Skip to content

[clang] Emit @llvm.assume before streaming_compatible functions when the streaming mode is known #121917

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

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[clang] Emit @llvm.assume before streaming_compatible functions when the streaming mode is known #121917

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
27e9773
[clang] Emit @llvm.assume when we know the streaming mode of the func…
NickGuy-Arm Jan 7, 2025
7cc6750
Format
NickGuy-Arm Jan 7, 2025
ac671ca
Add hook to allow targets to emit additional IR at call sites
NickGuy-Arm Jan 8, 2025
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
3 changes: 3 additions & 0 deletions clang/lib/CodeGen/CGCall.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5101,6 +5101,9 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
const FunctionDecl *CalleeDecl = dyn_cast_or_null<FunctionDecl>(TargetDecl);
CGM.getTargetCodeGenInfo().checkFunctionCallABI(CGM, Loc, CallerDecl,
CalleeDecl, CallArgs, RetTy);
// 0. Allow the target to emit an additional prolog for the function call
CGM.getTargetCodeGenInfo().emitFunctionCallProlog(Builder, CallerDecl,
CalleeDecl);

// 1. Set up the arguments.

Expand Down
4 changes: 4 additions & 0 deletions clang/lib/CodeGen/TargetInfo.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -443,6 +443,10 @@ class TargetCodeGenInfo {
return nullptr;
}

virtual void emitFunctionCallProlog(CGBuilderTy &Builder,
const FunctionDecl *Caller,
const FunctionDecl *Callee) const {}

// Set the Branch Protection Attributes of the Function accordingly to the
// BPI. Remove attributes that contradict with current BPI.
static void
Expand Down
29 changes: 29 additions & 0 deletions clang/lib/CodeGen/Targets/AArch64.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
#include "TargetInfo.h"
#include "clang/AST/Decl.h"
#include "clang/Basic/DiagnosticFrontend.h"
#include "llvm/IR/IntrinsicsAArch64.h"
#include "llvm/TargetParser/AArch64TargetParser.h"

using namespace clang;
Expand Down Expand Up @@ -181,6 +182,9 @@ class AArch64TargetCodeGenInfo : public TargetCodeGenInfo {
bool wouldInliningViolateFunctionCallABI(
const FunctionDecl *Caller, const FunctionDecl *Callee) const override;

void emitFunctionCallProlog(CGBuilderTy &Builder, const FunctionDecl *Caller,
const FunctionDecl *Callee) const override;

private:
// Diagnose calls between functions with incompatible Streaming SVE
// attributes.
Expand Down Expand Up @@ -1275,6 +1279,31 @@ bool AArch64TargetCodeGenInfo::wouldInliningViolateFunctionCallABI(
GetArmSMEInlinability(Caller, Callee) != ArmSMEInlinability::Ok;
}

void AArch64TargetCodeGenInfo::emitFunctionCallProlog(
CGBuilderTy &Builder, const FunctionDecl *Caller,
const FunctionDecl *Callee) const {
const AArch64ABIInfo &ABIInfo = getABIInfo<AArch64ABIInfo>();
const TargetInfo &TI = ABIInfo.getContext().getTargetInfo();

if (!TI.hasFeature("sme"))
return;

Comment on lines +1285 to +1290
Copy link
Collaborator

@sdesmalen-arm sdesmalen-arm Jan 8, 2025

Choose a reason for hiding this comment

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

Is this check really necessary?

if (!Callee || !isStreamingCompatible(Callee))
Copy link
Collaborator

@sdesmalen-arm sdesmalen-arm Jan 8, 2025

Choose a reason for hiding this comment

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

Can Caller be nullptr too?

return;

if (const auto *FPT = Caller->getType()->getAs<FunctionProtoType>()) {
unsigned SMEAttrs = FPT->getAArch64SMEAttributes();
if (!(SMEAttrs & FunctionType::SME_PStateSMCompatibleMask)) {
bool IsStreaming = SMEAttrs & FunctionType::SME_PStateSMEnabledMask;
Copy link
Collaborator

@sdesmalen-arm sdesmalen-arm Jan 8, 2025

Choose a reason for hiding this comment

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

nit:

Suggested change
bool IsStreaming = SMEAttrs & FunctionType::SME_PStateSMEnabledMask;
bool CallerIsStreaming = SMEAttrs & FunctionType::SME_PStateSMEnabledMask;

llvm::Value *Call = Builder.CreateIntrinsic(
llvm::Intrinsic::aarch64_sme_in_streaming_mode, {}, {});
if (!IsStreaming)
Call = Builder.CreateNot(Call);
Builder.CreateAssumption(Call);
}
}
}

void AArch64ABIInfo::appendAttributeMangling(TargetClonesAttr *Attr,
unsigned Index,
raw_ostream &Out) const {
Expand Down
25 changes: 12 additions & 13 deletions clang/test/CodeGen/AArch64/sme-intrinsics/acle_sme_state_funs.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@ bool test_in_streaming_mode_streaming_compatible(void) __arm_streaming_compatibl
// CPP-CHECK-NEXT: ret i1 true
//
bool test_in_streaming_mode_streaming(void) __arm_streaming {
//
return __arm_in_streaming_mode();
}

Expand All @@ -47,12 +46,12 @@ bool test_in_streaming_mode_non_streaming(void) {

// CHECK-LABEL: @test_za_disable(
// CHECK-NEXT: entry:
// CHECK-NEXT: tail call void @__arm_za_disable() #[[ATTR7:[0-9]+]]
// CHECK-NEXT: tail call void @__arm_za_disable() #[[ATTR8:[0-9]+]]
// CHECK-NEXT: ret void
//
// CPP-CHECK-LABEL: @_Z15test_za_disablev(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: tail call void @__arm_za_disable() #[[ATTR7:[0-9]+]]
// CPP-CHECK-NEXT: tail call void @__arm_za_disable() #[[ATTR8:[0-9]+]]
// CPP-CHECK-NEXT: ret void
//
void test_za_disable(void) __arm_streaming_compatible {
Expand All @@ -61,14 +60,14 @@ void test_za_disable(void) __arm_streaming_compatible {

// CHECK-LABEL: @test_has_sme(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call aarch64_sme_preservemost_from_x2 { i64, i64 } @__arm_sme_state() #[[ATTR7]]
// CHECK-NEXT: [[TMP0:%.*]] = tail call aarch64_sme_preservemost_from_x2 { i64, i64 } @__arm_sme_state() #[[ATTR8]]
// CHECK-NEXT: [[TMP1:%.*]] = extractvalue { i64, i64 } [[TMP0]], 0
// CHECK-NEXT: [[TOBOOL_I:%.*]] = icmp slt i64 [[TMP1]], 0
// CHECK-NEXT: ret i1 [[TOBOOL_I]]
//
// CPP-CHECK-LABEL: @_Z12test_has_smev(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call aarch64_sme_preservemost_from_x2 { i64, i64 } @__arm_sme_state() #[[ATTR7]]
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call aarch64_sme_preservemost_from_x2 { i64, i64 } @__arm_sme_state() #[[ATTR8]]
// CPP-CHECK-NEXT: [[TMP1:%.*]] = extractvalue { i64, i64 } [[TMP0]], 0
// CPP-CHECK-NEXT: [[TOBOOL_I:%.*]] = icmp slt i64 [[TMP1]], 0
// CPP-CHECK-NEXT: ret i1 [[TOBOOL_I]]
Expand All @@ -91,12 +90,12 @@ void test_svundef_za(void) __arm_streaming_compatible __arm_out("za") {

// CHECK-LABEL: @test_sc_memcpy(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memcpy(ptr noundef [[DEST:%.*]], ptr noundef [[SRC:%.*]], i64 noundef [[N:%.*]]) #[[ATTR7]]
// CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memcpy(ptr noundef [[DEST:%.*]], ptr noundef [[SRC:%.*]], i64 noundef [[N:%.*]]) #[[ATTR8]]
// CHECK-NEXT: ret ptr [[CALL]]
//
// CPP-CHECK-LABEL: @_Z14test_sc_memcpyPvPKvm(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memcpy(ptr noundef [[DEST:%.*]], ptr noundef [[SRC:%.*]], i64 noundef [[N:%.*]]) #[[ATTR7]]
// CPP-CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memcpy(ptr noundef [[DEST:%.*]], ptr noundef [[SRC:%.*]], i64 noundef [[N:%.*]]) #[[ATTR8]]
// CPP-CHECK-NEXT: ret ptr [[CALL]]
//
void *test_sc_memcpy(void *dest, const void *src, size_t n) __arm_streaming_compatible {
Expand All @@ -105,12 +104,12 @@ void *test_sc_memcpy(void *dest, const void *src, size_t n) __arm_streaming_comp

// CHECK-LABEL: @test_sc_memmove(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memmove(ptr noundef [[DEST:%.*]], ptr noundef [[SRC:%.*]], i64 noundef [[N:%.*]]) #[[ATTR7]]
// CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memmove(ptr noundef [[DEST:%.*]], ptr noundef [[SRC:%.*]], i64 noundef [[N:%.*]]) #[[ATTR8]]
// CHECK-NEXT: ret ptr [[CALL]]
//
// CPP-CHECK-LABEL: @_Z15test_sc_memmovePvPKvm(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memmove(ptr noundef [[DEST:%.*]], ptr noundef [[SRC:%.*]], i64 noundef [[N:%.*]]) #[[ATTR7]]
// CPP-CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memmove(ptr noundef [[DEST:%.*]], ptr noundef [[SRC:%.*]], i64 noundef [[N:%.*]]) #[[ATTR8]]
// CPP-CHECK-NEXT: ret ptr [[CALL]]
//
void *test_sc_memmove(void *dest, const void *src, size_t n) __arm_streaming_compatible {
Expand All @@ -119,12 +118,12 @@ void *test_sc_memmove(void *dest, const void *src, size_t n) __arm_streaming_com

// CHECK-LABEL: @test_sc_memset(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memset(ptr noundef [[S:%.*]], i32 noundef [[C:%.*]], i64 noundef [[N:%.*]]) #[[ATTR7]]
// CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memset(ptr noundef [[S:%.*]], i32 noundef [[C:%.*]], i64 noundef [[N:%.*]]) #[[ATTR8]]
// CHECK-NEXT: ret ptr [[CALL]]
//
// CPP-CHECK-LABEL: @_Z14test_sc_memsetPvim(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memset(ptr noundef [[S:%.*]], i32 noundef [[C:%.*]], i64 noundef [[N:%.*]]) #[[ATTR7]]
// CPP-CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memset(ptr noundef [[S:%.*]], i32 noundef [[C:%.*]], i64 noundef [[N:%.*]]) #[[ATTR8]]
// CPP-CHECK-NEXT: ret ptr [[CALL]]
//
void *test_sc_memset(void *s, int c, size_t n) __arm_streaming_compatible {
Expand All @@ -133,12 +132,12 @@ void *test_sc_memset(void *s, int c, size_t n) __arm_streaming_compatible {

// CHECK-LABEL: @test_sc_memchr(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memchr(ptr noundef [[S:%.*]], i32 noundef [[C:%.*]], i64 noundef [[N:%.*]]) #[[ATTR7]]
// CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memchr(ptr noundef [[S:%.*]], i32 noundef [[C:%.*]], i64 noundef [[N:%.*]]) #[[ATTR8]]
// CHECK-NEXT: ret ptr [[CALL]]
//
// CPP-CHECK-LABEL: @_Z14test_sc_memchrPvim(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memchr(ptr noundef [[S:%.*]], i32 noundef [[C:%.*]], i64 noundef [[N:%.*]]) #[[ATTR7]]
// CPP-CHECK-NEXT: [[CALL:%.*]] = tail call ptr @__arm_sc_memchr(ptr noundef [[S:%.*]], i32 noundef [[C:%.*]], i64 noundef [[N:%.*]]) #[[ATTR8]]
// CPP-CHECK-NEXT: ret ptr [[CALL]]
//
void *test_sc_memchr(void *s, int c, size_t n) __arm_streaming_compatible {
Expand Down
Loading