[PATCH] D115385: [CostModel][AMDGPU] Fix intrinsics costs estimations.

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: llvm/test/Analysis/CostModel/AMDGPU/fma.ll:84
 define amdgpu_kernel void @fma_f64() #0 {
-; GFX90A-LABEL: 'fma_f64'
-; GFX90A-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64 = call double @llvm.fma.f64(double undef, double undef, double undef) #2
-; GFX90A-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef) #2
-; GFX90A-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v3f64 = call <3 x double> @llvm.fma.v3f64(<3 x double> undef, <3 x double> undef, <3 x double> undef) #2
-; GFX90A-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4f64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef) #2
-; GFX90A-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v5f64 = call <5 x double> @llvm.fma.v5f64(<5 x double> undef, <5 x double> undef, <5 x double> undef) #2
-; GFX90A-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
-;
-; GFX900-LABEL: 'fma_f64'
-; GFX900-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f64 = call double @llvm.fma.f64(double undef, double undef, double undef) #2
-; GFX900-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef) #2
-; GFX900-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v3f64 = call <3 x double> @llvm.fma.v3f64(<3 x double> undef, <3 x double> undef, <3 x double> undef) #2
-; GFX900-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef) #2
-; GFX900-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v5f64 = call <5 x double> @llvm.fma.v5f64(<5 x double> undef, <5 x double> undef, <5 x double> undef) #2
-; GFX900-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+; FASTF64-LABEL: 'fma_f64'
+; FASTF64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f64 = call double @llvm.fma.f64(double undef, double undef, double undef) #2
----------------
Fast is slow and slow is fast now.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D115385/new/

https://reviews.llvm.org/D115385