x62,0x01,0x06,0x06,0x06] @@ -100878,7 +100878,7 @@ # CHECK: v_min_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x62,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x62,0x01,0xe4,0x00,0x0f -# CHECK: v_min_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x62,0x01,0xe4,0x08,0x00] +# CHECK: v_min_u16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x62,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x62,0x01,0xe4,0x08,0x00 # CHECK: v_min_i16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x64,0x01,0x06,0x06,0x06] @@ -101067,7 +101067,7 @@ # CHECK: v_min_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x64,0x01,0xe4,0x00,0x0f -# CHECK: v_min_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00] +# CHECK: v_min_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x64,0x01,0xe4,0x08,0x00 # CHECK: v_ldexp_f16_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x66,0x01,0x06,0x06,0x06] @@ -101268,7 +101268,7 @@ # CHECK: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x66,0x01,0xe4,0x00,0x0f -# CHECK: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00] +# CHECK: v_ldexp_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x66,0x01,0xe4,0x08,0x00 # CHECK: v_ldexp_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x66,0x01,0xe4,0x10,0x00] @@ -101472,7 +101472,7 @@ # CHECK: v_add_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x68,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x68,0x01,0xe4,0x00,0x0f -# CHECK: v_add_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x68,0x01,0xe4,0x08,0x00] +# CHECK: v_add_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x68,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x68,0x01,0xe4,0x08,0x00 # CHECK: v_sub_u32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x6a,0x01,0x06,0x06,0x06] @@ -101670,7 +101670,7 @@ # CHECK: v_sub_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x00,0x0f -# CHECK: v_sub_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x08,0x00] +# CHECK: v_sub_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x08,0x00 # CHECK: v_subrev_u32_sdwa v5, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x0a,0x6c,0x01,0x06,0x06,0x06] @@ -101868,7 +101868,7 @@ # CHECK: v_subrev_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6c,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x6c,0x01,0xe4,0x00,0x0f -# CHECK: v_subrev_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x6c,0x01,0xe4,0x08,0x00] +# CHECK: v_subrev_u32_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x6c,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x6c,0x01,0xe4,0x08,0x00 # CHECK: v_cmp_class_f32_sdwa s[6:7], v1, v2 src0_sel:DWORD src1_sel:DWORD ; encoding: [0xf9,0x04,0x20,0x7c,0x01,0x86,0x06,0x06] Index: llvm/test/MC/Disassembler/AMDGPU/xdl-insts-gfx1011-gfx1012.txt =================================================================== --- llvm/test/MC/Disassembler/AMDGPU/xdl-insts-gfx1011-gfx1012.txt +++ llvm/test/MC/Disassembler/AMDGPU/xdl-insts-gfx1011-gfx1012.txt @@ -70,7 +70,7 @@ # CHECK: v_dot2c_f32_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x04,0x01,0xe4,0x00,0x0f -# CHECK: v_dot2c_f32_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00] +# CHECK: v_dot2c_f32_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x04,0x01,0xe4,0x08,0x00 # CHECK: v_dot2c_f32_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x04,0x01,0xe4,0x10,0x00] @@ -154,5 +154,5 @@ # CHECK: v_dot4c_i32_i8_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x00,0x0f -# CHECK: v_dot4c_i32_i8_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00] +# CHECK: v_dot4c_i32_i8_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x1a,0x01,0xe4,0x08,0x00 Index: llvm/test/MC/Disassembler/AMDGPU/xdl-insts-gfx908.txt =================================================================== --- llvm/test/MC/Disassembler/AMDGPU/xdl-insts-gfx908.txt +++ llvm/test/MC/Disassembler/AMDGPU/xdl-insts-gfx908.txt @@ -81,7 +81,7 @@ # CHECK: v_dot2c_f32_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6e,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x6e,0x01,0xe4,0x00,0x0f -# CHECK: v_dot2c_f32_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x6e,0x01,0xe4,0x08,0x00] +# CHECK: v_dot2c_f32_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x6e,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x6e,0x01,0xe4,0x08,0x00 # CHECK: v_dot2c_f32_f16_dpp v5, -v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 ; encoding: [0xfa,0x04,0x0a,0x6e,0x01,0xe4,0x10,0x00] @@ -177,7 +177,7 @@ # CHECK: v_dot2c_i32_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x70,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x70,0x01,0xe4,0x00,0x0f -# CHECK: v_dot2c_i32_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x70,0x01,0xe4,0x08,0x00] +# CHECK: v_dot2c_i32_i16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x70,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x70,0x01,0xe4,0x08,0x00 # CHECK: v_dot4c_i32_i8_e32 v5, v1, v2 ; encoding: [0x01,0x05,0x0a,0x72] @@ -261,7 +261,7 @@ # CHECK: v_dot4c_i32_i8_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x72,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x72,0x01,0xe4,0x00,0x0f -# CHECK: v_dot4c_i32_i8_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x72,0x01,0xe4,0x08,0x00] +# CHECK: v_dot4c_i32_i8_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x72,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x72,0x01,0xe4,0x08,0x00 # CHECK: v_dot8c_i32_i4_e32 v5, v1, v2 ; encoding: [0x01,0x05,0x0a,0x74] @@ -345,7 +345,7 @@ # CHECK: v_dot8c_i32_i4_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x74,0x01,0xe4,0x00,0x0f] 0xfa,0x04,0x0a,0x74,0x01,0xe4,0x00,0x0f -# CHECK: v_dot8c_i32_i4_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:0 ; encoding: [0xfa,0x04,0x0a,0x74,0x01,0xe4,0x08,0x00] +# CHECK: v_dot8c_i32_i4_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0x0 bank_mask:0x0 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x74,0x01,0xe4,0x08,0x00] 0xfa,0x04,0x0a,0x74,0x01,0xe4,0x08,0x00 # CHECK: v_pk_fmac_f16_e32 v5, v1, v2 ; encoding: [0x01,0x05,0x0a,0x78]