aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib
diff options
context:
space:
mode:
authorLuke Lau <luke@igalia.com>2025-07-28 22:59:49 +0800
committerGitHub <noreply@github.com>2025-07-28 22:59:49 +0800
commitfe4f6c1a58ab4f00a88a97af01000b6783b573ee (patch)
treed791a6647c08648b7bb038dbf215592fbab58ea7 /llvm/lib
parent4b1d5b8d4f4d09e9988c0f5ca4a35957bf99235e (diff)
downloadllvm-fe4f6c1a58ab4f00a88a97af01000b6783b573ee.zip
llvm-fe4f6c1a58ab4f00a88a97af01000b6783b573ee.tar.gz
llvm-fe4f6c1a58ab4f00a88a97af01000b6783b573ee.tar.bz2
[RISCV] Cost bf16/f16 vector non-unit memory accesses as legal without zvfhmin/zvfbfmin (#150882)
When vectorizing with predication some loops that were previously vectorized without zvfhmin/zvfbfmin will no longer be vectorized because the masked load/store or gather/scatter cost returns illegal. This is due to a discrepancy where for these costs we check isLegalElementTypeForRVV but for regular memory accesses we don't. But for bf16 and f16 vectors we don't actually need the extension support for loads and stores, so this adds a new function which takes this into account. For regular memory accesses we should probably also e.g. return an invalid cost for i64 elements on zve32x, but it doesn't look like we have tests for this yet. We also should probably not be vectorizing these bf16/f16 loops to begin with if we don't have zvfhmin/zvfbfmin and zfhmin/zfbfmin. I think this is due to the scalar costs being too cheap. I've added tests for this in a100f6367205c6a909d68027af6a8675a8091bd9 to fix in another patch.
Diffstat (limited to 'llvm/lib')
-rw-r--r--llvm/lib/Target/RISCV/RISCVISelLowering.cpp23
-rw-r--r--llvm/lib/Target/RISCV/RISCVISelLowering.h1
-rw-r--r--llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp2
-rw-r--r--llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h4
4 files changed, 26 insertions, 4 deletions
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 54845e5..607edd3 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -2739,6 +2739,27 @@ bool RISCVTargetLowering::isLegalElementTypeForRVV(EVT ScalarTy) const {
}
}
+bool RISCVTargetLowering::isLegalLoadStoreElementTypeForRVV(
+ EVT ScalarTy) const {
+ if (!ScalarTy.isSimple())
+ return false;
+ switch (ScalarTy.getSimpleVT().SimpleTy) {
+ case MVT::iPTR:
+ return Subtarget.is64Bit() ? Subtarget.hasVInstructionsI64() : true;
+ case MVT::i8:
+ case MVT::i16:
+ case MVT::i32:
+ case MVT::f16:
+ case MVT::bf16:
+ case MVT::f32:
+ return true;
+ case MVT::i64:
+ case MVT::f64:
+ return Subtarget.hasVInstructionsI64();
+ default:
+ return false;
+ }
+}
unsigned RISCVTargetLowering::combineRepeatedFPDivisors() const {
return NumRepeatedDivisors;
@@ -24239,7 +24260,7 @@ bool RISCVTargetLowering::isLegalStridedLoadStore(EVT DataType,
return false;
EVT ScalarType = DataType.getScalarType();
- if (!isLegalElementTypeForRVV(ScalarType))
+ if (!isLegalLoadStoreElementTypeForRVV(ScalarType))
return false;
if (!Subtarget.enableUnalignedVectorMem() &&
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.h b/llvm/lib/Target/RISCV/RISCVISelLowering.h
index ca70c46..a788c0b7 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.h
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.h
@@ -384,6 +384,7 @@ public:
bool shouldRemoveExtendFromGSIndex(SDValue Extend, EVT DataVT) const override;
bool isLegalElementTypeForRVV(EVT ScalarTy) const;
+ bool isLegalLoadStoreElementTypeForRVV(EVT ScalarTy) const;
bool shouldConvertFpToSat(unsigned Op, EVT FPVT, EVT VT) const override;
diff --git a/llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp b/llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp
index 30d8f85..3cbe668 100644
--- a/llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp
+++ b/llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp
@@ -32,7 +32,7 @@ bool RISCVTargetLowering::isLegalInterleavedAccessType(
if (!isTypeLegal(VT))
return false;
- if (!isLegalElementTypeForRVV(VT.getScalarType()) ||
+ if (!isLegalLoadStoreElementTypeForRVV(VT.getScalarType()) ||
!allowsMemoryAccessForAlignment(VTy->getContext(), DL, VT, AddrSpace,
Alignment))
return false;
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
index d62d99c..f0510ec 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
@@ -265,7 +265,7 @@ public:
if (!ST->enableUnalignedVectorMem() && Alignment < ElemType.getStoreSize())
return false;
- return TLI->isLegalElementTypeForRVV(ElemType);
+ return TLI->isLegalLoadStoreElementTypeForRVV(ElemType);
}
bool isLegalMaskedLoad(Type *DataType, Align Alignment,
@@ -297,7 +297,7 @@ public:
if (!ST->enableUnalignedVectorMem() && Alignment < ElemType.getStoreSize())
return false;
- return TLI->isLegalElementTypeForRVV(ElemType);
+ return TLI->isLegalLoadStoreElementTypeForRVV(ElemType);
}
bool isLegalMaskedGather(Type *DataType, Align Alignment) const override {