[llvm] 3289ecf - [𝘀𝗽𝗿] changes introduced through rebase
Mehdi Amini via llvm-commits
llvm-commits at lists.llvm.org
Fri Nov 3 03:24:06 PDT 2023
Author: Mehdi Amini
Date: 2023-11-03T03:23:43-07:00
New Revision: 3289ecff8e8f5022cb6a40777392c98f1bcf5780
URL: https://github.com/llvm/llvm-project/commit/3289ecff8e8f5022cb6a40777392c98f1bcf5780
DIFF: https://github.com/llvm/llvm-project/commit/3289ecff8e8f5022cb6a40777392c98f1bcf5780.diff
LOG: [𝘀𝗽𝗿] changes introduced through rebase
Created using spr 1.3.4
[skip ci]
Added:
Modified:
clang/test/OpenMP/cancel_codegen.cpp
clang/test/OpenMP/parallel_codegen.cpp
llvm/lib/IR/ConstantFold.cpp
mlir/include/mlir/Conversion/Passes.td
mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVMPass.cpp
mlir/test/Conversion/VectorToLLVM/vector-mask-to-llvm.mlir
mlir/test/Conversion/VectorToLLVM/vector-reduction-to-llvm.mlir
mlir/test/Conversion/VectorToLLVM/vector-scalable-memcpy.mlir
mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir
Removed:
mlir/test/Conversion/VectorToLLVM/typed-pointers.mlir
################################################################################
diff --git a/clang/test/OpenMP/cancel_codegen.cpp b/clang/test/OpenMP/cancel_codegen.cpp
index 53580e0c2b0293f..03024cf331b2717 100644
--- a/clang/test/OpenMP/cancel_codegen.cpp
+++ b/clang/test/OpenMP/cancel_codegen.cpp
@@ -1026,25 +1026,25 @@ for (int i = 0; i < argc; ++i) {
// CHECK3-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META8:![0-9]+]])
// CHECK3-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META10:![0-9]+]])
// CHECK3-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META12:![0-9]+]])
-// CHECK3-NEXT: store i32 [[TMP2]], ptr [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !14
-// CHECK3-NEXT: store ptr [[TMP5]], ptr [[DOTPART_ID__ADDR_I]], align 8, !noalias !14
-// CHECK3-NEXT: store ptr null, ptr [[DOTPRIVATES__ADDR_I]], align 8, !noalias !14
-// CHECK3-NEXT: store ptr null, ptr [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !14
-// CHECK3-NEXT: store ptr [[TMP3]], ptr [[DOTTASK_T__ADDR_I]], align 8, !noalias !14
-// CHECK3-NEXT: store ptr [[TMP7]], ptr [[__CONTEXT_ADDR_I]], align 8, !noalias !14
-// CHECK3-NEXT: [[TMP8:%.*]] = load ptr, ptr [[__CONTEXT_ADDR_I]], align 8, !noalias !14
+// CHECK3-NEXT: store i32 [[TMP2]], ptr [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias ![[NOALIAS0:[0-9]+]]
+// CHECK3-NEXT: store ptr [[TMP5]], ptr [[DOTPART_ID__ADDR_I]], align 8, !noalias ![[NOALIAS0]]
+// CHECK3-NEXT: store ptr null, ptr [[DOTPRIVATES__ADDR_I]], align 8, !noalias ![[NOALIAS0]]
+// CHECK3-NEXT: store ptr null, ptr [[DOTCOPY_FN__ADDR_I]], align 8, !noalias ![[NOALIAS0]]
+// CHECK3-NEXT: store ptr [[TMP3]], ptr [[DOTTASK_T__ADDR_I]], align 8, !noalias ![[NOALIAS0]]
+// CHECK3-NEXT: store ptr [[TMP7]], ptr [[__CONTEXT_ADDR_I]], align 8, !noalias ![[NOALIAS0]]
+// CHECK3-NEXT: [[TMP8:%.*]] = load ptr, ptr [[__CONTEXT_ADDR_I]], align 8, !noalias ![[NOALIAS0]]
// CHECK3-NEXT: [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB12:[0-9]+]])
// CHECK3-NEXT: [[TMP9:%.*]] = call i32 @__kmpc_cancel(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i32 4)
// CHECK3-NEXT: [[TMP10:%.*]] = icmp ne i32 [[TMP9]], 0
// CHECK3-NEXT: br i1 [[TMP10]], label [[DOTCANCEL_EXIT_I:%.*]], label [[DOTCANCEL_CONTINUE_I:%.*]]
// CHECK3: .cancel.exit.i:
-// CHECK3-NEXT: store i32 1, ptr [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !14
+// CHECK3-NEXT: store i32 1, ptr [[CLEANUP_DEST_SLOT_I]], align 4, !noalias ![[NOALIAS1:[0-9]+]]
// CHECK3-NEXT: br label [[DOTOMP_OUTLINED__EXIT:%.*]]
// CHECK3: .cancel.continue.i:
-// CHECK3-NEXT: store i32 0, ptr [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !14
+// CHECK3-NEXT: store i32 0, ptr [[CLEANUP_DEST_SLOT_I]], align 4, !noalias ![[NOALIAS1]]
// CHECK3-NEXT: br label [[DOTOMP_OUTLINED__EXIT]]
// CHECK3: .omp_outlined..exit:
-// CHECK3-NEXT: [[CLEANUP_DEST_I:%.*]] = load i32, ptr [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !14
+// CHECK3-NEXT: [[CLEANUP_DEST_I:%.*]] = load i32, ptr [[CLEANUP_DEST_SLOT_I]], align 4, !noalias ![[NOALIAS1]]
// CHECK3-NEXT: ret i32 0
//
//
diff --git a/clang/test/OpenMP/parallel_codegen.cpp b/clang/test/OpenMP/parallel_codegen.cpp
index 5c98761be0808ef..d545b4a9d9fa887 100644
--- a/clang/test/OpenMP/parallel_codegen.cpp
+++ b/clang/test/OpenMP/parallel_codegen.cpp
@@ -812,7 +812,7 @@ int main (int argc, char **argv) {
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_..omp_par
-// CHECK3-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]], ptr [[TMP0:%.*]]) #[[ATTR1]] {
+// CHECK3-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]], ptr [[TMP0:%.*]]) #[[ATTR2:[0-9]+]]
// CHECK3-NEXT: omp.par.entry:
// CHECK3-NEXT: [[GEP__RELOADED:%.*]] = getelementptr { ptr, ptr }, ptr [[TMP0]], i32 0, i32 0
// CHECK3-NEXT: [[LOADGEP__RELOADED:%.*]] = load ptr, ptr [[GEP__RELOADED]], align 8
@@ -956,7 +956,7 @@ int main (int argc, char **argv) {
//
//
// CHECK4-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_..omp_par
-// CHECK4-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]], ptr [[TMP0:%.*]]) #[[ATTR1]] !dbg [[DBG57:![0-9]+]] {
+// CHECK4-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]], ptr [[TMP0:%.*]]) #[[ATTR2:[0-9]+]] !dbg [[DBG57:![0-9]+]] {
// CHECK4-NEXT: omp.par.entry:
// CHECK4-NEXT: [[GEP__RELOADED:%.*]] = getelementptr { ptr, ptr }, ptr [[TMP0]], i32 0, i32 0
// CHECK4-NEXT: [[LOADGEP__RELOADED:%.*]] = load ptr, ptr [[GEP__RELOADED]], align 8
diff --git a/llvm/lib/IR/ConstantFold.cpp b/llvm/lib/IR/ConstantFold.cpp
index 81691a5f69aa0a6..4651767d0655a06 100644
--- a/llvm/lib/IR/ConstantFold.cpp
+++ b/llvm/lib/IR/ConstantFold.cpp
@@ -37,45 +37,6 @@ using namespace llvm::PatternMatch;
// ConstantFold*Instruction Implementations
//===----------------------------------------------------------------------===//
-/// Convert the specified vector Constant node to the specified vector type.
-/// At this point, we know that the elements of the input vector constant are
-/// all simple integer or FP values.
-static Constant *BitCastConstantVector(Constant *CV, VectorType *DstTy) {
-
- if (CV->isAllOnesValue()) return Constant::getAllOnesValue(DstTy);
- if (CV->isNullValue()) return Constant::getNullValue(DstTy);
-
- // Do not iterate on scalable vector. The num of elements is unknown at
- // compile-time.
- if (isa<ScalableVectorType>(DstTy))
- return nullptr;
-
- // If this cast changes element count then we can't handle it here:
- // doing so requires endianness information. This should be handled by
- // Analysis/ConstantFolding.cpp
- unsigned NumElts = cast<FixedVectorType>(DstTy)->getNumElements();
- if (NumElts != cast<FixedVectorType>(CV->getType())->getNumElements())
- return nullptr;
-
- Type *DstEltTy = DstTy->getElementType();
- // Fast path for splatted constants.
- if (Constant *Splat = CV->getSplatValue()) {
- return ConstantVector::getSplat(DstTy->getElementCount(),
- ConstantExpr::getBitCast(Splat, DstEltTy));
- }
-
- SmallVector<Constant*, 16> Result;
- Type *Ty = IntegerType::get(CV->getContext(), 32);
- for (unsigned i = 0; i != NumElts; ++i) {
- Constant *C =
- ConstantExpr::getExtractElement(CV, ConstantInt::get(Ty, i));
- C = ConstantExpr::getBitCast(C, DstEltTy);
- Result.push_back(C);
- }
-
- return ConstantVector::get(Result);
-}
-
/// This function determines which opcode to use to fold two constant cast
/// expressions together. It uses CastInst::isEliminableCastPair to determine
/// the opcode. Consequently its just a wrapper around that function.
@@ -114,38 +75,16 @@ static Constant *FoldBitCast(Constant *V, Type *DestTy) {
// Handle casts from one vector constant to another. We know that the src
// and dest type have the same size (otherwise its an illegal cast).
if (VectorType *DestPTy = dyn_cast<VectorType>(DestTy)) {
- if (VectorType *SrcTy = dyn_cast<VectorType>(V->getType())) {
- assert(DestPTy->getPrimitiveSizeInBits() ==
- SrcTy->getPrimitiveSizeInBits() &&
- "Not cast between same sized vectors!");
- SrcTy = nullptr;
- // First, check for null. Undef is already handled.
- if (isa<ConstantAggregateZero>(V))
- return Constant::getNullValue(DestTy);
-
- // Handle ConstantVector and ConstantAggregateVector.
- return BitCastConstantVector(V, DestPTy);
- }
-
// Canonicalize scalar-to-vector bitcasts into vector-to-vector bitcasts
// This allows for other simplifications (although some of them
// can only be handled by Analysis/ConstantFolding.cpp).
if (isa<ConstantInt>(V) || isa<ConstantFP>(V))
return ConstantExpr::getBitCast(ConstantVector::get(V), DestPTy);
+ return nullptr;
}
- // Finally, implement bitcast folding now. The code below doesn't handle
- // bitcast right.
- if (isa<ConstantPointerNull>(V)) // ptr->ptr cast.
- return ConstantPointerNull::get(cast<PointerType>(DestTy));
-
// Handle integral constant input.
if (ConstantInt *CI = dyn_cast<ConstantInt>(V)) {
- if (DestTy->isIntegerTy())
- // Integral -> Integral. This is a no-op because the bit widths must
- // be the same. Consequently, we just fold to V.
- return V;
-
// See note below regarding the PPC_FP128 restriction.
if (DestTy->isFloatingPointTy() && !DestTy->isPPC_FP128Ty())
return ConstantFP::get(DestTy->getContext(),
diff --git a/mlir/include/mlir/Conversion/Passes.td b/mlir/include/mlir/Conversion/Passes.td
index 00e342f8f30eb3e..c2f90b8984b97fb 100644
--- a/mlir/include/mlir/Conversion/Passes.td
+++ b/mlir/include/mlir/Conversion/Passes.td
@@ -1270,10 +1270,7 @@ def ConvertVectorToLLVMPass : Pass<"convert-vector-to-llvm"> {
Option<"x86Vector", "enable-x86vector",
"bool", /*default=*/"false",
"Enables the use of X86Vector dialect while lowering the vector "
- "dialect.">,
- Option<"useOpaquePointers", "use-opaque-pointers", "bool",
- /*default=*/"true", "Generate LLVM IR using opaque pointers "
- "instead of typed pointers">
+ "dialect.">
];
}
diff --git a/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp b/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
index 4af58653c8227ae..75a35b4c801e4a5 100644
--- a/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
+++ b/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
@@ -112,19 +112,6 @@ static Value getIndexedPtrs(ConversionPatternRewriter &rewriter, Location loc,
base, index);
}
-// Casts a strided element pointer to a vector pointer. The vector pointer
-// will be in the same address space as the incoming memref type.
-static Value castDataPtr(ConversionPatternRewriter &rewriter, Location loc,
- Value ptr, MemRefType memRefType, Type vt,
- const LLVMTypeConverter &converter) {
- if (converter.useOpaquePointers())
- return ptr;
-
- unsigned addressSpace = *converter.getMemRefAddressSpace(memRefType);
- auto pType = LLVM::LLVMPointerType::get(vt, addressSpace);
- return rewriter.create<LLVM::BitcastOp>(loc, pType, ptr);
-}
-
/// Convert `foldResult` into a Value. Integer attribute is converted to
/// an LLVM constant op.
static Value getAsLLVMValue(OpBuilder &builder, Location loc,
@@ -261,10 +248,8 @@ class VectorLoadStoreConversion : public ConvertOpToLLVMPattern<LoadOrStoreOp> {
this->typeConverter->convertType(loadOrStoreOp.getVectorType()));
Value dataPtr = this->getStridedElementPtr(loc, memRefTy, adaptor.getBase(),
adaptor.getIndices(), rewriter);
- Value ptr = castDataPtr(rewriter, loc, dataPtr, memRefTy, vtype,
- *this->getTypeConverter());
-
- replaceLoadOrStoreOp(loadOrStoreOp, adaptor, vtype, ptr, align, rewriter);
+ replaceLoadOrStoreOp(loadOrStoreOp, adaptor, vtype, dataPtr, align,
+ rewriter);
return success();
}
};
@@ -1440,19 +1425,12 @@ class VectorTypeCastOpConversion
// Create descriptor.
auto desc = MemRefDescriptor::undef(rewriter, loc, llvmTargetDescriptorTy);
- Type llvmTargetElementTy = desc.getElementPtrType();
// Set allocated ptr.
Value allocated = sourceMemRef.allocatedPtr(rewriter, loc);
- if (!getTypeConverter()->useOpaquePointers())
- allocated =
- rewriter.create<LLVM::BitcastOp>(loc, llvmTargetElementTy, allocated);
desc.setAllocatedPtr(rewriter, loc, allocated);
// Set aligned ptr.
Value ptr = sourceMemRef.alignedPtr(rewriter, loc);
- if (!getTypeConverter()->useOpaquePointers())
- ptr = rewriter.create<LLVM::BitcastOp>(loc, llvmTargetElementTy, ptr);
-
desc.setAlignedPtr(rewriter, loc, ptr);
// Fill offset 0.
auto attr = rewriter.getIntegerAttr(rewriter.getIndexType(), 0);
diff --git a/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVMPass.cpp b/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVMPass.cpp
index b865a2671fff762..4c6d0672d4108ef 100644
--- a/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVMPass.cpp
+++ b/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVMPass.cpp
@@ -82,7 +82,6 @@ void LowerVectorToLLVMPass::runOnOperation() {
// Convert to the LLVM IR dialect.
LowerToLLVMOptions options(&getContext());
- options.useOpaquePointers = useOpaquePointers;
LLVMTypeConverter converter(&getContext(), options);
RewritePatternSet patterns(&getContext());
populateVectorMaskMaterializationPatterns(patterns, force32BitVectorIndices);
diff --git a/mlir/test/Conversion/VectorToLLVM/typed-pointers.mlir b/mlir/test/Conversion/VectorToLLVM/typed-pointers.mlir
deleted file mode 100644
index 5dbd9a589f39277..000000000000000
--- a/mlir/test/Conversion/VectorToLLVM/typed-pointers.mlir
+++ /dev/null
@@ -1,172 +0,0 @@
-// RUN: mlir-opt %s -convert-vector-to-llvm='use-opaque-pointers=0' -split-input-file | FileCheck %s
-
-func.func @vector_type_cast(%arg0: memref<8x8x8xf32>) -> memref<vector<8x8x8xf32>> {
- %0 = vector.type_cast %arg0: memref<8x8x8xf32> to memref<vector<8x8x8xf32>>
- return %0 : memref<vector<8x8x8xf32>>
-}
-// CHECK-LABEL: @vector_type_cast
-// CHECK: llvm.mlir.undef : !llvm.struct<(ptr<array<8 x array<8 x vector<8xf32>>>>, ptr<array<8 x array<8 x vector<8xf32>>>>, i64)>
-// CHECK: %[[allocated:.*]] = llvm.extractvalue {{.*}}[0] : !llvm.struct<(ptr<f32>, ptr<f32>, i64, array<3 x i64>, array<3 x i64>)>
-// CHECK: %[[allocatedBit:.*]] = llvm.bitcast %[[allocated]] : !llvm.ptr<f32> to !llvm.ptr<array<8 x array<8 x vector<8xf32>>>>
-// CHECK: llvm.insertvalue %[[allocatedBit]], {{.*}}[0] : !llvm.struct<(ptr<array<8 x array<8 x vector<8xf32>>>>, ptr<array<8 x array<8 x vector<8xf32>>>>, i64)>
-// CHECK: %[[aligned:.*]] = llvm.extractvalue {{.*}}[1] : !llvm.struct<(ptr<f32>, ptr<f32>, i64, array<3 x i64>, array<3 x i64>)>
-// CHECK: %[[alignedBit:.*]] = llvm.bitcast %[[aligned]] : !llvm.ptr<f32> to !llvm.ptr<array<8 x array<8 x vector<8xf32>>>>
-// CHECK: llvm.insertvalue %[[alignedBit]], {{.*}}[1] : !llvm.struct<(ptr<array<8 x array<8 x vector<8xf32>>>>, ptr<array<8 x array<8 x vector<8xf32>>>>, i64)>
-// CHECK: llvm.mlir.constant(0 : index
-// CHECK: llvm.insertvalue {{.*}}[2] : !llvm.struct<(ptr<array<8 x array<8 x vector<8xf32>>>>, ptr<array<8 x array<8 x vector<8xf32>>>>, i64)>
-
-// -----
-
-func.func @vector_type_cast_non_zero_addrspace(%arg0: memref<8x8x8xf32, 3>) -> memref<vector<8x8x8xf32>, 3> {
- %0 = vector.type_cast %arg0: memref<8x8x8xf32, 3> to memref<vector<8x8x8xf32>, 3>
- return %0 : memref<vector<8x8x8xf32>, 3>
-}
-// CHECK-LABEL: @vector_type_cast_non_zero_addrspace
-// CHECK: llvm.mlir.undef : !llvm.struct<(ptr<array<8 x array<8 x vector<8xf32>>>, 3>, ptr<array<8 x array<8 x vector<8xf32>>>, 3>, i64)>
-// CHECK: %[[allocated:.*]] = llvm.extractvalue {{.*}}[0] : !llvm.struct<(ptr<f32, 3>, ptr<f32, 3>, i64, array<3 x i64>, array<3 x i64>)>
-// CHECK: %[[allocatedBit:.*]] = llvm.bitcast %[[allocated]] : !llvm.ptr<f32, 3> to !llvm.ptr<array<8 x array<8 x vector<8xf32>>>, 3>
-// CHECK: llvm.insertvalue %[[allocatedBit]], {{.*}}[0] : !llvm.struct<(ptr<array<8 x array<8 x vector<8xf32>>>, 3>, ptr<array<8 x array<8 x vector<8xf32>>>, 3>, i64)>
-// CHECK: %[[aligned:.*]] = llvm.extractvalue {{.*}}[1] : !llvm.struct<(ptr<f32, 3>, ptr<f32, 3>, i64, array<3 x i64>, array<3 x i64>)>
-// CHECK: %[[alignedBit:.*]] = llvm.bitcast %[[aligned]] : !llvm.ptr<f32, 3> to !llvm.ptr<array<8 x array<8 x vector<8xf32>>>, 3>
-// CHECK: llvm.insertvalue %[[alignedBit]], {{.*}}[1] : !llvm.struct<(ptr<array<8 x array<8 x vector<8xf32>>>, 3>, ptr<array<8 x array<8 x vector<8xf32>>>, 3>, i64)>
-// CHECK: llvm.mlir.constant(0 : index
-// CHECK: llvm.insertvalue {{.*}}[2] : !llvm.struct<(ptr<array<8 x array<8 x vector<8xf32>>>, 3>, ptr<array<8 x array<8 x vector<8xf32>>>, 3>, i64)>
-
-// -----
-
-func.func @transfer_read_1d(%A : memref<?xf32>, %base: index) -> vector<17xf32> {
- %f7 = arith.constant 7.0: f32
- %f = vector.transfer_read %A[%base], %f7
- {permutation_map = affine_map<(d0) -> (d0)>} :
- memref<?xf32>, vector<17xf32>
- vector.transfer_write %f, %A[%base]
- {permutation_map = affine_map<(d0) -> (d0)>} :
- vector<17xf32>, memref<?xf32>
- return %f: vector<17xf32>
-}
-// CHECK-LABEL: func @transfer_read_1d
-// CHECK-SAME: %[[MEM:.*]]: memref<?xf32>,
-// CHECK-SAME: %[[BASE:.*]]: index) -> vector<17xf32>
-// CHECK: %[[C7:.*]] = arith.constant 7.0
-//
-// 1. Let dim be the memref dimension, compute the in-bound index (dim - offset)
-// CHECK: %[[C0:.*]] = arith.constant 0 : index
-// CHECK: %[[DIM:.*]] = memref.dim %[[MEM]], %[[C0]] : memref<?xf32>
-// CHECK: %[[BOUND:.*]] = arith.subi %[[DIM]], %[[BASE]] : index
-//
-// 2. Create a vector with linear indices [ 0 .. vector_length - 1 ].
-// CHECK: %[[linearIndex:.*]] = arith.constant dense
-// CHECK-SAME: <[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16]> :
-// CHECK-SAME: vector<17xi32>
-//
-// 3. Create bound vector to compute in-bound mask:
-// [ 0 .. vector_length - 1 ] < [ dim - offset .. dim - offset ]
-// CHECK: %[[btrunc:.*]] = arith.index_cast %[[BOUND]] : index to i32
-// CHECK: %[[boundVecInsert:.*]] = llvm.insertelement %[[btrunc]]
-// CHECK: %[[boundVect:.*]] = llvm.shufflevector %[[boundVecInsert]]
-// CHECK: %[[mask:.*]] = arith.cmpi slt, %[[linearIndex]], %[[boundVect]]
-// CHECK-SAME: : vector<17xi32>
-//
-// 4. Create pass-through vector.
-// CHECK: %[[PASS_THROUGH:.*]] = arith.constant dense<7.{{.*}}> : vector<17xf32>
-//
-// 5. Bitcast to vector form.
-// CHECK: %[[gep:.*]] = llvm.getelementptr %{{.*}} :
-// CHECK-SAME: (!llvm.ptr<f32>, i64) -> !llvm.ptr<f32>
-// CHECK: %[[vecPtr:.*]] = llvm.bitcast %[[gep]] :
-// CHECK-SAME: !llvm.ptr<f32> to !llvm.ptr<vector<17xf32>>
-//
-// 6. Rewrite as a masked read.
-// CHECK: %[[loaded:.*]] = llvm.intr.masked.load %[[vecPtr]], %[[mask]],
-// CHECK-SAME: %[[PASS_THROUGH]] {alignment = 4 : i32} :
-//
-// 1. Let dim be the memref dimension, compute the in-bound index (dim - offset)
-// CHECK: %[[C0_b:.*]] = arith.constant 0 : index
-// CHECK: %[[DIM_b:.*]] = memref.dim %[[MEM]], %[[C0_b]] : memref<?xf32>
-// CHECK: %[[BOUND_b:.*]] = arith.subi %[[DIM_b]], %[[BASE]] : index
-//
-// 2. Create a vector with linear indices [ 0 .. vector_length - 1 ].
-// CHECK: %[[linearIndex_b:.*]] = arith.constant dense
-// CHECK-SAME: <[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16]> :
-// CHECK-SAME: vector<17xi32>
-//
-// 3. Create bound vector to compute in-bound mask:
-// [ 0 .. vector_length - 1 ] < [ dim - offset .. dim - offset ]
-// CHECK: %[[btrunc_b:.*]] = arith.index_cast %[[BOUND_b]] : index to i32
-// CHECK: %[[boundVecInsert_b:.*]] = llvm.insertelement %[[btrunc_b]]
-// CHECK: %[[boundVect_b:.*]] = llvm.shufflevector %[[boundVecInsert_b]]
-// CHECK: %[[mask_b:.*]] = arith.cmpi slt, %[[linearIndex_b]],
-// CHECK-SAME: %[[boundVect_b]] : vector<17xi32>
-//
-// 4. Bitcast to vector form.
-// CHECK: %[[gep_b:.*]] = llvm.getelementptr {{.*}} :
-// CHECK-SAME: (!llvm.ptr<f32>, i64) -> !llvm.ptr<f32>
-// CHECK: %[[vecPtr_b:.*]] = llvm.bitcast %[[gep_b]] :
-// CHECK-SAME: !llvm.ptr<f32> to !llvm.ptr<vector<17xf32>>
-//
-// 5. Rewrite as a masked write.
-// CHECK: llvm.intr.masked.store %[[loaded]], %[[vecPtr_b]], %[[mask_b]]
-// CHECK-SAME: {alignment = 4 : i32} :
-// CHECK-SAME: vector<17xf32>, vector<17xi1> into !llvm.ptr<vector<17xf32>>
-
-// -----
-
-func.func @vector_load_op(%memref : memref<200x100xf32>, %i : index, %j : index) -> vector<8xf32> {
- %0 = vector.load %memref[%i, %j] : memref<200x100xf32>, vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @vector_load_op
-// CHECK: %[[c100:.*]] = llvm.mlir.constant(100 : index) : i64
-// CHECK: %[[mul:.*]] = llvm.mul %{{.*}}, %[[c100]] : i64
-// CHECK: %[[add:.*]] = llvm.add %[[mul]], %{{.*}} : i64
-// CHECK: %[[gep:.*]] = llvm.getelementptr %{{.*}}[%[[add]]] : (!llvm.ptr<f32>, i64) -> !llvm.ptr<f32>
-// CHECK: %[[bcast:.*]] = llvm.bitcast %[[gep]] : !llvm.ptr<f32> to !llvm.ptr<vector<8xf32>>
-// CHECK: llvm.load %[[bcast]] {alignment = 4 : i64} : !llvm.ptr<vector<8xf32>>
-
-// -----
-
-func.func @vector_store_op(%memref : memref<200x100xf32>, %i : index, %j : index) {
- %val = arith.constant dense<11.0> : vector<4xf32>
- vector.store %val, %memref[%i, %j] : memref<200x100xf32>, vector<4xf32>
- return
-}
-
-// CHECK-LABEL: func @vector_store_op
-// CHECK: %[[c100:.*]] = llvm.mlir.constant(100 : index) : i64
-// CHECK: %[[mul:.*]] = llvm.mul %{{.*}}, %[[c100]] : i64
-// CHECK: %[[add:.*]] = llvm.add %[[mul]], %{{.*}} : i64
-// CHECK: %[[gep:.*]] = llvm.getelementptr %{{.*}}[%[[add]]] : (!llvm.ptr<f32>, i64) -> !llvm.ptr<f32>
-// CHECK: %[[bcast:.*]] = llvm.bitcast %[[gep]] : !llvm.ptr<f32> to !llvm.ptr<vector<4xf32>>
-// CHECK: llvm.store %{{.*}}, %[[bcast]] {alignment = 4 : i64} : !llvm.ptr<vector<4xf32>>
-
-// -----
-
-func.func @masked_load_op(%arg0: memref<?xf32>, %arg1: vector<16xi1>, %arg2: vector<16xf32>) -> vector<16xf32> {
- %c0 = arith.constant 0: index
- %0 = vector.maskedload %arg0[%c0], %arg1, %arg2 : memref<?xf32>, vector<16xi1>, vector<16xf32> into vector<16xf32>
- return %0 : vector<16xf32>
-}
-
-// CHECK-LABEL: func @masked_load_op
-// CHECK: %[[CO:.*]] = arith.constant 0 : index
-// CHECK: %[[C:.*]] = builtin.unrealized_conversion_cast %[[CO]] : index to i64
-// CHECK: %[[P:.*]] = llvm.getelementptr %{{.*}}[%[[C]]] : (!llvm.ptr<f32>, i64) -> !llvm.ptr<f32>
-// CHECK: %[[B:.*]] = llvm.bitcast %[[P]] : !llvm.ptr<f32> to !llvm.ptr<vector<16xf32>>
-// CHECK: %[[L:.*]] = llvm.intr.masked.load %[[B]], %{{.*}}, %{{.*}} {alignment = 4 : i32} : (!llvm.ptr<vector<16xf32>>, vector<16xi1>, vector<16xf32>) -> vector<16xf32>
-// CHECK: return %[[L]] : vector<16xf32>
-
-// -----
-
-func.func @masked_store_op(%arg0: memref<?xf32>, %arg1: vector<16xi1>, %arg2: vector<16xf32>) {
- %c0 = arith.constant 0: index
- vector.maskedstore %arg0[%c0], %arg1, %arg2 : memref<?xf32>, vector<16xi1>, vector<16xf32>
- return
-}
-
-// CHECK-LABEL: func @masked_store_op
-// CHECK: %[[CO:.*]] = arith.constant 0 : index
-// CHECK: %[[C:.*]] = builtin.unrealized_conversion_cast %[[CO]] : index to i64
-// CHECK: %[[P:.*]] = llvm.getelementptr %{{.*}}[%[[C]]] : (!llvm.ptr<f32>, i64) -> !llvm.ptr<f32>
-// CHECK: %[[B:.*]] = llvm.bitcast %[[P]] : !llvm.ptr<f32> to !llvm.ptr<vector<16xf32>>
-// CHECK: llvm.intr.masked.store %{{.*}}, %[[B]], %{{.*}} {alignment = 4 : i32} : vector<16xf32>, vector<16xi1> into !llvm.ptr<vector<16xf32>>
diff --git a/mlir/test/Conversion/VectorToLLVM/vector-mask-to-llvm.mlir b/mlir/test/Conversion/VectorToLLVM/vector-mask-to-llvm.mlir
index 11354213d9ab497..1abadcc345cd2d8 100644
--- a/mlir/test/Conversion/VectorToLLVM/vector-mask-to-llvm.mlir
+++ b/mlir/test/Conversion/VectorToLLVM/vector-mask-to-llvm.mlir
@@ -1,5 +1,5 @@
-// RUN: mlir-opt %s --convert-vector-to-llvm='force-32bit-vector-indices=1 use-opaque-pointers=1' | FileCheck %s --check-prefix=CMP32
-// RUN: mlir-opt %s --convert-vector-to-llvm='force-32bit-vector-indices=0 use-opaque-pointers=1' | FileCheck %s --check-prefix=CMP64
+// RUN: mlir-opt %s --convert-vector-to-llvm='force-32bit-vector-indices=1' | FileCheck %s --check-prefix=CMP32
+// RUN: mlir-opt %s --convert-vector-to-llvm='force-32bit-vector-indices=0' | FileCheck %s --check-prefix=CMP64
// CMP32-LABEL: @genbool_var_1d(
// CMP32-SAME: %[[ARG:.*]]: index)
diff --git a/mlir/test/Conversion/VectorToLLVM/vector-reduction-to-llvm.mlir b/mlir/test/Conversion/VectorToLLVM/vector-reduction-to-llvm.mlir
index 13b7faed4790d7f..22463f57f24cfd2 100644
--- a/mlir/test/Conversion/VectorToLLVM/vector-reduction-to-llvm.mlir
+++ b/mlir/test/Conversion/VectorToLLVM/vector-reduction-to-llvm.mlir
@@ -1,5 +1,5 @@
-// RUN: mlir-opt %s -convert-vector-to-llvm='use-opaque-pointers=1' -split-input-file | FileCheck %s
-// RUN: mlir-opt %s -convert-vector-to-llvm='reassociate-fp-reductions use-opaque-pointers=1' -split-input-file | FileCheck %s --check-prefix=REASSOC
+// RUN: mlir-opt %s -convert-vector-to-llvm -split-input-file | FileCheck %s
+// RUN: mlir-opt %s -convert-vector-to-llvm='reassociate-fp-reductions' -split-input-file | FileCheck %s --check-prefix=REASSOC
// CHECK-LABEL: @reduce_add_f32(
// CHECK-SAME: %[[A:.*]]: vector<16xf32>)
diff --git a/mlir/test/Conversion/VectorToLLVM/vector-scalable-memcpy.mlir b/mlir/test/Conversion/VectorToLLVM/vector-scalable-memcpy.mlir
index 4a5a2032816626f..811b10721bf2849 100644
--- a/mlir/test/Conversion/VectorToLLVM/vector-scalable-memcpy.mlir
+++ b/mlir/test/Conversion/VectorToLLVM/vector-scalable-memcpy.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -convert-vector-to-llvm='use-opaque-pointers=1' | mlir-opt | FileCheck %s
+// RUN: mlir-opt %s -convert-vector-to-llvm | mlir-opt | FileCheck %s
// CHECK: vector_scalable_memcopy([[SRC:%arg[0-9]+]]: memref<?xf32>, [[DST:%arg[0-9]+]]
func.func @vector_scalable_memcopy(%src : memref<?xf32>, %dst : memref<?xf32>, %size : index) {
diff --git a/mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir b/mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir
index 05733214bc3ae80..012d30d96799f20 100644
--- a/mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir
+++ b/mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir
@@ -1,5 +1,4 @@
-// RUN: mlir-opt %s -convert-vector-to-llvm='use-opaque-pointers=1' -split-input-file | FileCheck %s
-
+// RUN: mlir-opt %s -convert-vector-to-llvm -split-input-file | FileCheck %s
func.func @bitcast_f32_to_i32_vector_0d(%input: vector<f32>) -> vector<i32> {
%0 = vector.bitcast %input : vector<f32> to vector<i32>
More information about the llvm-commits
mailing list