[AMDGPU] Fix DPP operand order in atomic optimizer

[critson]

Summary

Ensure order of operands in DPP atomic optimizer final WWM step is appropriate for sub instructions.

Change-Id: I631d050e1c00a3b4bc7c11a90437064403c4cf30

[sheredom]

LGTM.

llvm/trunk/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp

for (unsigned Idx = 0; Idx < Iters; Idx++) {
           {Identity, UpdateValue, B.getInt32(DPPCtrl[Idx]),
            B.getInt32(RowMask[Idx]), B.getInt32(BankMask[Idx]), B.getFalse()});
       setConvergent(DPP);
 
       NewV = B.CreateBinOp(Op, NewV, DPP);
     }
 
     LaneOffset = B.CreateIntrinsic(Intrinsic::amdgcn_wwm, Ty, NewV);
-    NewV = B.CreateBinOp(Op, NewV, SetInactive);
+    NewV = B.CreateBinOp(Op, SetInactive, NewV);
 
     // Read the value from the last lane, which has accumlated the values of
     // each active lane in the wavefront. This will be our new value with which
     // we will provide to the atomic operation.
     if (TyBitWidth == 64) {
       Value *const ExtractLo = B.CreateTrunc(NewV, B.getInt32Ty());
       Value *const ExtractHi =
           B.CreateTrunc(B.CreateLShr(NewV, B.getInt64(32)), B.getInt32Ty());

llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll

entry:
   ret void
 }
 
 ; GCN-LABEL: sub_i32_varying_vdata:
 ; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
 ; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
 ; GFX7LESS-NOT: s_bcnt1_i32_b64
 ; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
-; GFX8MORE: v_mov_b32_dpp v[[wave_shr1:[0-9]+]], v{{[0-9]+}} wave_shr:1 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_mov_b32_dpp v[[wave_shr1:[0-9]+]], v[[sub_value:[0-9]+]] wave_shr:1 row_mask:0xf bank_mask:0xf
 ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:1 row_mask:0xf bank_mask:0xf
 ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:2 row_mask:0xf bank_mask:0xf
 ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[wave_shr1]] row_shr:3 row_mask:0xf bank_mask:0xf
 ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:4 row_mask:0xf bank_mask:0xe
 ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:8 row_mask:0xf bank_mask:0xc
 ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_bcast:15 row_mask:0xa bank_mask:0xf
 ; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_bcast:31 row_mask:0xc bank_mask:0xf
-; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_sub_u32_e32 v[[sub_value]],{{( vcc,)?}} v[[sub_value]], v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v[[sub_value]], 63
 ; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
 ; GFX8MORE: buffer_atomic_sub v[[value]]
 define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
   %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i1 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void

llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll

entry:
   ret void
 }
 
 ; GCN-LABEL: sub_i32_varying:
 ; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
 ; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
 ; GFX7LESS-NOT: s_bcnt1_i32_b64
 ; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
-; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[sub_value:[0-9]+]] wave_shr:1 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_sub_u32_e32 v[[sub_value]],{{( vcc,)?}} v[[sub_value]], v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v[[sub_value]], 63
 ; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
 ; GFX8MORE: buffer_atomic_sub v[[value]]
 define amdgpu_kernel void @sub_i32_varying(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
   %old = atomicrmw sub i32 addrspace(1)* %inout, i32 %lane acq_rel
   store i32 %old, i32 addrspace(1)* %out
   ret void

llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll

entry:
   ret void
 }
 
 ; GCN-LABEL: sub_i32_varying:
 ; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
 ; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
 ; GFX7LESS-NOT: s_bcnt1_i32_b64
 ; GFX7LESS: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
-; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[sub_value:[0-9]+]] wave_shr:1 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_sub_u32_e32 v[[sub_value]],{{( vcc,)?}} v[[sub_value]], v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v[[sub_value]], 63
 ; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
 ; GFX8MORE: ds_sub_rtn_u32 v{{[0-9]+}}, v{{[0-9]+}}, v[[value]]
 define amdgpu_kernel void @sub_i32_varying(i32 addrspace(1)* %out) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
   %old = atomicrmw sub i32 addrspace(3)* @local_var32, i32 %lane acq_rel
   store i32 %old, i32 addrspace(1)* %out
   ret void

llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll

entry:
   ret void
 }
 
 ; GCN-LABEL: sub_i32_varying_vdata:
 ; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
 ; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
 ; GFX7LESS-NOT: s_bcnt1_i32_b64
 ; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
-; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[sub_value:[0-9]+]] wave_shr:1 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_sub_u32_e32 v[[sub_value]],{{( vcc,)?}} v[[sub_value]], v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v[[sub_value]], 63
 ; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
 ; GFX8MORE: buffer_atomic_sub v[[value]]
 define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
   %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void

llvm/trunk/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll

entry:
   ret void
 }
 
 ; GCN-LABEL: sub_i32_varying_vdata:
 ; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
 ; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
 ; GFX7LESS-NOT: s_bcnt1_i32_b64
 ; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
-; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v[[sub_value:[0-9]+]] wave_shr:1 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_sub_u32_e32 v[[sub_value]],{{( vcc,)?}} v[[sub_value]], v{{[0-9]+}}
+; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v[[sub_value]], 63
 ; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
 ; GFX8MORE: buffer_atomic_sub v[[value]]
 define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
   %old = call i32 @llvm.amdgcn.struct.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void