Index: lib/Target/AMDGPU/SIInstrInfo.h =================================================================== --- lib/Target/AMDGPU/SIInstrInfo.h +++ lib/Target/AMDGPU/SIInstrInfo.h @@ -548,8 +548,9 @@ int getAtomicNoRetOp(uint16_t Opcode); const uint64_t RSRC_DATA_FORMAT = 0xf00000000000LL; - const uint64_t RSRC_TID_ENABLE = 1LL << 55; - const uint64_t RSRC_ELEMENT_SIZE_SHIFT = 51; + const uint64_t RSRC_ELEMENT_SIZE_SHIFT = (32 + 19); + const uint64_t RSRC_INDEX_STRIDE_SHIFT = (32 + 21); + const uint64_t RSRC_TID_ENABLE = 1LL << (32 + 23); } // End namespace AMDGPU namespace SI { Index: lib/Target/AMDGPU/SIInstrInfo.cpp =================================================================== --- lib/Target/AMDGPU/SIInstrInfo.cpp +++ lib/Target/AMDGPU/SIInstrInfo.cpp @@ -3094,7 +3094,8 @@ uint64_t EltSizeValue = Log2_32(ST.getMaxPrivateElementSize()) - 1; - Rsrc23 |= (EltSizeValue << AMDGPU::RSRC_ELEMENT_SIZE_SHIFT); + Rsrc23 |= (EltSizeValue << AMDGPU::RSRC_ELEMENT_SIZE_SHIFT) | + (3LL << AMDGPU::RSRC_INDEX_STRIDE_SHIFT); // IndexStride = 64 // If TID_ENABLE is set, DATA_FORMAT specifies stride bits [14:17]. // Clear them unless we want a huge stride. Index: test/CodeGen/AMDGPU/large-alloca-compute.ll =================================================================== --- test/CodeGen/AMDGPU/large-alloca-compute.ll +++ test/CodeGen/AMDGPU/large-alloca-compute.ll @@ -10,8 +10,8 @@ ; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0 ; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1 ; GCN-DAG: s_mov_b32 s{{[0-9]+}}, -1 -; CI-DAG: s_mov_b32 s{{[0-9]+}}, 0x88f000 -; VI-DAG: s_mov_b32 s{{[0-9]+}}, 0x880000 +; CI-DAG: s_mov_b32 s{{[0-9]+}}, 0xe8f000 +; VI-DAG: s_mov_b32 s{{[0-9]+}}, 0xe80000 ; GCNHSA: .amd_kernel_code_t Index: test/CodeGen/AMDGPU/large-alloca-graphics.ll =================================================================== --- test/CodeGen/AMDGPU/large-alloca-graphics.ll +++ test/CodeGen/AMDGPU/large-alloca-graphics.ll @@ -5,8 +5,8 @@ ; GCN-DAG: s_mov_b32 s8, SCRATCH_RSRC_DWORD0 ; GCN-DAG: s_mov_b32 s9, SCRATCH_RSRC_DWORD1 ; GCN-DAG: s_mov_b32 s10, -1 -; CI-DAG: s_mov_b32 s11, 0x88f000 -; VI-DAG: s_mov_b32 s11, 0x880000 +; CI-DAG: s_mov_b32 s11, 0xe8f000 +; VI-DAG: s_mov_b32 s11, 0xe80000 ; GCN: buffer_store_dword {{v[0-9]+}}, {{v[0-9]+}}, s[8:11], s0 offen ; GCN: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, s[8:11], s0 offen @@ -26,8 +26,8 @@ ; GCN-DAG: s_mov_b32 s8, SCRATCH_RSRC_DWORD0 ; GCN-DAG: s_mov_b32 s9, SCRATCH_RSRC_DWORD1 ; GCN-DAG: s_mov_b32 s10, -1 -; CI-DAG: s_mov_b32 s11, 0x88f000 -; VI-DAG: s_mov_b32 s11, 0x880000 +; CI-DAG: s_mov_b32 s11, 0xe8f000 +; VI-DAG: s_mov_b32 s11, 0xe80000 ; GCN: buffer_store_dword {{v[0-9]+}}, {{v[0-9]+}}, s[8:11], s2 offen ; GCN: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, s[8:11], s2 offen Index: test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot-compute.ll =================================================================== --- test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot-compute.ll +++ test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot-compute.ll @@ -23,8 +23,8 @@ ; GCNMESA-DAG: s_mov_b32 s12, SCRATCH_RSRC_DWORD0 ; GCNMESA--DAG: s_mov_b32 s13, SCRATCH_RSRC_DWORD1 ; GCNMESA-DAG: s_mov_b32 s14, -1 -; SIMESA-DAG: s_mov_b32 s15, 0x88f000 -; VIMESA-DAG: s_mov_b32 s15, 0x880000 +; SIMESA-DAG: s_mov_b32 s15, 0xe8f000 +; VIMESA-DAG: s_mov_b32 s15, 0xe80000 ; GCN: buffer_store_dword {{v[0-9]+}}, off, s[12:15], s16 offset:{{[0-9]+}} ; 4-byte Folded Spill Index: test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot.ll =================================================================== --- test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot.ll +++ test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot.ll @@ -16,8 +16,8 @@ ; GCN-DAG: s_mov_b32 s16, SCRATCH_RSRC_DWORD0 ; GCN-DAG: s_mov_b32 s17, SCRATCH_RSRC_DWORD1 ; GCN-DAG: s_mov_b32 s18, -1 -; SI-DAG: s_mov_b32 s19, 0x88f000 -; VI-DAG: s_mov_b32 s19, 0x880000 +; SI-DAG: s_mov_b32 s19, 0xe8f000 +; VI-DAG: s_mov_b32 s19, 0xe80000 ; s13 is offset system SGPR ; GCN: buffer_store_dword {{v[0-9]+}}, off, s[16:19], s13 offset:{{[0-9]+}} ; 16-byte Folded Spill