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

[CostModel] rearrange basic intrinsic cost implementation 

This is bigger/uglier than before, but it should allow fixing
all of the broken paths more easily. Test coverage added with
rGfab028b and other commits.

This is not NFC - the scalable vector test would crash
without this patch.
This commit is contained in:
Sanjay Patel 2020-10-13 11:52:00 -04:00
parent 1b94261e36
commit ef748583c2
2 changed files with 66 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
llvm/include/llvm/CodeGen/BasicTTIImpl.h
View File

@ -1125,32 +1125,14 @@ public:
if (BaseT::getIntrinsicInstrCost(ICA, CostKind) == 0)
return 0;
// Special case some scalar intrinsics.
Intrinsic::ID IID = ICA.getID();
if (CostKind != TTI::TCK_RecipThroughput) {
switch (IID) {
default:
break;
case Intrinsic::cttz:
if (getTLI()->isCheapToSpeculateCttz())
return TargetTransformInfo::TCC_Basic;
break;
case Intrinsic::ctlz:
if (getTLI()->isCheapToSpeculateCtlz())
return TargetTransformInfo::TCC_Basic;
break;
case Intrinsic::memcpy:
return thisT()->getMemcpyCost(ICA.getInst());
// TODO: other libc intrinsics.
}
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
}
// TODO: Combine these two logic paths.
if (ICA.isTypeBasedOnly())
return getTypeBasedIntrinsicInstrCost(ICA, CostKind);
// TODO: Handle scalable vectors?
Type *RetTy = ICA.getReturnType();
if (isa<ScalableVectorType>(RetTy))
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
unsigned VF = ICA.getVectorFactor();
unsigned RetVF =
(RetTy->isVectorTy() ? cast<FixedVectorType>(RetTy)->getNumElements()
@ -1159,11 +1141,42 @@ public:
const IntrinsicInst *I = ICA.getInst();
const SmallVectorImpl<const Value *> &Args = ICA.getArgs();
FastMathFlags FMF = ICA.getFlags();
Intrinsic::ID IID = ICA.getID();
switch (IID) {
default:
// FIXME: all cost kinds should default to the same thing?
if (CostKind != TTI::TCK_RecipThroughput)
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
break;
case Intrinsic::cttz:
// FIXME: all cost kinds should default to the same thing?
if (CostKind != TTI::TCK_RecipThroughput) {
if (getTLI()->isCheapToSpeculateCttz())
return TargetTransformInfo::TCC_Basic;
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
}
break;
case Intrinsic::ctlz:
// FIXME: all cost kinds should default to the same thing?
if (CostKind != TTI::TCK_RecipThroughput) {
if (getTLI()->isCheapToSpeculateCtlz())
return TargetTransformInfo::TCC_Basic;
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
}
break;
case Intrinsic::memcpy:
// FIXME: all cost kinds should default to the same thing?
if (CostKind != TTI::TCK_RecipThroughput)
return thisT()->getMemcpyCost(ICA.getInst());
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
case Intrinsic::masked_scatter: {
// FIXME: all cost kinds should default to the same thing?
if (CostKind != TTI::TCK_RecipThroughput)
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
assert(VF == 1 && "Can't vectorize types here.");
const Value *Mask = Args[3];
bool VarMask = !isa<Constant>(Mask);
@ -1173,6 +1186,9 @@ public:
VarMask, Alignment, CostKind, I);
}
case Intrinsic::masked_gather: {
// FIXME: all cost kinds should default to the same thing?
if (CostKind != TTI::TCK_RecipThroughput)
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
assert(VF == 1 && "Can't vectorize types here.");
const Value *Mask = Args[2];
bool VarMask = !isa<Constant>(Mask);
@ -1193,11 +1209,17 @@ public:
case Intrinsic::vector_reduce_fmin:
case Intrinsic::vector_reduce_umax:
case Intrinsic::vector_reduce_umin: {
// FIXME: all cost kinds should default to the same thing?
if (CostKind != TTI::TCK_RecipThroughput)
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
IntrinsicCostAttributes Attrs(IID, RetTy, Args[0]->getType(), FMF, 1, I);
return getTypeBasedIntrinsicInstrCost(Attrs, CostKind);
}
case Intrinsic::fshl:
case Intrinsic::fshr: {
// FIXME: all cost kinds should default to the same thing?
if (CostKind != TTI::TCK_RecipThroughput)
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
const Value *X = Args[0];
const Value *Y = Args[1];
const Value *Z = Args[2];

21
llvm/test/Analysis/CostModel/AArch64/sve-math.ll
View File

@ -26,3 +26,24 @@ define <vscale x 2 x double> @fadd_v2f64(<vscale x 2 x double> %a, <vscale x 2 x
%r = fadd <vscale x 2 x double> %a, %b
ret <vscale x 2 x double> %r
}
define <vscale x 2 x double> @sqrt_v2f64(<vscale x 2 x double> %a) {
; THRU-LABEL: 'sqrt_v2f64'
; THRU-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> %a)
; THRU-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 2 x double> %r
;
; LATE-LABEL: 'sqrt_v2f64'
; LATE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> %a)
; LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <vscale x 2 x double> %r
;
; SIZE-LABEL: 'sqrt_v2f64'
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> %a)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <vscale x 2 x double> %r
;
; SIZE_LATE-LABEL: 'sqrt_v2f64'
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> %a)
; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <vscale x 2 x double> %r
;
%r = call <vscale x 2 x double> @llvm.sqrt.v2f64(<vscale x 2 x double> %a)
ret <vscale x 2 x double> %r
}