[Clang] New loop pragma vectorize_predicate
This adds a new vectorize predication loop hint:
#pragma clang loop vectorize_predicate(enable)
that can be used to indicate to the vectoriser that all (load/store)
instructions should be predicated (masked). This allows, for example, folding
of the remainder loop into the main loop.
This patch will be followed up with D64916 and D65197. The former is a
refactoring in the loopvectorizer and the groundwork to make tail loop folding
a more general concept, and in the latter the actual tail loop folding
transformation will be implemented.
Differential Revision: https://reviews.llvm.org/D64744
llvm-svn: 366989
diff --git a/clang/lib/CodeGen/CGLoopInfo.cpp b/clang/lib/CodeGen/CGLoopInfo.cpp
index b2bc42bf..8e4a0a2 100644
--- a/clang/lib/CodeGen/CGLoopInfo.cpp
+++ b/clang/lib/CodeGen/CGLoopInfo.cpp
@@ -218,6 +218,7 @@
if (Attrs.VectorizeEnable == LoopAttributes::Disable)
Enabled = false;
else if (Attrs.VectorizeEnable != LoopAttributes::Unspecified ||
+ Attrs.VectorizePredicateEnable != LoopAttributes::Unspecified ||
Attrs.InterleaveCount != 0 || Attrs.VectorizeWidth != 0)
Enabled = true;
@@ -251,6 +252,16 @@
Args.push_back(TempNode.get());
Args.append(LoopProperties.begin(), LoopProperties.end());
+ // Setting vectorize.predicate
+ if (Attrs.VectorizePredicateEnable != LoopAttributes::Unspecified) {
+ Metadata *Vals[] = {
+ MDString::get(Ctx, "llvm.loop.vectorize.predicate.enable"),
+ ConstantAsMetadata::get(ConstantInt::get(
+ llvm::Type::getInt1Ty(Ctx),
+ (Attrs.VectorizePredicateEnable == LoopAttributes::Enable)))};
+ Args.push_back(MDNode::get(Ctx, Vals));
+ }
+
// Setting vectorize.width
if (Attrs.VectorizeWidth > 0) {
Metadata *Vals[] = {
@@ -411,7 +422,8 @@
LoopAttributes::LoopAttributes(bool IsParallel)
: IsParallel(IsParallel), VectorizeEnable(LoopAttributes::Unspecified),
UnrollEnable(LoopAttributes::Unspecified),
- UnrollAndJamEnable(LoopAttributes::Unspecified), VectorizeWidth(0),
+ UnrollAndJamEnable(LoopAttributes::Unspecified),
+ VectorizePredicateEnable(LoopAttributes::Unspecified), VectorizeWidth(0),
InterleaveCount(0), UnrollCount(0), UnrollAndJamCount(0),
DistributeEnable(LoopAttributes::Unspecified), PipelineDisabled(false),
PipelineInitiationInterval(0) {}
@@ -425,6 +437,7 @@
VectorizeEnable = LoopAttributes::Unspecified;
UnrollEnable = LoopAttributes::Unspecified;
UnrollAndJamEnable = LoopAttributes::Unspecified;
+ VectorizePredicateEnable = LoopAttributes::Unspecified;
DistributeEnable = LoopAttributes::Unspecified;
PipelineDisabled = false;
PipelineInitiationInterval = 0;
@@ -446,6 +459,7 @@
Attrs.InterleaveCount == 0 && Attrs.UnrollCount == 0 &&
Attrs.UnrollAndJamCount == 0 && !Attrs.PipelineDisabled &&
Attrs.PipelineInitiationInterval == 0 &&
+ Attrs.VectorizePredicateEnable == LoopAttributes::Unspecified &&
Attrs.VectorizeEnable == LoopAttributes::Unspecified &&
Attrs.UnrollEnable == LoopAttributes::Unspecified &&
Attrs.UnrollAndJamEnable == LoopAttributes::Unspecified &&
@@ -480,6 +494,7 @@
BeforeJam.InterleaveCount = Attrs.InterleaveCount;
BeforeJam.VectorizeEnable = Attrs.VectorizeEnable;
BeforeJam.DistributeEnable = Attrs.DistributeEnable;
+ BeforeJam.VectorizePredicateEnable = Attrs.VectorizePredicateEnable;
switch (Attrs.UnrollEnable) {
case LoopAttributes::Unspecified:
@@ -495,6 +510,7 @@
break;
}
+ AfterJam.VectorizePredicateEnable = Attrs.VectorizePredicateEnable;
AfterJam.UnrollCount = Attrs.UnrollCount;
AfterJam.PipelineDisabled = Attrs.PipelineDisabled;
AfterJam.PipelineInitiationInterval = Attrs.PipelineInitiationInterval;
@@ -516,6 +532,7 @@
// add it manually.
SmallVector<Metadata *, 1> BeforeLoopProperties;
if (BeforeJam.VectorizeEnable != LoopAttributes::Unspecified ||
+ BeforeJam.VectorizePredicateEnable != LoopAttributes::Unspecified ||
BeforeJam.InterleaveCount != 0 || BeforeJam.VectorizeWidth != 0)
BeforeLoopProperties.push_back(
MDNode::get(Ctx, MDString::get(Ctx, "llvm.loop.isvectorized")));
@@ -603,6 +620,9 @@
case LoopHintAttr::UnrollAndJam:
setUnrollAndJamState(LoopAttributes::Disable);
break;
+ case LoopHintAttr::VectorizePredicate:
+ setVectorizePredicateState(LoopAttributes::Disable);
+ break;
case LoopHintAttr::Distribute:
setDistributeState(false);
break;
@@ -630,6 +650,9 @@
case LoopHintAttr::UnrollAndJam:
setUnrollAndJamState(LoopAttributes::Enable);
break;
+ case LoopHintAttr::VectorizePredicate:
+ setVectorizePredicateState(LoopAttributes::Enable);
+ break;
case LoopHintAttr::Distribute:
setDistributeState(true);
break;
@@ -653,6 +676,7 @@
break;
case LoopHintAttr::Unroll:
case LoopHintAttr::UnrollAndJam:
+ case LoopHintAttr::VectorizePredicate:
case LoopHintAttr::UnrollCount:
case LoopHintAttr::UnrollAndJamCount:
case LoopHintAttr::VectorizeWidth:
@@ -681,6 +705,7 @@
case LoopHintAttr::Distribute:
case LoopHintAttr::PipelineDisabled:
case LoopHintAttr::PipelineInitiationInterval:
+ case LoopHintAttr::VectorizePredicate:
llvm_unreachable("Options cannot be used with 'full' hint.");
break;
}
@@ -704,6 +729,7 @@
break;
case LoopHintAttr::Unroll:
case LoopHintAttr::UnrollAndJam:
+ case LoopHintAttr::VectorizePredicate:
case LoopHintAttr::Vectorize:
case LoopHintAttr::Interleave:
case LoopHintAttr::Distribute:
diff --git a/clang/lib/CodeGen/CGLoopInfo.h b/clang/lib/CodeGen/CGLoopInfo.h
index 35d0e00..31322c7 100644
--- a/clang/lib/CodeGen/CGLoopInfo.h
+++ b/clang/lib/CodeGen/CGLoopInfo.h
@@ -51,6 +51,9 @@
/// Value for llvm.loop.unroll_and_jam.* metadata (enable, disable, or full).
LVEnableState UnrollAndJamEnable;
+ /// Value for llvm.loop.vectorize.predicate metadata
+ LVEnableState VectorizePredicateEnable;
+
/// Value for llvm.loop.vectorize.width metadata.
unsigned VectorizeWidth;
@@ -237,6 +240,11 @@
StagedAttrs.UnrollEnable = State;
}
+ /// Set the next pushed vectorize predicate state.
+ void setVectorizePredicateState(const LoopAttributes::LVEnableState &State) {
+ StagedAttrs.VectorizePredicateEnable = State;
+ }
+
/// Set the next pushed loop unroll_and_jam state.
void setUnrollAndJamState(const LoopAttributes::LVEnableState &State) {
StagedAttrs.UnrollAndJamEnable = State;