[llvm] 76f243b - [RISCV] Add cost modelling for masked memory op
Alex Tsao via llvm-commits
llvm-commits at lists.llvm.org
Wed Mar 2 06:48:47 PST 2022
Author: Alex Tsao
Date: 2022-03-02T22:48:41+08:00
New Revision: 76f243b53b1c4bed5defe8ffac1fd739a39b0097
URL: https://github.com/llvm/llvm-project/commit/76f243b53b1c4bed5defe8ffac1fd739a39b0097
DIFF: https://github.com/llvm/llvm-project/commit/76f243b53b1c4bed5defe8ffac1fd739a39b0097.diff
LOG: [RISCV] Add cost modelling for masked memory op
The patch adds very basic cost model for masked memory op on scalable vector.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D117884
Added:
llvm/test/Analysis/CostModel/RISCV/masked_ldst.ll
Modified:
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index a317501f4db11..e164264851a3e 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -180,6 +180,17 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
return BaseT::getShuffleCost(Kind, Tp, Mask, Index, SubTp);
}
+InstructionCost
+RISCVTTIImpl::getMaskedMemoryOpCost(unsigned Opcode, Type *Src, Align Alignment,
+ unsigned AddressSpace,
+ TTI::TargetCostKind CostKind) {
+ if (!isa<ScalableVectorType>(Src))
+ return BaseT::getMaskedMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
+ CostKind);
+
+ return getMemoryOpCost(Opcode, Src, Alignment, AddressSpace, CostKind);
+}
+
InstructionCost RISCVTTIImpl::getGatherScatterOpCost(
unsigned Opcode, Type *DataTy, const Value *Ptr, bool VariableMask,
Align Alignment, TTI::TargetCostKind CostKind, const Instruction *I) {
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
index 086c59c3f9add..f973b0537baf7 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
@@ -62,6 +62,10 @@ class RISCVTTIImpl : public BasicTTIImplBase<RISCVTTIImpl> {
InstructionCost getRegUsageForType(Type *Ty);
+ InstructionCost getMaskedMemoryOpCost(unsigned Opcode, Type *Src,
+ Align Alignment, unsigned AddressSpace,
+ TTI::TargetCostKind CostKind);
+
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP,
OptimizationRemarkEmitter *ORE);
diff --git a/llvm/test/Analysis/CostModel/RISCV/masked_ldst.ll b/llvm/test/Analysis/CostModel/RISCV/masked_ldst.ll
new file mode 100644
index 0000000000000..78926de7781e8
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/RISCV/masked_ldst.ll
@@ -0,0 +1,143 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -cost-model -analyze -mtriple=riscv64 -mattr=+experimental-v | FileCheck %s
+
+define void @fixed() {
+; CHECK-LABEL: 'fixed'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2i8 = call <2 x i8> @llvm.masked.load.v2i8.p0v2i8(<2 x i8>* undef, i32 8, <2 x i1> undef, <2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %v4i8 = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* undef, i32 8, <4 x i1> undef, <4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %v8i8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 8, <8 x i1> undef, <8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %v16i8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 8, <16 x i1> undef, <16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2i16 = call <2 x i16> @llvm.masked.load.v2i16.p0v2i16(<2 x i16>* undef, i32 8, <2 x i1> undef, <2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %v4i16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 8, <4 x i1> undef, <4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %v8i16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 8, <8 x i1> undef, <8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2i32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 8, <2 x i1> undef, <2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %v4i32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 8, <4 x i1> undef, <4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2i64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 8, <2 x i1> undef, <2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2f16 = call <2 x half> @llvm.masked.load.v2f16.p0v2f16(<2 x half>* undef, i32 8, <2 x i1> undef, <2 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %v4f16 = call <4 x half> @llvm.masked.load.v4f16.p0v4f16(<4 x half>* undef, i32 8, <4 x i1> undef, <4 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %v8f16 = call <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>* undef, i32 8, <8 x i1> undef, <8 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2f32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 8, <2 x i1> undef, <2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %v4f32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 8, <4 x i1> undef, <4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2f64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 8, <2 x i1> undef, <2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %v4i64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 8, <4 x i1> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %v32f16 = call <32 x half> @llvm.masked.load.v32f16.p0v32f16(<32 x half>* undef, i32 8, <32 x i1> undef, <32 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+entry:
+ ; fixed-width integer types
+ %v2i8 = call <2 x i8> @llvm.masked.load.v2i8.p0v2i8(<2 x i8> *undef, i32 8, <2 x i1> undef, <2 x i8> undef)
+ %v4i8 = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8> *undef, i32 8, <4 x i1> undef, <4 x i8> undef)
+ %v8i8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8> *undef, i32 8, <8 x i1> undef, <8 x i8> undef)
+ %v16i8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8> *undef, i32 8, <16 x i1> undef, <16 x i8> undef)
+ %v2i16 = call <2 x i16> @llvm.masked.load.v2i16.p0v2i16(<2 x i16> *undef, i32 8, <2 x i1> undef, <2 x i16> undef)
+ %v4i16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16> *undef, i32 8, <4 x i1> undef, <4 x i16> undef)
+ %v8i16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16> *undef, i32 8, <8 x i1> undef, <8 x i16> undef)
+ %v2i32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32> *undef, i32 8, <2 x i1> undef, <2 x i32> undef)
+ %v4i32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32> *undef, i32 8, <4 x i1> undef, <4 x i32> undef)
+ %v2i64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64> *undef, i32 8, <2 x i1> undef, <2 x i64> undef)
+
+ ; fixed-width floating point types
+ %v2f16 = call <2 x half> @llvm.masked.load.v2f16.p0v2f16(<2 x half> *undef, i32 8, <2 x i1> undef, <2 x half> undef)
+ %v4f16 = call <4 x half> @llvm.masked.load.v4f16.p0v4f16(<4 x half> *undef, i32 8, <4 x i1> undef, <4 x half> undef)
+ %v8f16 = call <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half> *undef, i32 8, <8 x i1> undef, <8 x half> undef)
+ %v2f32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float> *undef, i32 8, <2 x i1> undef, <2 x float> undef)
+ %v4f32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float> *undef, i32 8, <4 x i1> undef, <4 x float> undef)
+ %v2f64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double> *undef, i32 8, <2 x i1> undef, <2 x double> undef)
+
+ %v4i64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64> *undef, i32 8, <4 x i1> undef, <4 x i64> undef)
+ %v32f16 = call <32 x half> @llvm.masked.load.v32f16.p0v32f16(<32 x half> *undef, i32 8, <32 x i1> undef, <32 x half> undef)
+
+ ret void
+}
+
+
+define void @scalable() {
+; CHECK-LABEL: 'scalable'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0nxv2i8(<vscale x 2 x i8>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0nxv4i8(<vscale x 4 x i8>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0nxv16i8(<vscale x 16 x i8>* undef, i32 8, <vscale x 16 x i1> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0nxv2i16(<vscale x 2 x i16>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0nxv4i16(<vscale x 4 x i16>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0nxv2i32(<vscale x 2 x i32>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nxv2f16 = call <vscale x 2 x half> @llvm.masked.load.nxv2f16.p0nxv2f16(<vscale x 2 x half>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x half> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nxv4f16 = call <vscale x 4 x half> @llvm.masked.load.nxv4f16.p0nxv4f16(<vscale x 4 x half>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x half> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nxv8f16 = call <vscale x 8 x half> @llvm.masked.load.nxv8f16.p0nxv8f16(<vscale x 8 x half>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = call <vscale x 2 x float> @llvm.masked.load.nxv2f32.p0nxv2f32(<vscale x 2 x float>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0nxv2f64(<vscale x 2 x double>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = call <vscale x 1 x i64> @llvm.masked.load.nxv1i64.p0nxv1i64(<vscale x 1 x i64>* undef, i32 8, <vscale x 1 x i1> undef, <vscale x 1 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = call <vscale x 4 x i64> @llvm.masked.load.nxv4i64.p0nxv4i64(<vscale x 4 x i64>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nxv32f16 = call <vscale x 32 x half> @llvm.masked.load.nxv32f16.p0nxv32f16(<vscale x 32 x half>* undef, i32 8, <vscale x 32 x i1> undef, <vscale x 32 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+entry:
+ ; scalable integer types
+ %nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0nxv2i8(<vscale x 2 x i8> *undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
+ %nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0nxv4i8(<vscale x 4 x i8> *undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
+ %nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8> *undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
+ %nxv16i8 = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0nxv16i8(<vscale x 16 x i8> *undef, i32 8, <vscale x 16 x i1> undef, <vscale x 16 x i8> undef)
+ %nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0nxv2i16(<vscale x 2 x i16> *undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
+ %nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0nxv4i16(<vscale x 4 x i16> *undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+ %nxv8i16 = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16> *undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
+ %nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0nxv2i32(<vscale x 2 x i32> *undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
+ %nxv4i32 = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32> *undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i32> undef)
+ %nxv2i64 = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64> *undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i64> undef)
+
+ ; scalable floating point types
+ %nxv2f16 = call <vscale x 2 x half> @llvm.masked.load.nxv2f16.p0nxv2f16(<vscale x 2 x half> *undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x half> undef)
+ %nxv4f16 = call <vscale x 4 x half> @llvm.masked.load.nxv4f16.p0nxv4f16(<vscale x 4 x half> *undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x half> undef)
+ %nxv8f16 = call <vscale x 8 x half> @llvm.masked.load.nxv8f16.p0nxv8f16(<vscale x 8 x half> *undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x half> undef)
+ %nxv2f32 = call <vscale x 2 x float> @llvm.masked.load.nxv2f32.p0nxv2f32(<vscale x 2 x float> *undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
+ %nxv4f32 = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float> *undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
+ %nxv2f64 = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0nxv2f64(<vscale x 2 x double> *undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
+
+ %nxv1i64 = call <vscale x 1 x i64> @llvm.masked.load.nxv1i64.p0nxv1i64(<vscale x 1 x i64> *undef, i32 8, <vscale x 1 x i1> undef, <vscale x 1 x i64> undef)
+ %nxv4i64 = call <vscale x 4 x i64> @llvm.masked.load.nxv4i64.p0nxv4i64(<vscale x 4 x i64> *undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i64> undef)
+ %nxv32f16 = call <vscale x 32 x half> @llvm.masked.load.nxv32f16.p0nxv32f16(<vscale x 32 x half> *undef, i32 8, <vscale x 32 x i1> undef, <vscale x 32 x half> undef)
+
+ ret void
+}
+
+declare <2 x i8> @llvm.masked.load.v2i8.p0v2i8(<2 x i8>*, i32, <2 x i1>, <2 x i8>)
+declare <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>*, i32, <4 x i1>, <4 x i8>)
+declare <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>*, i32, <8 x i1>, <8 x i8>)
+declare <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>*, i32, <16 x i1>, <16 x i8>)
+declare <2 x i16> @llvm.masked.load.v2i16.p0v2i16(<2 x i16>*, i32, <2 x i1>, <2 x i16>)
+declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32, <4 x i1>, <4 x i16>)
+declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32, <8 x i1>, <8 x i16>)
+declare <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
+declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
+declare <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>*, i32, <2 x i1>, <2 x i64>)
+declare <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>*, i32, <4 x i1>, <4 x i64>)
+declare <2 x half> @llvm.masked.load.v2f16.p0v2f16(<2 x half>*, i32, <2 x i1>, <2 x half>)
+declare <4 x half> @llvm.masked.load.v4f16.p0v4f16(<4 x half>*, i32, <4 x i1>, <4 x half>)
+declare <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>*, i32, <8 x i1>, <8 x half>)
+declare <32 x half> @llvm.masked.load.v32f16.p0v32f16(<32 x half>*, i32, <32 x i1>, <32 x half>)
+declare <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
+declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
+declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
+
+
+declare <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0nxv2i8(<vscale x 2 x i8>*, i32, <vscale x 2 x i1>, <vscale x 2 x i8>)
+declare <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0nxv4i8(<vscale x 4 x i8>*, i32, <vscale x 4 x i1>, <vscale x 4 x i8>)
+declare <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>*, i32, <vscale x 8 x i1>, <vscale x 8 x i8>)
+declare <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0nxv16i8(<vscale x 16 x i8>*, i32, <vscale x 16 x i1>, <vscale x 16 x i8>)
+declare <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0nxv2i16(<vscale x 2 x i16>*, i32, <vscale x 2 x i1>, <vscale x 2 x i16>)
+declare <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0nxv4i16(<vscale x 4 x i16>*, i32, <vscale x 4 x i1>, <vscale x 4 x i16>)
+declare <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>*, i32, <vscale x 8 x i1>, <vscale x 8 x i16>)
+declare <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0nxv2i32(<vscale x 2 x i32>*, i32, <vscale x 2 x i1>, <vscale x 2 x i32>)
+declare <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>*, i32, <vscale x 4 x i1>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64>*, i32, <vscale x 2 x i1>, <vscale x 2 x i64>)
+declare <vscale x 4 x i64> @llvm.masked.load.nxv4i64.p0nxv4i64(<vscale x 4 x i64>*, i32, <vscale x 4 x i1>, <vscale x 4 x i64>)
+declare <vscale x 1 x i64> @llvm.masked.load.nxv1i64.p0nxv1i64(<vscale x 1 x i64>*, i32, <vscale x 1 x i1>, <vscale x 1 x i64>)
+declare <vscale x 2 x half> @llvm.masked.load.nxv2f16.p0nxv2f16(<vscale x 2 x half>*, i32, <vscale x 2 x i1>, <vscale x 2 x half>)
+declare <vscale x 4 x half> @llvm.masked.load.nxv4f16.p0nxv4f16(<vscale x 4 x half>*, i32, <vscale x 4 x i1>, <vscale x 4 x half>)
+declare <vscale x 8 x half> @llvm.masked.load.nxv8f16.p0nxv8f16(<vscale x 8 x half>*, i32, <vscale x 8 x i1>, <vscale x 8 x half>)
+declare <vscale x 32 x half> @llvm.masked.load.nxv32f16.p0nxv32f16(<vscale x 32 x half>*, i32, <vscale x 32 x i1>, <vscale x 32 x half>)
+declare <vscale x 2 x float> @llvm.masked.load.nxv2f32.p0nxv2f32(<vscale x 2 x float>*, i32, <vscale x 2 x i1>, <vscale x 2 x float>)
+declare <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>*, i32, <vscale x 4 x i1>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0nxv2f64(<vscale x 2 x double>*, i32, <vscale x 2 x i1>, <vscale x 2 x double>)
More information about the llvm-commits
mailing list