[SimplifyLibCalls] fdim constant fold (llvm#109235)

2nd PR to fix llvm#108695 based on llvm#108702 --------- Signed-off-by: Kushal Pal <kushalpal109@gmail.com>
ROCm · Oct 10, 2024 · 3645c64 · 3645c64
1 parent bb34008
commit 3645c64
Show file tree

Hide file tree

Showing 4 changed files with 207 additions and 0 deletions.
diff --git a/llvm/include/llvm/Transforms/Utils/SimplifyLibCalls.h b/llvm/include/llvm/Transforms/Utils/SimplifyLibCalls.h
@@ -212,6 +212,7 @@ class LibCallSimplifier {
   Value *optimizeTrigInversionPairs(CallInst *CI, IRBuilderBase &B);
   Value *optimizeSymmetric(CallInst *CI, LibFunc Func, IRBuilderBase &B);
   Value *optimizeRemquo(CallInst *CI, IRBuilderBase &B);
+  Value *optimizeFdim(CallInst *CI, IRBuilderBase &B);
   // Wrapper for all floating point library call optimizations
   Value *optimizeFloatingPointLibCall(CallInst *CI, LibFunc Func,
                                       IRBuilderBase &B);

diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
@@ -3126,6 +3126,33 @@ Value *LibCallSimplifier::optimizeRemquo(CallInst *CI, IRBuilderBase &B) {
   return ConstantFP::get(CI->getType(), Rem);
 }
 
+/// Constant folds fdim
+Value *LibCallSimplifier::optimizeFdim(CallInst *CI, IRBuilderBase &B) {
+  // Cannot perform the fold unless the call has attribute memory(none)
+  if (!CI->doesNotAccessMemory())
+    return nullptr;
+
+  // TODO : Handle undef values
+  // Propagate poison if any
+  if (isa<PoisonValue>(CI->getArgOperand(0)))
+    return CI->getArgOperand(0);
+  if (isa<PoisonValue>(CI->getArgOperand(1)))
+    return CI->getArgOperand(1);
+
+  const APFloat *X, *Y;
+  // Check if both values are constants
+  if (!match(CI->getArgOperand(0), m_APFloat(X)) ||
+      !match(CI->getArgOperand(1), m_APFloat(Y)))
+    return nullptr;
+
+  APFloat Difference = *X;
+  Difference.subtract(*Y, RoundingMode::NearestTiesToEven);
+
+  APFloat MaxVal =
+      maximum(Difference, APFloat::getZero(CI->getType()->getFltSemantics()));
+  return ConstantFP::get(CI->getType(), MaxVal);
+}
+
 //===----------------------------------------------------------------------===//
 // Integer Library Call Optimizations
 //===----------------------------------------------------------------------===//
@@ -4059,6 +4086,10 @@ Value *LibCallSimplifier::optimizeFloatingPointLibCall(CallInst *CI,
     if (hasFloatVersion(M, CI->getCalledFunction()->getName()))
       return optimizeBinaryDoubleFP(CI, Builder, TLI);
     return nullptr;
+  case LibFunc_fdim:
+  case LibFunc_fdimf:
+  case LibFunc_fdiml:
+    return optimizeFdim(CI, Builder);
   case LibFunc_fminf:
   case LibFunc_fmin:
   case LibFunc_fminl:

diff --git a/llvm/test/Transforms/InstCombine/fdim.ll b/llvm/test/Transforms/InstCombine/fdim.ll
@@ -0,0 +1,139 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s -passes=instcombine -S | FileCheck %s
+
+define double @fdim_double() {
+; CHECK-LABEL: define double @fdim_double() {
+; CHECK-NEXT:    ret double 2.500000e+00
+;
+  %dim = call double @fdim(double 10.5, double 8.0)
+  ret double %dim
+}
+
+define double @fdim_double1() {
+; CHECK-LABEL: define double @fdim_double1() {
+; CHECK-NEXT:    ret double 0.000000e+00
+;
+  %dim = call double @fdim(double 7.0, double 8.0)
+  ret double %dim
+}
+
+define float @fdim_float() {
+; CHECK-LABEL: define float @fdim_float() {
+; CHECK-NEXT:    ret float 0.000000e+00
+;
+  %dim = call float @fdimf(float 1.500000e+00, float 8.0)
+  ret float %dim
+}
+
+define float @fdim_float1() {
+; CHECK-LABEL: define float @fdim_float1() {
+; CHECK-NEXT:    ret float 2.000000e+00
+;
+  %dim = call float @fdimf(float 1.000000e+01, float 8.0)
+  ret float %dim
+}
+
+define double @fdim_poison1() {
+; CHECK-LABEL: define double @fdim_poison1() {
+; CHECK-NEXT:    ret double poison
+;
+  %dim = call double @fdim(double poison, double 1.0)
+  ret double %dim
+}
+
+define double @fdim_poison2() {
+; CHECK-LABEL: define double @fdim_poison2() {
+; CHECK-NEXT:    ret double poison
+;
+  %dim = call double @fdim(double 1.0, double poison)
+  ret double %dim
+}
+
+define double @fdim_poison3() {
+; CHECK-LABEL: define double @fdim_poison3() {
+; CHECK-NEXT:    ret double poison
+;
+  %dim = call double @fdim(double poison, double poison)
+  ret double %dim
+}
+
+; undef folding is not implemented yet
+define double @fdim_undef1() {
+; CHECK-LABEL: define double @fdim_undef1() {
+; CHECK-NEXT:    [[DIM:%.*]] = call double @fdim(double undef, double 1.000000e+00)
+; CHECK-NEXT:    ret double [[DIM]]
+;
+  %dim = call double @fdim(double undef, double 1.0)
+  ret double %dim
+}
+
+define double @fdim_inf_ninf() {
+; CHECK-LABEL: define double @fdim_inf_ninf() {
+; CHECK-NEXT:    ret double 0x7FF0000000000000
+;
+  %dim = call double @fdim(double 0x7FF0000000000000, double 0x8000000000000000 )
+  ret double %dim
+}
+
+define double @fdim_inf() {
+; CHECK-LABEL: define double @fdim_inf() {
+; CHECK-NEXT:    ret double 0x7FF8000000000000
+;
+  %dim = call double @fdim(double 0x7FF0000000000000, double 0x7FF0000000000000)
+  ret double %dim
+}
+
+define double @fdim_nzero() {
+; CHECK-LABEL: define double @fdim_nzero() {
+; CHECK-NEXT:    ret double 0.000000e+00
+;
+  %dim = call double @fdim(double -0.0, double +0.0)
+  ret double %dim
+}
+
+define double @fdim_strictfp() {
+; CHECK-LABEL: define double @fdim_strictfp() {
+; CHECK-NEXT:    [[DIM:%.*]] = call double @fdim(double 1.000000e+01, double 8.000000e+00) #[[ATTR1:[0-9]+]]
+; CHECK-NEXT:    ret double [[DIM]]
+;
+  %dim = call double @fdim(double 10.0, double 8.0) strictfp
+  ret double %dim
+}
+
+define double @fdim_nan1() {
+; CHECK-LABEL: define double @fdim_nan1() {
+; CHECK-NEXT:    ret double 0x7FF8000000000000
+;
+  %dim = call double @fdim(double 10.0, double 0x7FF8000000000000)
+  ret double %dim
+}
+
+
+define double @fdim_nan2() {
+; CHECK-LABEL: define double @fdim_nan2() {
+; CHECK-NEXT:    ret double 0x7FF8000000000000
+;
+  %dim = call double @fdim(double 0x7FF8000000000000, double 1.4)
+  ret double %dim
+}
+
+define double @fdim_snan1() {
+; CHECK-LABEL: define double @fdim_snan1() {
+; CHECK-NEXT:    ret double 0x7FFC000000000000
+;
+  %dim = call double @fdim(double 0x7FF4000000000000, double 1.4)
+  ret double %dim
+}
+
+define double @fdim_snan2() {
+; CHECK-LABEL: define double @fdim_snan2() {
+; CHECK-NEXT:    ret double 0x7FFC000000000000
+;
+  %dim = call double @fdim(double 1.7, double 0x7FF4000000000000)
+  ret double %dim
+}
+
+declare double @fdim(double, double) #0
+declare float @fdimf(float, float) #0
+
+attributes #0 = { memory(none) }
diff --git a/llvm/test/Transforms/InstCombine/win-fdim.ll b/llvm/test/Transforms/InstCombine/win-fdim.ll
@@ -0,0 +1,36 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt %s -passes=instcombine -S -mtriple=i386-pc-windows-msvc | FileCheck %s --check-prefixes=MSVC19
+
+define double @fdim_double() {
+; MSVC19-LABEL: define double @fdim_double() {
+; MSVC19-NEXT:    ret double 2.500000e+00
+;
+  %dim = call double @fdim(double 10.5, double 8.0)
+  ret double %dim
+}
+
+;fdimf is not supported by windows
+define float @fdim_float() {
+; MSVC19-LABEL: define float @fdim_float() {
+; MSVC19-NEXT:    [[DIM:%.*]] = call float @fdimf(float 1.500000e+00, float 8.000000e+00)
+; MSVC19-NEXT:    ret float [[DIM]]
+;
+  %dim = call float @fdimf(float 1.500000e+00, float 8.0)
+  ret float %dim
+}
+
+;fdiml is not supported by windows
+define fp128 @fdim_long() {
+; MSVC19-LABEL: define fp128 @fdim_long() {
+; MSVC19-NEXT:    [[DIM:%.*]] = call fp128 @fdiml(fp128 0xL00000000000000000000000000000000, fp128 0xL00000000000000000000000000000000)
+; MSVC19-NEXT:    ret fp128 [[DIM]]
+;
+  %dim = call fp128 @fdiml(fp128  0xL00000000000000000000000000000000 , fp128 0xL00000000000000000000000000000000)
+  ret fp128 %dim
+}
+
+declare double @fdim(double, double) #0
+declare float @fdimf(float, float) #0
+declare fp128 @fdiml(fp128, fp128) #0
+
+attributes #0 = { memory(none) }