Skip to content

[SimplifyLibCalls] Constant fold remquo #99647

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Jul 24, 2024
Merged
Show file tree
Hide file tree
Changes from 4 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions llvm/include/llvm/Transforms/Utils/SimplifyLibCalls.h
Original file line number Diff line number Diff line change
Expand Up @@ -205,6 +205,7 @@ class LibCallSimplifier {
Value *optimizeSinCosPi(CallInst *CI, bool IsSin, IRBuilderBase &B);
Value *optimizeTrigInversionPairs(CallInst *CI, IRBuilderBase &B);
Value *optimizeSymmetric(CallInst *CI, LibFunc Func, IRBuilderBase &B);
Value *optimizeRemquo(CallInst *CI, IRBuilderBase &B);
// Wrapper for all floating point library call optimizations
Value *optimizeFloatingPointLibCall(CallInst *CI, LibFunc Func,
IRBuilderBase &B);
Expand Down
37 changes: 37 additions & 0 deletions llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -3018,6 +3018,39 @@ void LibCallSimplifier::classifyArgUse(
}
}

/// Constant folds remquo
Value *LibCallSimplifier::optimizeRemquo(CallInst *CI, IRBuilderBase &B) {
const APFloat *X, *Y;
if (!match(CI->getArgOperand(0), m_APFloat(X)) ||
!match(CI->getArgOperand(1), m_APFloat(Y)))
return nullptr;

if (X->isNaN() || Y->isNaN() || X->isInfinity() || Y->isZero())
return nullptr;

APFloat::opStatus Status;
APFloat Quot = *X;
Status = Quot.divide(*Y, APFloat::rmNearestTiesToEven);
if (Status != APFloat::opOK && Status != APFloat::opInexact)
return nullptr;
APFloat Rem = *X;
if (Rem.remainder(*Y) != APFloat::opOK)
return nullptr;

// TODO: We can only keep at least the three of the last bits of x/y
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The current implementation is slightly conservative. The integer part of x/y may be out of range of i32.

unsigned IntBW = TLI->getIntSize();
APSInt QuotInt(IntBW, /*isUnsigned=*/false);
bool IsExact;
Status =
Quot.convertToInteger(QuotInt, APFloat::rmNearestTiesToEven, &IsExact);
if (Status != APFloat::opOK && Status != APFloat::opInexact)
return nullptr;

B.CreateAlignedStore(ConstantInt::get(B.getIntNTy(IntBW), QuotInt.getExtValue()),
CI->getArgOperand(2), CI->getParamAlign(2));
return ConstantFP::get(CI->getType(), Rem);
}

//===----------------------------------------------------------------------===//
// Integer Library Call Optimizations
//===----------------------------------------------------------------------===//
Expand Down Expand Up @@ -3926,6 +3959,10 @@ Value *LibCallSimplifier::optimizeFloatingPointLibCall(CallInst *CI,
case LibFunc_cabsf:
case LibFunc_cabsl:
return optimizeCAbs(CI, Builder);
case LibFunc_remquo:
case LibFunc_remquof:
case LibFunc_remquol:
return optimizeRemquo(CI, Builder);
default:
return nullptr;
}
Expand Down
103 changes: 103 additions & 0 deletions llvm/test/Transforms/InstCombine/remquo.ll
Original file line number Diff line number Diff line change
@@ -0,0 +1,103 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -passes=instcombine -S | FileCheck %s

define float @remquo_f32(ptr %quo) {
; CHECK-LABEL: define float @remquo_f32(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: store i32 -2, ptr [[QUO]], align 4
; CHECK-NEXT: ret float 1.000000e+00
;
entry:
%call = call float @remquof(float -5.000000e+00, float 3.000000e+00, ptr %quo)
ret float %call
}

define float @remquo_f32_quo_sign(ptr %quo) {
; CHECK-LABEL: define float @remquo_f32_quo_sign(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: store i32 2, ptr [[QUO]], align 4
; CHECK-NEXT: ret float -1.000000e+00
;
entry:
%call = call float @remquof(float 5.000000e+00, float 3.000000e+00, ptr %quo)
ret float %call
}

define float @remquo_f32_round(ptr %quo) {
; CHECK-LABEL: define float @remquo_f32_round(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: store i32 -6, ptr [[QUO]], align 4
; CHECK-NEXT: ret float 0xBFC9999900000000
;
entry:
%call = call float @remquof(float -5.000000e+00, float 0x3FE99999A0000000, ptr %quo)
ret float %call
}

define double @remquo_f64(ptr %quo) {
; CHECK-LABEL: define double @remquo_f64(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: store i32 -5, ptr [[QUO]], align 4
; CHECK-NEXT: ret double -0.000000e+00
;
entry:
%call = call double @remquo(double -5.000000e+00, double 1.000000e+00, ptr %quo)
ret double %call
}

; Negative tests

define float @remquo_f32_inf_x(ptr %quo) {
; CHECK-LABEL: define float @remquo_f32_inf_x(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[CALL:%.*]] = call float @remquof(float 0x7FF0000000000000, float 1.000000e+00, ptr [[QUO]])
; CHECK-NEXT: ret float [[CALL]]
;
entry:
%call = call float @remquof(float 0x7FF0000000000000, float 1.000000e+00, ptr %quo)
ret float %call
}

define float @remquo_f32_zero_y(ptr %quo) {
; CHECK-LABEL: define float @remquo_f32_zero_y(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[CALL:%.*]] = call float @remquof(float -5.000000e+00, float 0.000000e+00, ptr [[QUO]])
; CHECK-NEXT: ret float [[CALL]]
;
entry:
%call = call float @remquof(float -5.000000e+00, float 0.000000e+00, ptr %quo)
ret float %call
}

define float @remquo_f32_nan_x(ptr %quo) {
; CHECK-LABEL: define float @remquo_f32_nan_x(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[CALL:%.*]] = call float @remquof(float 0x7FF8000000000000, float 1.000000e+00, ptr [[QUO]])
; CHECK-NEXT: ret float [[CALL]]
;
entry:
%call = call float @remquof(float 0x7FF8000000000000, float 1.000000e+00, ptr %quo)
ret float %call
}

define float @remquo_f32_nan_y(ptr %quo) {
; CHECK-LABEL: define float @remquo_f32_nan_y(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[CALL:%.*]] = call float @remquof(float 1.000000e+00, float 0x7FF8000000000000, ptr [[QUO]])
; CHECK-NEXT: ret float [[CALL]]
;
entry:
%call = call float @remquof(float 1.000000e+00, float 0x7FF8000000000000, ptr %quo)
ret float %call
}

declare float @remquof(float, float, ptr)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Need a non-edgcase strictfp case?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

See remquo_f32_strictfp

declare double @remquo(double, double, ptr)
16 changes: 16 additions & 0 deletions llvm/test/Transforms/InstCombine/remquol-fp128.ll
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -passes=instcombine -S | FileCheck %s

define fp128 @remquo_fp128(ptr %quo) {
; CHECK-LABEL: define fp128 @remquo_fp128(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: store i32 -2, ptr [[QUO]], align 4
; CHECK-NEXT: ret fp128 0xL00000000000000003FFF000000000000
;
entry:
%call = call fp128 @remquol(fp128 0xL0000000000000000C001400000000000, fp128 0xL00000000000000004000800000000000, ptr %quo)
ret fp128 %call
}

declare fp128 @remquol(fp128, fp128, ptr)
16 changes: 16 additions & 0 deletions llvm/test/Transforms/InstCombine/remquol-fp80.ll
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -passes=instcombine -S | FileCheck %s

define x86_fp80 @remquo_fp80(ptr %quo) {
; CHECK-LABEL: define x86_fp80 @remquo_fp80(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: store i32 -2, ptr [[QUO]], align 4
; CHECK-NEXT: ret x86_fp80 0xK3FFF8000000000000000
;
entry:
%call = call x86_fp80 @remquol(x86_fp80 0xKC001A000000000000000, x86_fp80 0xK4000C000000000000000, ptr %quo)
ret x86_fp80 %call
}

declare x86_fp80 @remquol(x86_fp80, x86_fp80, ptr)
16 changes: 16 additions & 0 deletions llvm/test/Transforms/InstCombine/remquol-ppc-fp128.ll
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -passes=instcombine -S | FileCheck %s

define ppc_fp128 @remquo_ppc_fp128(ptr %quo) {
; CHECK-LABEL: define ppc_fp128 @remquo_ppc_fp128(
; CHECK-SAME: ptr [[QUO:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: store i32 -2, ptr [[QUO]], align 4
; CHECK-NEXT: ret ppc_fp128 0xM3FF00000000000000000000000000000
;
entry:
%call = call ppc_fp128 @remquol(ppc_fp128 0xMC0140000000000000000000000000000, ppc_fp128 0xM40080000000000000000000000000000, ptr %quo)
ret ppc_fp128 %call
}

declare ppc_fp128 @remquol(ppc_fp128, ppc_fp128, ptr)
Loading