[AArch64] Add cost tests for reduction add and fast fadd

[virnarula]

Summary

Add test coverage showing how the costs of fadd reductions is overestimated at the moment.

[virnarula]

Fix costs to relfect pre-optimization numbers

[fhahn]

LGTM, thanks.

As for the description, it should be sufficient to say something like Add test coverage showing how the costs of fadd reductions is overestimated at the moment.

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 @fast_fp_reductions() {
+; CHECK-LABEL: 'fast_fp_reductions'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f16_reassoc = call reassoc 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 30 for instruction: %fadd_v8f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %fadd_v11f16 = call fast half @llvm.vector.reduce.fadd.v11f16(half 0xH0000, <11 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %fadd_v13f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v13f16(half 0xH0000, <13 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 10 for instruction: %fadd_v4f32_reassoc = call reassoc 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 30 for instruction: %fadd_v8f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %fadd_v13f32 = call fast float @llvm.vector.reduce.fadd.v13f32(float 0.000000e+00, <13 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %fadd_v5f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v5f32(float 0.000000e+00, <5 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 3 for instruction: %fadd_v2f64_reassoc = call reassoc 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 11 for instruction: %fadd_v4f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.000000e+00, <7 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.000000e+00, <9 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef)
+  %fadd_v4f16_reassoc = call reassoc 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_v8f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef)
+
+  %fadd_v11f16 = call fast half @llvm.vector.reduce.fadd.v11f16(half 0.0, <11 x half> undef)
+  %fadd_v13f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v13f16(half 0.0, <13 x half> undef)
+
+  %fadd_v4f32 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.0, <4 x float> undef)
+  %fadd_v4f32_reassoc = call reassoc 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_v8f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v8f32(float 0.0, <8 x float> undef)
+
+  %fadd_v13f32 = call fast float @llvm.vector.reduce.fadd.v13f32(float 0.0, <13 x float> undef)
+  %fadd_v5f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v5f32(float 0.0, <5 x float> undef)
+
+  %fadd_v2f64 = call fast double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef)
+  %fadd_v2f64_reassoc = call reassoc 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)
+  %fadd_v4f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef)
+
+  %fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.0, <7 x double> undef)
+  %fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.0, <9 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 half @llvm.vector.reduce.fadd.v11f16(half, <11 x half>)
+declare half @llvm.vector.reduce.fadd.v13f16(half, <13 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 float @llvm.vector.reduce.fadd.v13f32(float, <13 x float>)
+declare float @llvm.vector.reduce.fadd.v5f32(float, <5 x float>)
+
 declare double @llvm.vector.reduce.fadd.v2f64(double, <2 x double>)
 declare double @llvm.vector.reduce.fadd.v4f64(double, <4 x double>)
+declare double @llvm.vector.reduce.fadd.v7f64(double, <7 x double>)
+declare double @llvm.vector.reduce.fadd.v9f64(double, <9 x double>)