Skip to content

[Downstream change][LV] Workaround for sincos vectorization on aarch64-amazon-linux triple #279

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.

Sign up for GitHub

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

Closed
wants to merge 1 commit into from
Closed

[Downstream change][LV] Workaround for sincos vectorization on aarch64-amazon-linux triple #279

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 9 additions & 1 deletion llvm/include/llvm/CodeGen/BasicTTIImpl.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,8 +308,16 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
!isVectorizedStructTy(cast<StructType>(RetTy)))
return std::nullopt;

auto getLibcallName = [&] {
if (LC == RTLIB::SINCOS_F32)
return "sincosf";
if (LC == RTLIB::SINCOS_F64)
return "sincos";
return getTLI()->getLibcallName(LC);
};

// Find associated libcall.
const char *LCName = getTLI()->getLibcallName(LC);
const char *LCName = getLibcallName();
if (!LCName)
return std::nullopt;

Expand Down
14 changes: 13 additions & 1 deletion llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2554,7 +2554,19 @@ bool SelectionDAG::expandMultipleResultFPLibCall(
EVT VT = Node->getValueType(0);
unsigned NumResults = Node->getNumValues();

const char *LCName = TLI->getLibcallName(LC);
/* Downstream change: #87 (sincos vectorization)*/
auto getLibcallName = [&] {
if (VT.isVector()) {
if (LC == RTLIB::SINCOS_F32)
return "sincosf";
if (LC == RTLIB::SINCOS_F64)
return "sincos";
}
return TLI->getLibcallName(LC);
};
/* End downstream change: #87 */

const char *LCName = getLibcallName();
if (!LC || !LCName)
return false;

Expand Down
3 changes: 3 additions & 0 deletions llvm/test/CodeGen/AArch64/veclib-llvm.sincos.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --filter "(bl|ptrue)" --version 5
; RUN: llc -mtriple=aarch64-gnu-linux -mattr=+neon,+sve -vector-library=sleefgnuabi < %s | FileCheck %s -check-prefix=SLEEF
; RUN: llc -mtriple=aarch64-gnu-linux -mattr=+neon,+sve -vector-library=ArmPL < %s | FileCheck %s -check-prefix=ARMPL
; Check we expand to a vector library call on aarch64-amazon-linux:
; RUN: llc -mtriple=aarch64-amazon-linux -mattr=+neon,+sve -vector-library=sleefgnuabi < %s | FileCheck %s -check-prefix=SLEEF
; RUN: llc -mtriple=aarch64-amazon-linux -mattr=+neon,+sve -vector-library=ArmPL < %s | FileCheck %s -check-prefix=ARMPL

define void @test_sincos_v4f32(<4 x float> %x, ptr noalias %out_sin, ptr noalias %out_cos) {
; SLEEF-LABEL: test_sincos_v4f32:
Expand Down
3 changes: 3 additions & 0 deletions llvm/test/Transforms/LoopVectorize/AArch64/sincos.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,11 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --filter "(:|sincos|extractvalue|store)" --version 5
; RUN: opt -passes=loop-vectorize -mtriple=aarch64-gnu-linux -mcpu=neoverse-v1 -mattr=+sve < %s -S -o - -debug-only=loop-vectorize 2>%t.1 | FileCheck %s --check-prefix=CHECK
; RUN: opt -passes=loop-vectorize -mtriple=aarch64-gnu-linux -mcpu=neoverse-v1 -mattr=+sve -vector-library=ArmPL < %s -S -o - -debug-only=loop-vectorize 2>%t.2 | FileCheck %s --check-prefix=CHECK-ARMPL
; RUN: opt -passes=loop-vectorize -mtriple=aarch64-amazon-linux -mcpu=neoverse-v1 -mattr=+sve -vector-library=ArmPL < %s -S -o - -debug-only=loop-vectorize 2>%t.3 | FileCheck %s --check-prefix=CHECK-ARMPL
; RUN: FileCheck --input-file=%t.1 --check-prefix=CHECK-COST %s
; RUN: FileCheck --input-file=%t.2 --check-prefix=CHECK-COST-ARMPL %s
; Check we vectorize the functions with the vector-library on aarch64-amazon-linux:
; RUN: FileCheck --input-file=%t.3 --check-prefix=CHECK-COST-ARMPL %s
; REQUIRES: asserts

; CHECK-COST-LABEL: sincos_f32
Expand Down