diff options
author | Geoff Berry <gberry@codeaurora.org> | 2018-02-27 16:59:10 +0000 |
---|---|---|
committer | Geoff Berry <gberry@codeaurora.org> | 2018-02-27 16:59:10 +0000 |
commit | a2b901129099b93f20e8cdf41f520e31398c0c4d (patch) | |
tree | dce027ceb74117c28b4d882383b8ebb172de0fd7 /llvm/test/CodeGen/AMDGPU | |
parent | 3bfa8f01207f907551c8ea39a938e0f2f8ec018b (diff) | |
download | bcm5719-llvm-a2b901129099b93f20e8cdf41f520e31398c0c4d.tar.gz bcm5719-llvm-a2b901129099b93f20e8cdf41f520e31398c0c4d.zip |
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding"
Re-enable commit r323991 now that r325931 has been committed to make
MachineOperand::isRenamable() check more conservative w.r.t. code
changes and opt-in on a per-target basis.
llvm-svn: 326208
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU')
-rw-r--r-- | llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll | 12 | ||||
-rw-r--r-- | llvm/test/CodeGen/AMDGPU/fix-vgpr-copies.mir | 2 | ||||
-rw-r--r-- | llvm/test/CodeGen/AMDGPU/multilevel-break.ll | 2 | ||||
-rw-r--r-- | llvm/test/CodeGen/AMDGPU/ret.ll | 18 |
4 files changed, 17 insertions, 17 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll b/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll index de61b24c702..380d5a4f338 100644 --- a/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll +++ b/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll @@ -547,16 +547,16 @@ define void @func_use_every_sgpr_input_call_use_workgroup_id_xyz() #1 { ; GCN: s_mov_b32 s5, s32 ; GCN: s_add_u32 s32, s32, 0x300 -; GCN-DAG: s_mov_b32 [[SAVE_X:s[0-9]+]], s14 -; GCN-DAG: s_mov_b32 [[SAVE_Y:s[0-9]+]], s15 -; GCN-DAG: s_mov_b32 [[SAVE_Z:s[0-9]+]], s16 +; GCN-DAG: s_mov_b32 [[SAVE_X:s[0-57-9][0-9]*]], s14 +; GCN-DAG: s_mov_b32 [[SAVE_Y:s[0-68-9][0-9]*]], s15 +; GCN-DAG: s_mov_b32 [[SAVE_Z:s[0-79][0-9]*]], s16 ; GCN-DAG: s_mov_b64 {{s\[[0-9]+:[0-9]+\]}}, s[6:7] ; GCN-DAG: s_mov_b64 {{s\[[0-9]+:[0-9]+\]}}, s[8:9] ; GCN-DAG: s_mov_b64 {{s\[[0-9]+:[0-9]+\]}}, s[10:11] -; GCN-DAG: s_mov_b32 s6, [[SAVE_X]] -; GCN-DAG: s_mov_b32 s7, [[SAVE_Y]] -; GCN-DAG: s_mov_b32 s8, [[SAVE_Z]] +; GCN-DAG: s_mov_b32 s6, s14 +; GCN-DAG: s_mov_b32 s7, s15 +; GCN-DAG: s_mov_b32 s8, s16 ; GCN: s_swappc_b64 ; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s5 offset:4 diff --git a/llvm/test/CodeGen/AMDGPU/fix-vgpr-copies.mir b/llvm/test/CodeGen/AMDGPU/fix-vgpr-copies.mir index c53ff28b547..66a238dff82 100644 --- a/llvm/test/CodeGen/AMDGPU/fix-vgpr-copies.mir +++ b/llvm/test/CodeGen/AMDGPU/fix-vgpr-copies.mir @@ -1,4 +1,4 @@ -# RUN: llc -march=amdgcn -start-after=greedy -stop-after=si-optimize-exec-masking -o - %s | FileCheck %s +# RUN: llc -march=amdgcn -start-after=greedy -disable-copyprop -stop-after=si-optimize-exec-masking -o - %s | FileCheck %s # Check that we first do all vector instructions and only then change exec # CHECK-DAG: COPY $vgpr10_vgpr11 # CHECK-DAG: COPY $vgpr12_vgpr13 diff --git a/llvm/test/CodeGen/AMDGPU/multilevel-break.ll b/llvm/test/CodeGen/AMDGPU/multilevel-break.ll index 8cc02d49709..5917f87e19a 100644 --- a/llvm/test/CodeGen/AMDGPU/multilevel-break.ll +++ b/llvm/test/CodeGen/AMDGPU/multilevel-break.ll @@ -78,7 +78,7 @@ ENDIF: ; preds = %LOOP ; Uses a copy intsead of an or ; GCN: s_mov_b64 [[COPY:s\[[0-9]+:[0-9]+\]]], [[BREAK_REG]] -; GCN: s_or_b64 [[BREAK_REG]], exec, [[COPY]] +; GCN: s_or_b64 [[BREAK_REG]], exec, [[BREAK_REG]] define amdgpu_kernel void @multi_if_break_loop(i32 %arg) #0 { bb: %id = call i32 @llvm.amdgcn.workitem.id.x() diff --git a/llvm/test/CodeGen/AMDGPU/ret.ll b/llvm/test/CodeGen/AMDGPU/ret.ll index c86cfa198db..deedf365d2c 100644 --- a/llvm/test/CodeGen/AMDGPU/ret.ll +++ b/llvm/test/CodeGen/AMDGPU/ret.ll @@ -2,10 +2,10 @@ ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s ; GCN-LABEL: {{^}}vgpr: -; GCN: v_mov_b32_e32 v1, v0 -; GCN-DAG: v_add_f32_e32 v0, 1.0, v1 -; GCN-DAG: exp mrt0 v1, v1, v1, v1 done vm +; GCN-DAG: v_mov_b32_e32 v1, v0 +; GCN-DAG: exp mrt0 v0, v0, v0, v0 done vm ; GCN: s_waitcnt expcnt(0) +; GCN: v_add_f32_e32 v0, 1.0, v1 ; GCN-NOT: s_endpgm define amdgpu_vs { float, float } @vgpr([9 x <16 x i8>] addrspace(4)* byval %arg, i32 inreg %arg1, i32 inreg %arg2, float %arg3) #0 { bb: @@ -179,7 +179,7 @@ bb: ; GCN-LABEL: {{^}}sgpr: ; GCN: s_mov_b32 s2, s3 -; GCN: s_add_i32 s0, s2, 2 +; GCN: s_add_i32 s0, s3, 2 ; GCN-NOT: s_endpgm define amdgpu_vs { i32, i32, i32 } @sgpr([9 x <16 x i8>] addrspace(4)* byval %arg, i32 inreg %arg1, i32 inreg %arg2, float %arg3) #0 { bb: @@ -204,13 +204,13 @@ bb: } ; GCN-LABEL: {{^}}both: -; GCN: v_mov_b32_e32 v1, v0 -; GCN-DAG: exp mrt0 v1, v1, v1, v1 done vm -; GCN-DAG: v_add_f32_e32 v0, 1.0, v1 -; GCN-DAG: s_add_i32 s0, s3, 2 +; GCN-DAG: exp mrt0 v0, v0, v0, v0 done vm +; GCN-DAG: v_mov_b32_e32 v1, v0 ; GCN-DAG: s_mov_b32 s1, s2 -; GCN: s_mov_b32 s2, s3 ; GCN: s_waitcnt expcnt(0) +; GCN: v_add_f32_e32 v0, 1.0, v1 +; GCN-DAG: s_add_i32 s0, s3, 2 +; GCN-DAG: s_mov_b32 s2, s3 ; GCN-NOT: s_endpgm define amdgpu_vs { float, i32, float, i32, i32 } @both([9 x <16 x i8>] addrspace(4)* byval %arg, i32 inreg %arg1, i32 inreg %arg2, float %arg3) #0 { bb: |