maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Replace hardcoded intrinsic list with speculatable attribute. 

No change in which intrinsics should be speculated.

llvm-svn: 301995
This commit is contained in:
Matt Arsenault 2017-05-03 02:26:10 +00:00
parent 8955efc36f
commit 6a288c1e32
12 changed files with 44 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
llvm/include/llvm/IR/Intrinsics.td
View File

@ -404,7 +404,7 @@ def int_memset : Intrinsic<[],
// FIXME: Add version of these floating point intrinsics which allow non-default
// rounding modes and FP exception handling.
let IntrProperties = [IntrNoMem] in {
let IntrProperties = [IntrNoMem, IntrSpeculatable] in {
def int_fma : Intrinsic<[llvm_anyfloat_ty],
[LLVMMatchType<0>, LLVMMatchType<0>,
LLVMMatchType<0>]>;
@ -440,10 +440,12 @@ let IntrProperties = [IntrNoMem] in {
}
def int_minnum : Intrinsic<[llvm_anyfloat_ty],
[LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem, Commutative]
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem, IntrSpeculatable, Commutative]
>;
def int_maxnum : Intrinsic<[llvm_anyfloat_ty],
[LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem, Commutative]
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem, IntrSpeculatable, Commutative]
>;
// NOTE: these are internal interfaces.
@ -455,7 +457,7 @@ def int_siglongjmp : Intrinsic<[], [llvm_ptr_ty, llvm_i32_ty], [IntrNoReturn]>;
// Internal interface for object size checking
def int_objectsize : Intrinsic<[llvm_anyint_ty],
[llvm_anyptr_ty, llvm_i1_ty, llvm_i1_ty],
[IntrNoMem]>,
[IntrNoMem, IntrSpeculatable]>,
GCCBuiltin<"__builtin_object_size">;
//===--------------- Constrained Floating Point Intrinsics ----------------===//
@ -500,7 +502,7 @@ def int_expect : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>,
//
// None of these intrinsics accesses memory at all.
let IntrProperties = [IntrNoMem] in {
let IntrProperties = [IntrNoMem, IntrSpeculatable] in {
def int_bswap: Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>]>;
def int_ctpop: Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>]>;
def int_ctlz : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i1_ty]>;
@ -511,10 +513,11 @@ let IntrProperties = [IntrNoMem] in {
//===------------------------ Debugger Intrinsics -------------------------===//
//
// None of these intrinsics accesses memory at all...but that doesn't mean the
// optimizers can change them aggressively. Special handling needed in a few
// places.
let IntrProperties = [IntrNoMem] in {
// None of these intrinsics accesses memory at all...but that doesn't
// mean the optimizers can change them aggressively. Special handling
// needed in a few places. These synthetic intrinsics have no
// side-effects and just mark information about their operands.
let IntrProperties = [IntrNoMem, IntrSpeculatable] in {
def int_dbg_declare : Intrinsic<[],
[llvm_metadata_ty,
llvm_metadata_ty,
@ -592,24 +595,24 @@ def int_adjust_trampoline : Intrinsic<[llvm_ptr_ty], [llvm_ptr_ty],
// Expose the carry flag from add operations on two integrals.
def int_sadd_with_overflow : Intrinsic<[llvm_anyint_ty, llvm_i1_ty],
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem]>;
[IntrNoMem, IntrSpeculatable]>;
def int_uadd_with_overflow : Intrinsic<[llvm_anyint_ty, llvm_i1_ty],
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem]>;
[IntrNoMem, IntrSpeculatable]>;
def int_ssub_with_overflow : Intrinsic<[llvm_anyint_ty, llvm_i1_ty],
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem]>;
[IntrNoMem, IntrSpeculatable]>;
def int_usub_with_overflow : Intrinsic<[llvm_anyint_ty, llvm_i1_ty],
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem]>;
[IntrNoMem, IntrSpeculatable]>;
def int_smul_with_overflow : Intrinsic<[llvm_anyint_ty, llvm_i1_ty],
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem]>;
[IntrNoMem, IntrSpeculatable]>;
def int_umul_with_overflow : Intrinsic<[llvm_anyint_ty, llvm_i1_ty],
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem]>;
[IntrNoMem, IntrSpeculatable]>;
//===------------------------- Memory Use Markers -------------------------===//
//
@ -633,7 +636,7 @@ def int_invariant_end : Intrinsic<[],
// it can be CSE only if memory didn't change between 2 barriers call,
// which is valid.
// The argument also can't be marked with 'returned' attribute, because
// it would remove barrier.
// it would remove barrier.
def int_invariant_group_barrier : Intrinsic<[llvm_ptr_ty],
[llvm_ptr_ty],
[IntrReadMem, IntrArgMemOnly]>;

63
llvm/lib/Analysis/ValueTracking.cpp
View File

@ -3320,67 +3320,10 @@ bool llvm::isSafeToSpeculativelyExecute(const Value *V,
case Instruction::Call: {
auto *CI = cast<const CallInst>(Inst);
const Function *Callee = CI->getCalledFunction();
if (Callee && Callee->isSpeculatable())
return true;
if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(Inst)) {
switch (II->getIntrinsicID()) {
// These synthetic intrinsics have no side-effects and just mark
// information about their operands.
// FIXME: There are other no-op synthetic instructions that potentially
// should be considered at least *safe* to speculate...
// FIXME: The speculatable attribute should be added to all these
// intrinsics and this case statement should be removed.
case Intrinsic::dbg_declare:
case Intrinsic::dbg_value:
return true;
case Intrinsic::bitreverse:
case Intrinsic::bswap:
case Intrinsic::ctlz:
case Intrinsic::ctpop:
case Intrinsic::cttz:
case Intrinsic::objectsize:
case Intrinsic::sadd_with_overflow:
case Intrinsic::smul_with_overflow:
case Intrinsic::ssub_with_overflow:
case Intrinsic::uadd_with_overflow:
case Intrinsic::umul_with_overflow:
case Intrinsic::usub_with_overflow:
return true;
// These intrinsics are defined to have the same behavior as libm
// functions except for setting errno.
case Intrinsic::sqrt:
case Intrinsic::fma:
case Intrinsic::fmuladd:
return true;
// These intrinsics are defined to have the same behavior as libm
// functions, and the corresponding libm functions never set errno.
case Intrinsic::trunc:
case Intrinsic::copysign:
case Intrinsic::fabs:
case Intrinsic::minnum:
case Intrinsic::maxnum:
return true;
// These intrinsics are defined to have the same behavior as libm
// functions, which never overflow when operating on the IEEE754 types
// that we support, and never set errno otherwise.
case Intrinsic::ceil:
case Intrinsic::floor:
case Intrinsic::nearbyint:
case Intrinsic::rint:
case Intrinsic::round:
return true;
// These intrinsics do not correspond to any libm function, and
// do not set errno.
case Intrinsic::powi:
return true;
// TODO: are convert_{from,to}_fp16 safe?
// TODO: can we list target-specific intrinsics here?
default: break;
}
}
return false; // The called function could have undefined behavior or
// side-effects, even if marked readnone nounwind.
// The called function could have undefined behavior or side-effects, even
// if marked readnone nounwind.
return Callee && Callee->isSpeculatable();
}
case Instruction::VAArg:
case Instruction::Alloca:

8
llvm/lib/Transforms/Utils/BuildLibCalls.cpp
View File

@ -889,7 +889,13 @@ Value *llvm::emitUnaryFloatFnCall(Value *Op, StringRef Name, IRBuilder<> &B,
Value *Callee = M->getOrInsertFunction(Name, Op->getType(),
Op->getType());
CallInst *CI = B.CreateCall(Callee, Op, Name);
CI->setAttributes(Attrs);
// The incoming attribute set may have come from a speculatable intrinsic, but
// is being replaced with a library call which is not allowed to be
// speculatable.
CI->setAttributes(Attrs.removeAttribute(B.getContext(),
AttributeList::FunctionIndex,
Attribute::Speculatable));
if (const Function *F = dyn_cast<Function>(Callee->stripPointerCasts()))
CI->setCallingConv(F->getCallingConv());

2
llvm/test/Feature/intrinsics.ll
View File

@ -69,5 +69,5 @@ define void @trap() {
ret void
}
; CHECK: attributes #0 = { nounwind readnone }
; CHECK: attributes #0 = { nounwind readnone speculatable }
; CHECK: attributes #1 = { noreturn nounwind }

2
llvm/test/Transforms/BBVectorize/simple-int.ll
View File

@ -503,4 +503,4 @@ define i64 @testcttzneg(i64 %A1, i64 %A2, i64 %B1, i64 %B2) {
; CHECK: declare <2 x i64> @llvm.ctpop.v2i64(<2 x i64>) #0
; CHECK: declare <2 x i64> @llvm.ctlz.v2i64(<2 x i64>, i1) #0
; CHECK: declare <2 x i64> @llvm.cttz.v2i64(<2 x i64>, i1) #0
; CHECK: attributes #0 = { nounwind readnone }
; CHECK: attributes #0 = { nounwind readnone speculatable }

2
llvm/test/Transforms/DeadArgElim/2010-04-30-DbgInfo.ll
View File

@ -39,7 +39,7 @@ bb2: ; preds = %bb1, %bb
declare void @llvm.dbg.value(metadata, i64, metadata, metadata) nounwind readnone
; CHECK: attributes #0 = { nounwind ssp }
; CHECK: attributes #1 = { nounwind readnone }
; CHECK: attributes #1 = { nounwind readnone speculatable }
; CHECK: attributes #2 = { noinline nounwind ssp }
; CHECK: attributes [[NUW]] = { nounwind }

4
llvm/test/Transforms/InstCombine/intrinsics.ll
View File

@ -284,7 +284,7 @@ define i32 @cttz(i32 %a) {
define i1 @cttz_knownbits(i32 %arg) {
; CHECK-LABEL: @cttz_knownbits(
; CHECK-NEXT: [[OR:%.*]] = or i32 [[ARG:%.*]], 4
; CHECK-NEXT: [[CNT:%.*]] = call i32 @llvm.cttz.i32(i32 [[OR]], i1 true) #0
; CHECK-NEXT: [[CNT:%.*]] = call i32 @llvm.cttz.i32(i32 [[OR]], i1 true)
; CHECK-NEXT: [[RES:%.*]] = icmp eq i32 [[CNT]], 4
; CHECK-NEXT: ret i1 [[RES]]
;
@ -307,7 +307,7 @@ define i8 @ctlz(i8 %a) {
define i1 @ctlz_knownbits(i8 %arg) {
; CHECK-LABEL: @ctlz_knownbits(
; CHECK-NEXT: [[OR:%.*]] = or i8 [[ARG:%.*]], 32
; CHECK-NEXT: [[CNT:%.*]] = call i8 @llvm.ctlz.i8(i8 [[OR]], i1 true) #0
; CHECK-NEXT: [[CNT:%.*]] = call i8 @llvm.ctlz.i8(i8 [[OR]], i1 true)
; CHECK-NEXT: [[RES:%.*]] = icmp eq i8 [[CNT]], 4
; CHECK-NEXT: ret i1 [[RES]]
;

9
llvm/test/Transforms/InstCombine/pow-sqrt.ll
View File

@ -6,7 +6,7 @@ define double @pow_half(double %x) {
}
; CHECK-LABEL: define double @pow_half(
; CHECK-NEXT: %sqrt = call fast double @sqrt(double %x)
; CHECK-NEXT: %sqrt = call fast double @sqrt(double %x) #1
; CHECK-NEXT: ret double %sqrt
define double @pow_neghalf(double %x) {
@ -15,8 +15,11 @@ define double @pow_neghalf(double %x) {
}
; CHECK-LABEL: define double @pow_neghalf(
; CHECK-NEXT: %sqrt = call fast double @sqrt(double %x) #0
; CHECK-NEXT: %sqrt = call fast double @sqrt(double %x) #1
; CHECK-NEXT: %sqrtrecip = fdiv fast double 1.000000e+00, %sqrt
; CHECK-NEXT: ret double %sqrtrecip
declare double @llvm.pow.f64(double, double)
declare double @llvm.pow.f64(double, double) #0
attributes #0 = { nounwind readnone speculatable }
attributes #1 = { nounwind readnone }

2
llvm/test/Transforms/InstCombine/sub-xor.ll
View File

@ -27,7 +27,7 @@ declare i32 @llvm.ctlz.i32(i32, i1) nounwind readnone
define i32 @test2(i32 %x) nounwind {
; CHECK-LABEL: @test2(
; CHECK-NEXT: [[COUNT:%.*]] = tail call i32 @llvm.ctlz.i32(i32 %x, i1 true) #0
; CHECK-NEXT: [[COUNT:%.*]] = tail call i32 @llvm.ctlz.i32(i32 %x, i1 true)
; CHECK-NEXT: [[SUB:%.*]] = xor i32 [[COUNT]], 31
; CHECK-NEXT: ret i32 [[SUB]]
;

2
llvm/test/Transforms/ObjCARC/basic.ll
View File

@ -3049,6 +3049,6 @@ define void @test67(i8* %x) {
!4 = !DIFile(filename: "path/to/file", directory: "/path/to/dir")
!5 = !{i32 2, !"Debug Info Version", i32 3}
; CHECK: attributes #0 = { nounwind readnone }
; CHECK: attributes #0 = { nounwind readnone speculatable }
; CHECK: attributes [[NUW]] = { nounwind }
; CHECK: ![[RELEASE]] = !{}

2
llvm/test/Transforms/ObjCARC/ensure-that-exception-unwind-path-is-visited.ll
View File

@ -105,7 +105,7 @@ declare void @NSLog(i8*, ...)
declare void @llvm.dbg.value(metadata, i64, metadata, metadata) nounwind readnone
; CHECK: attributes #0 = { ssp uwtable }
; CHECK: attributes #1 = { nounwind readnone }
; CHECK: attributes #1 = { nounwind readnone speculatable }
; CHECK: attributes #2 = { nonlazybind }
; CHECK: attributes #3 = { noinline ssp uwtable }
; CHECK: attributes [[NUW]] = { nounwind }

2
llvm/test/Transforms/SLPVectorizer/X86/call.ll
View File

@ -147,5 +147,5 @@ entry:
; CHECK: declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>) [[ATTR0]]
; CHECK: declare <2 x double> @llvm.exp2.v2f64(<2 x double>) [[ATTR0]]
; CHECK: attributes [[ATTR0]] = { nounwind readnone }
; CHECK: attributes [[ATTR0]] = { nounwind readnone speculatable }