bd30a796fc
Continue the convergence between LLVM dialect and built-in types by using the built-in vector type whenever possible, that is for fixed vectors of built-in integers and built-in floats. LLVM dialect vector type is still in use for pointers, less frequent floating point types that do not have a built-in equivalent, and scalable vectors. However, the top-level `LLVMVectorType` class has been removed in favor of free functions capable of inspecting both built-in and LLVM dialect vector types: `LLVM::getVectorElementType`, `LLVM::getNumVectorElements` and `LLVM::getFixedVectorType`. Additional work is necessary to design an implemented the extensions to built-in types so as to remove the `LLVMFixedVectorType` entirely. Note that the default output format for the built-in vectors does not have whitespace around the `x` separator, e.g., `vector<4xf32>` as opposed to the LLVM dialect vector type format that does, e.g., `!llvm.vec<4 x fp128>`. This required changing the FileCheck patterns in several tests. Reviewed By: mehdi_amini, silvas Differential Revision: https://reviews.llvm.org/D94405
69 lines
2.2 KiB
MLIR
69 lines
2.2 KiB
MLIR
// RUN: mlir-opt %s -convert-vector-to-rocdl | FileCheck %s
|
|
|
|
gpu.module @test_read{
|
|
func @transfer_readx2(%A : memref<?xf32>, %base: index) -> vector<2xf32> {
|
|
%f0 = constant 0.0: f32
|
|
%f = vector.transfer_read %A[%base], %f0
|
|
{permutation_map = affine_map<(d0) -> (d0)>} :
|
|
memref<?xf32>, vector<2xf32>
|
|
return %f: vector<2xf32>
|
|
}
|
|
// CHECK-LABEL: @transfer_readx2
|
|
// CHECK: rocdl.buffer.load {{.*}} vector<2xf32>
|
|
|
|
func @transfer_readx4(%A : memref<?xf32>, %base: index) -> vector<4xf32> {
|
|
%f0 = constant 0.0: f32
|
|
%f = vector.transfer_read %A[%base], %f0
|
|
{permutation_map = affine_map<(d0) -> (d0)>} :
|
|
memref<?xf32>, vector<4xf32>
|
|
return %f: vector<4xf32>
|
|
}
|
|
// CHECK-LABEL: @transfer_readx4
|
|
// CHECK: rocdl.buffer.load {{.*}} vector<4xf32>
|
|
|
|
func @transfer_read_dwordConfig(%A : memref<?xf32>, %base: index) -> vector<4xf32> {
|
|
%f0 = constant 0.0: f32
|
|
%f = vector.transfer_read %A[%base], %f0
|
|
{permutation_map = affine_map<(d0) -> (d0)>} :
|
|
memref<?xf32>, vector<4xf32>
|
|
return %f: vector<4xf32>
|
|
}
|
|
// CHECK-LABEL: @transfer_read_dwordConfig
|
|
// CHECK: %[[gep:.*]] = llvm.getelementptr {{.*}}
|
|
// CHECK: [0, 0, -1, 159744]
|
|
// CHECK: %[[i64:.*]] = llvm.ptrtoint %[[gep]]
|
|
// CHECK: llvm.insertelement %[[i64]]
|
|
}
|
|
|
|
gpu.module @test_write{
|
|
func @transfer_writex2(%A : memref<?xf32>, %B : vector<2xf32>, %base: index) {
|
|
vector.transfer_write %B, %A[%base]
|
|
{permutation_map = affine_map<(d0) -> (d0)>} :
|
|
vector<2xf32>, memref<?xf32>
|
|
return
|
|
}
|
|
// CHECK-LABEL: @transfer_writex2
|
|
// CHECK: rocdl.buffer.store {{.*}} vector<2xf32>
|
|
|
|
func @transfer_writex4(%A : memref<?xf32>, %B : vector<4xf32>, %base: index) {
|
|
vector.transfer_write %B, %A[%base]
|
|
{permutation_map = affine_map<(d0) -> (d0)>} :
|
|
vector<4xf32>, memref<?xf32>
|
|
return
|
|
}
|
|
// CHECK-LABEL: @transfer_writex4
|
|
// CHECK: rocdl.buffer.store {{.*}} vector<4xf32>
|
|
|
|
func @transfer_write_dwordConfig(%A : memref<?xf32>, %B : vector<2xf32>, %base: index) {
|
|
vector.transfer_write %B, %A[%base]
|
|
{permutation_map = affine_map<(d0) -> (d0)>} :
|
|
vector<2xf32>, memref<?xf32>
|
|
return
|
|
}
|
|
// CHECK-LABEL: @transfer_write_dwordConfig
|
|
// CHECK: %[[gep:.*]] = llvm.getelementptr {{.*}}
|
|
// CHECK: [0, 0, -1, 159744]
|
|
// CHECK: %[[i64:.*]] = llvm.ptrtoint %[[gep]]
|
|
// CHECK: llvm.insertelement %[[i64]]
|
|
}
|