[AArch64] Add cost tests for fast fadd reduction

[virnarula]

Summary

Add cost model tests for upcoming dot product lowering change. Related because we had to fix the arm64 cost model for our change.

[fhahn]

Thanks! Could you also add tests for reductions with just the reassoicate fast-math flag?

Also, this is not really specific to matrix support in LLVM, but applies generally to the AArch64 cost modeling. So it would be better to use [AArch64] in the description.

llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll

25

I think the strict part here refers to the ordering requirement, i.e. strict sequential order.

So it would probably be better to name the function @fast_fp_reductions.

40

can you also throw in some vectors with some odd numbers of elements.

[virnarula]

Replaced with the following review: https://reviews.llvm.org/D127682. Squashing prior to running arc diff created a new review instead of updating this one.

llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll

+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt -passes='print<cost-model>' 2>&1 -disable-output -mtriple=aarch64--linux-gnu < %s | FileCheck %s
 
 define void @strict_fp_reductions() {
-; CHECK-LABEL: strict_fp_reductions
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
+; CHECK-LABEL: 'strict_fp_reductions'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f16 = call half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %fadd_v8f16 = call half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %fadd_v4f16 = call half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef)
+  %fadd_v8f16 = call half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef)
   %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.0, <4 x float> undef)
   %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.0, <8 x float> undef)
   %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef)
   %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef)
 
   ret void
 }
 
+
+define void @strict_fp_reductions_fast() {
+; CHECK-LABEL: 'strict_fp_reductions_fast'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f16 = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %fadd_v8f16 = call fast half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f32 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %fadd_v8f32 = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %fadd_v2f64 = call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %fadd_v4f64 = call fast double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %fadd_v4f16 = call fast half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef)
+  %fadd_v8f16 = call fast half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef)
+  %fadd_v4f32 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.0, <4 x float> undef)
+  %fadd_v8f32 = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.0, <8 x float> undef)
+  %fadd_v2f64 = call fast double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef)
+  %fadd_v4f64 = call fast double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef)
+
+  ret void
+}
+
+declare half @llvm.vector.reduce.fadd.v4f16(half, <4 x half>)
+declare half @llvm.vector.reduce.fadd.v8f16(half, <8 x half>)
 declare float @llvm.vector.reduce.fadd.v4f32(float, <4 x float>)
 declare float @llvm.vector.reduce.fadd.v8f32(float, <8 x float>)
 declare double @llvm.vector.reduce.fadd.v2f64(double, <2 x double>)
 declare double @llvm.vector.reduce.fadd.v4f64(double, <4 x double>)