[llvm] bbdc62e - [AArch64][CostModel] Improve scalar frem cost (#80423)

via llvm-commits llvm-commits at lists.llvm.org
Fri Feb 23 01:29:49 PST 2024


Author: Paschalis Mpeis
Date: 2024-02-23T09:29:45Z
New Revision: bbdc62e7180168effd0c480979bdaf933d0615d1

URL: https://github.com/llvm/llvm-project/commit/bbdc62e7180168effd0c480979bdaf933d0615d1
DIFF: https://github.com/llvm/llvm-project/commit/bbdc62e7180168effd0c480979bdaf933d0615d1.diff

LOG: [AArch64][CostModel] Improve scalar frem cost (#80423)

In AArch64 the cost of scalar frem is the cost of a call to 'fmod'.

Added: 
    

Modified: 
    llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/AArch64/arith-fp-frem.ll
    llvm/test/Analysis/CostModel/AArch64/arith-fp.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 6655931181c2d5..010e569809e276 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -2972,6 +2972,13 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
 
     return BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info,
                                          Op2Info);
+  case ISD::FREM:
+    // Pass nullptr as fmod/fmodf calls are emitted by the backend even when
+    // those functions are not declared in the module.
+    if (!Ty->isVectorTy())
+      return getCallInstrCost(/*Function*/ nullptr, Ty, {Ty, Ty}, CostKind);
+    return BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info,
+                                         Op2Info);
   }
 }
 

diff  --git a/llvm/test/Analysis/CostModel/AArch64/arith-fp-frem.ll b/llvm/test/Analysis/CostModel/AArch64/arith-fp-frem.ll
index 20e0ef7ea34281..63149adfa21587 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-fp-frem.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-fp-frem.ll
@@ -22,44 +22,44 @@ target triple = "aarch64-unknown-linux-gnu"
 
 define void @frem_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; NEON-NO-VECLIB-LABEL: 'frem_f64'
-; NEON-NO-VECLIB:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem double %in, %in
-; NEON-NO-VECLIB:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem double %in, %in
+; NEON-NO-VECLIB:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
+; NEON-NO-VECLIB:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem double %in, %in
 ;
 ; SVE-NO-VECLIB-LABEL: 'frem_f64'
-; SVE-NO-VECLIB:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem double %in, %in
-; SVE-NO-VECLIB:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem double %in, %in
+; SVE-NO-VECLIB:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
+; SVE-NO-VECLIB:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem double %in, %in
 ; SVE-NO-VECLIB:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem double %in, %in
 ; SVE-NO-VECLIB:  LV: Found an estimated cost of Invalid for VF vscale x 2 For instruction: %res = frem double %in, %in
 ;
 ; NEON-ARMPL-LABEL: 'frem_f64'
-; NEON-ARMPL:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem double %in, %in
-; NEON-ARMPL:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem double %in, %in
+; NEON-ARMPL:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
+; NEON-ARMPL:  LV: Found an estimated cost of 10 for VF 2 For instruction: %res = frem double %in, %in
 ;
 ; NEON-SLEEF-LABEL: 'frem_f64'
-; NEON-SLEEF:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem double %in, %in
-; NEON-SLEEF:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem double %in, %in
+; NEON-SLEEF:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
+; NEON-SLEEF:  LV: Found an estimated cost of 10 for VF 2 For instruction: %res = frem double %in, %in
 ;
 ; SVE-ARMPL-LABEL: 'frem_f64'
-; SVE-ARMPL:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem double %in, %in
-; SVE-ARMPL:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem double %in, %in
+; SVE-ARMPL:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
+; SVE-ARMPL:  LV: Found an estimated cost of 10 for VF 2 For instruction: %res = frem double %in, %in
 ; SVE-ARMPL:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem double %in, %in
 ; SVE-ARMPL:  LV: Found an estimated cost of 10 for VF vscale x 2 For instruction: %res = frem double %in, %in
 ;
 ; SVE-SLEEF-LABEL: 'frem_f64'
-; SVE-SLEEF:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem double %in, %in
-; SVE-SLEEF:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem double %in, %in
+; SVE-SLEEF:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
+; SVE-SLEEF:  LV: Found an estimated cost of 10 for VF 2 For instruction: %res = frem double %in, %in
 ; SVE-SLEEF:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem double %in, %in
 ; SVE-SLEEF:  LV: Found an estimated cost of 10 for VF vscale x 2 For instruction: %res = frem double %in, %in
 ;
 ; SVE-ARMPL-TAILFOLD-LABEL: 'frem_f64'
-; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem double %in, %in
-; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem double %in, %in
+; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
+; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 10 for VF 2 For instruction: %res = frem double %in, %in
 ; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem double %in, %in
 ; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 10 for VF vscale x 2 For instruction: %res = frem double %in, %in
 ;
 ; SVE-SLEEF-TAILFOLD-LABEL: 'frem_f64'
-; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem double %in, %in
-; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem double %in, %in
+; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
+; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 10 for VF 2 For instruction: %res = frem double %in, %in
 ; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem double %in, %in
 ; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 10 for VF vscale x 2 For instruction: %res = frem double %in, %in
 ;
@@ -83,55 +83,55 @@ define void @frem_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 
 define void @frem_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; NEON-NO-VECLIB-LABEL: 'frem_f32'
-; NEON-NO-VECLIB:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem float %in, %in
-; NEON-NO-VECLIB:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem float %in, %in
-; NEON-NO-VECLIB:  LV: Found an estimated cost of 20 for VF 4 For instruction: %res = frem float %in, %in
+; NEON-NO-VECLIB:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
+; NEON-NO-VECLIB:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem float %in, %in
+; NEON-NO-VECLIB:  LV: Found an estimated cost of 52 for VF 4 For instruction: %res = frem float %in, %in
 ;
 ; SVE-NO-VECLIB-LABEL: 'frem_f32'
-; SVE-NO-VECLIB:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem float %in, %in
-; SVE-NO-VECLIB:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem float %in, %in
-; SVE-NO-VECLIB:  LV: Found an estimated cost of 20 for VF 4 For instruction: %res = frem float %in, %in
+; SVE-NO-VECLIB:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
+; SVE-NO-VECLIB:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem float %in, %in
+; SVE-NO-VECLIB:  LV: Found an estimated cost of 52 for VF 4 For instruction: %res = frem float %in, %in
 ; SVE-NO-VECLIB:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem float %in, %in
 ; SVE-NO-VECLIB:  LV: Found an estimated cost of Invalid for VF vscale x 2 For instruction: %res = frem float %in, %in
 ; SVE-NO-VECLIB:  LV: Found an estimated cost of Invalid for VF vscale x 4 For instruction: %res = frem float %in, %in
 ;
 ; NEON-ARMPL-LABEL: 'frem_f32'
-; NEON-ARMPL:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem float %in, %in
-; NEON-ARMPL:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem float %in, %in
+; NEON-ARMPL:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
+; NEON-ARMPL:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem float %in, %in
 ; NEON-ARMPL:  LV: Found an estimated cost of 10 for VF 4 For instruction: %res = frem float %in, %in
 ;
 ; NEON-SLEEF-LABEL: 'frem_f32'
-; NEON-SLEEF:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem float %in, %in
-; NEON-SLEEF:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem float %in, %in
+; NEON-SLEEF:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
+; NEON-SLEEF:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem float %in, %in
 ; NEON-SLEEF:  LV: Found an estimated cost of 10 for VF 4 For instruction: %res = frem float %in, %in
 ;
 ; SVE-ARMPL-LABEL: 'frem_f32'
-; SVE-ARMPL:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem float %in, %in
-; SVE-ARMPL:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem float %in, %in
+; SVE-ARMPL:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
+; SVE-ARMPL:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem float %in, %in
 ; SVE-ARMPL:  LV: Found an estimated cost of 10 for VF 4 For instruction: %res = frem float %in, %in
 ; SVE-ARMPL:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem float %in, %in
 ; SVE-ARMPL:  LV: Found an estimated cost of Invalid for VF vscale x 2 For instruction: %res = frem float %in, %in
 ; SVE-ARMPL:  LV: Found an estimated cost of 10 for VF vscale x 4 For instruction: %res = frem float %in, %in
 ;
 ; SVE-SLEEF-LABEL: 'frem_f32'
-; SVE-SLEEF:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem float %in, %in
-; SVE-SLEEF:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem float %in, %in
+; SVE-SLEEF:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
+; SVE-SLEEF:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem float %in, %in
 ; SVE-SLEEF:  LV: Found an estimated cost of 10 for VF 4 For instruction: %res = frem float %in, %in
 ; SVE-SLEEF:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem float %in, %in
 ; SVE-SLEEF:  LV: Found an estimated cost of Invalid for VF vscale x 2 For instruction: %res = frem float %in, %in
 ; SVE-SLEEF:  LV: Found an estimated cost of 10 for VF vscale x 4 For instruction: %res = frem float %in, %in
 ;
 ; SVE-ARMPL-TAILFOLD-LABEL: 'frem_f32'
-; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem float %in, %in
-; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem float %in, %in
+; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
+; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem float %in, %in
 ; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 10 for VF 4 For instruction: %res = frem float %in, %in
 ; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem float %in, %in
 ; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of Invalid for VF vscale x 2 For instruction: %res = frem float %in, %in
 ; SVE-ARMPL-TAILFOLD:  LV: Found an estimated cost of 10 for VF vscale x 4 For instruction: %res = frem float %in, %in
 ;
 ; SVE-SLEEF-TAILFOLD-LABEL: 'frem_f32'
-; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 2 for VF 1 For instruction: %res = frem float %in, %in
-; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 8 for VF 2 For instruction: %res = frem float %in, %in
+; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
+; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 24 for VF 2 For instruction: %res = frem float %in, %in
 ; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of 10 for VF 4 For instruction: %res = frem float %in, %in
 ; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of Invalid for VF vscale x 1 For instruction: %res = frem float %in, %in
 ; SVE-SLEEF-TAILFOLD:  LV: Found an estimated cost of Invalid for VF vscale x 2 For instruction: %res = frem float %in, %in

diff  --git a/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll b/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
index c352892354fc24..497ade4f2f613c 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
@@ -197,17 +197,17 @@ define i32 @fdiv(i32 %arg) {
 
 define i32 @frem(i32 %arg) {
 ; CHECK-LABEL: 'frem'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F16 = frem half undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F16 = frem <4 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V8F16 = frem <8 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V16F16 = frem <16 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2F32 = frem <2 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4F32 = frem <4 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8F32 = frem <8 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2F64 = frem <2 x double> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4F64 = frem <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F16 = frem half undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V4F16 = frem <4 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V8F16 = frem <8 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16F16 = frem <16 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F32 = frem float undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F32 = frem <2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V4F32 = frem <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8F32 = frem <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %F64 = frem double undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = frem <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4F64 = frem <4 x double> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %F16 = frem half undef, undef


        


More information about the llvm-commits mailing list