diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2016-04-14 21:58:24 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2016-04-14 21:58:24 +0000 |
| commit | 3d1c1deb04efe0022f11ebc18bb43d7341ba0c75 (patch) | |
| tree | 3a14403716facae35ba4c41889a588710093fb5c /llvm/test/CodeGen/AMDGPU/uint_to_fp.f64.ll | |
| parent | 4ac341c8b31ab34c7cb90eda91a91e78a11a8baf (diff) | |
| download | bcm5719-llvm-3d1c1deb04efe0022f11ebc18bb43d7341ba0c75.tar.gz bcm5719-llvm-3d1c1deb04efe0022f11ebc18bb43d7341ba0c75.zip | |
AMDGPU: Run SIFoldOperands after PeepholeOptimizer
PeepholeOptimizer cleans up redundant copies, which makes
the operand folding more effective.
shader-db stats:
Totals:
SGPRS: 34200 -> 34336 (0.40 %)
VGPRS: 22118 -> 21655 (-2.09 %)
Code Size: 632144 -> 633460 (0.21 %) bytes
LDS: 11 -> 11 (0.00 %) blocks
Scratch: 10240 -> 11264 (10.00 %) bytes per wave
Max Waves: 8822 -> 8918 (1.09 %)
Wait states: 0 -> 0 (0.00 %)
Totals from affected shaders:
SGPRS: 7704 -> 7840 (1.77 %)
VGPRS: 5169 -> 4706 (-8.96 %)
Code Size: 234444 -> 235760 (0.56 %) bytes
LDS: 2 -> 2 (0.00 %) blocks
Scratch: 0 -> 1024 (0.00 %) bytes per wave
Max Waves: 1188 -> 1284 (8.08 %)
Wait states: 0 -> 0 (0.00 %)
Increases:
SGPRS: 35 (0.01 %)
VGPRS: 1 (0.00 %)
Code Size: 59 (0.02 %)
LDS: 0 (0.00 %)
Scratch: 1 (0.00 %)
Max Waves: 48 (0.02 %)
Wait states: 0 (0.00 %)
Decreases:
SGPRS: 26 (0.01 %)
VGPRS: 54 (0.02 %)
Code Size: 68 (0.03 %)
LDS: 0 (0.00 %)
Scratch: 0 (0.00 %)
Max Waves: 4 (0.00 %)
Wait states: 0 (0.00 %)
llvm-svn: 266378
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/uint_to_fp.f64.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/uint_to_fp.f64.ll | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/uint_to_fp.f64.ll b/llvm/test/CodeGen/AMDGPU/uint_to_fp.f64.ll index 2723c0dc95e..b36ce6b8d6c 100644 --- a/llvm/test/CodeGen/AMDGPU/uint_to_fp.f64.ll +++ b/llvm/test/CodeGen/AMDGPU/uint_to_fp.f64.ll @@ -70,10 +70,11 @@ define void @s_uint_to_fp_v4i32_to_v4f64(<4 x double> addrspace(1)* %out, <4 x i ret void } -; SI-LABEL: {{^}}uint_to_fp_i1_to_f64: -; SI: v_cmp_eq_i32_e64 vcc ; We can't fold the SGPRs into v_cndmask_b32_e32, because it already ; uses an SGPR (implicit vcc). + +; SI-LABEL: {{^}}uint_to_fp_i1_to_f64: +; SI-DAG: v_cmp_eq_i32_e64 vcc ; SI-DAG: v_cndmask_b32_e32 v[[SEL:[0-9]+]], 0, v{{[0-9]+}} ; SI-DAG: v_mov_b32_e32 v[[ZERO:[0-9]+]], 0{{$}} ; SI: buffer_store_dwordx2 v{{\[}}[[ZERO]]:[[SEL]]{{\]}} |
