[llvm] bc56f63 - [CostModel] Add bfloat and fp128 reduction tests

[Florian Hahn via llvm-commits]

Author: Vir Narula
Date: 2022-08-12T16:44:04+01:00
New Revision: bc56f6377c08f435d6678ac5b8492a176c899221

URL: https://github.com/llvm/llvm-project/commit/bc56f6377c08f435d6678ac5b8492a176c899221
DIFF: https://github.com/llvm/llvm-project/commit/bc56f6377c08f435d6678ac5b8492a176c899221.diff

LOG: [CostModel] Add bfloat and fp128 reduction tests

Reviewed By: fhahn

Differential Revision: https://reviews.llvm.org/D131269

Added: 
    

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

Removed: 
    


################################################################################
diff  --git a/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll
index ca3dd13e7688d..0e56042789a17 100644
--- a/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll
@@ -1,5 +1,6 @@
 ; 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
+; RUN: opt -passes='print<cost-model>' 2>&1 -disable-output -mtriple=aarch64--linux-gnu < %s | FileCheck %s
+; RUN: opt -passes='print<cost-model>' 2>&1 -disable-output -mtriple=aarch64--linux-gnu -mattr=+fullfp16 < %s | FileCheck %s
 
 define void @strict_fp_reductions() {
 ; CHECK-LABEL: 'strict_fp_reductions'
@@ -9,6 +10,8 @@ define void @strict_fp_reductions() {
 ; 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 12 for instruction: %fadd_v4f8 = call bfloat @llvm.vector.reduce.fadd.v4bf16(bfloat 0xR0000, <4 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %fadd_v4f128 = call fp128 @llvm.vector.reduce.fadd.v4f128(fp128 undef, <4 x fp128> 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)
@@ -17,6 +20,8 @@ define void @strict_fp_reductions() {
   %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)
+  %fadd_v4f8 = call bfloat @llvm.vector.reduce.fadd.v4f8(bfloat 0.0, <4 x bfloat> undef)
+  %fadd_v4f128 = call fp128 @llvm.vector.reduce.fadd.v4f128(fp128 undef, <4 x fp128> undef)
 
   ret void
 }
@@ -42,6 +47,8 @@ define void @fast_fp_reductions() {
 ; 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 6 for instruction: %fadd_v4f8 = call reassoc bfloat @llvm.vector.reduce.fadd.v4bf16(bfloat 0xR8000, <4 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %fadd_v4f128 = call reassoc fp128 @llvm.vector.reduce.fadd.v4f128(fp128 undef, <4 x fp128> 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)
@@ -71,9 +78,15 @@ define void @fast_fp_reductions() {
   %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)
 
+  %fadd_v4f8 = call reassoc bfloat @llvm.vector.reduce.fadd.v4f8(bfloat -0.0, <4 x bfloat> undef)
+  %fadd_v4f128 = call reassoc fp128 @llvm.vector.reduce.fadd.v4f128(fp128 undef, <4 x fp128> undef)
+
   ret void
 }
 
+declare bfloat @llvm.vector.reduce.fadd.v4f8(bfloat, <4 x bfloat>)
+declare fp128 @llvm.vector.reduce.fadd.v4f128(fp128, <4 x fp128>)
+
 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>)