mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
[InstCombine] simplify masked store intrinsics with all ones or zeros masks
A masked store with a zero mask means there's no store. A masked store with an allOnes mask means it's a normal vector store. This is a continuation of: http://reviews.llvm.org/rL259369 llvm-svn: 259392
This commit is contained in:
parent
bd28c13e3a
commit
0a594deff4
@ -773,6 +773,25 @@ static Value *simplifyMaskedLoad(const IntrinsicInst &II,
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
static Instruction *simplifyMaskedStore(IntrinsicInst &II, InstCombiner &IC) {
|
||||
auto *ConstMask = dyn_cast<Constant>(II.getArgOperand(3));
|
||||
if (!ConstMask)
|
||||
return nullptr;
|
||||
|
||||
// If the mask is all zeros, this instruction does nothing.
|
||||
if (ConstMask->isNullValue())
|
||||
return IC.EraseInstFromFunction(II);
|
||||
|
||||
// If the mask is all ones, this is a plain vector store of the 1st argument.
|
||||
if (ConstMask->isAllOnesValue()) {
|
||||
Value *StorePtr = II.getArgOperand(1);
|
||||
unsigned Alignment = cast<ConstantInt>(II.getArgOperand(2))->getZExtValue();
|
||||
return new StoreInst(II.getArgOperand(0), StorePtr, false, Alignment);
|
||||
}
|
||||
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
/// CallInst simplification. This mostly only handles folding of intrinsic
|
||||
/// instructions. For normal calls, it allows visitCallSite to do the heavy
|
||||
/// lifting.
|
||||
@ -901,9 +920,10 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
|
||||
if (Value *SimplifiedMaskedOp = simplifyMaskedLoad(*II, *Builder))
|
||||
return ReplaceInstUsesWith(CI, SimplifiedMaskedOp);
|
||||
break;
|
||||
case Intrinsic::masked_store:
|
||||
return simplifyMaskedStore(*II, *this);
|
||||
|
||||
// TODO: Handle the other masked ops.
|
||||
// case Intrinsic::masked_store:
|
||||
// case Intrinsic::masked_gather:
|
||||
// case Intrinsic::masked_scatter:
|
||||
|
||||
|
@ -1,6 +1,7 @@
|
||||
; RUN: opt -instcombine -S < %s | FileCheck %s
|
||||
|
||||
declare <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptrs, i32, <2 x i1> %mask, <2 x double> %src0)
|
||||
declare void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptrs, i32, <2 x i1> %mask)
|
||||
|
||||
|
||||
define <2 x double> @load_zeromask(<2 x double>* %ptr, <2 x double> %passthru) {
|
||||
@ -20,3 +21,20 @@ define <2 x double> @load_onemask(<2 x double>* %ptr, <2 x double> %passthru) {
|
||||
; CHECK-NEXT: ret <2 x double> %unmaskedload
|
||||
}
|
||||
|
||||
define void @store_zeromask(<2 x double>* %ptr, <2 x double> %val) {
|
||||
call void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptr, i32 3, <2 x i1> zeroinitializer)
|
||||
ret void
|
||||
|
||||
; CHECK-LABEL: @store_zeromask(
|
||||
; CHECK-NEXT: ret void
|
||||
}
|
||||
|
||||
define void @store_onemask(<2 x double>* %ptr, <2 x double> %val) {
|
||||
call void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptr, i32 4, <2 x i1> <i1 1, i1 1>)
|
||||
ret void
|
||||
|
||||
; CHECK-LABEL: @store_onemask(
|
||||
; CHECK-NEXT: store <2 x double> %val, <2 x double>* %ptr, align 4
|
||||
; CHECK-NEXT: ret void
|
||||
}
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user