e2310704d8
Create the memref dialect and move dialect-specific ops from std dialect to this dialect. Moved ops: AllocOp -> MemRef_AllocOp AllocaOp -> MemRef_AllocaOp AssumeAlignmentOp -> MemRef_AssumeAlignmentOp DeallocOp -> MemRef_DeallocOp DimOp -> MemRef_DimOp MemRefCastOp -> MemRef_CastOp MemRefReinterpretCastOp -> MemRef_ReinterpretCastOp GetGlobalMemRefOp -> MemRef_GetGlobalOp GlobalMemRefOp -> MemRef_GlobalOp LoadOp -> MemRef_LoadOp PrefetchOp -> MemRef_PrefetchOp ReshapeOp -> MemRef_ReshapeOp StoreOp -> MemRef_StoreOp SubViewOp -> MemRef_SubViewOp TransposeOp -> MemRef_TransposeOp TensorLoadOp -> MemRef_TensorLoadOp TensorStoreOp -> MemRef_TensorStoreOp TensorToMemRefOp -> MemRef_BufferCastOp ViewOp -> MemRef_ViewOp The roadmap to split the memref dialect from std is discussed here: https://llvm.discourse.group/t/rfc-split-the-memref-dialect-from-std/2667 Differential Revision: https://reviews.llvm.org/D98041
29 lines
1.3 KiB
MLIR
29 lines
1.3 KiB
MLIR
// RUN: mlir-opt -convert-affine-for-to-gpu="gpu-block-dims=1 gpu-thread-dims=1" %s | FileCheck %s
|
|
|
|
// CHECK-LABEL: @step_var
|
|
func @step_var(%A : memref<?x?xf32>, %B : memref<?x?xf32>) {
|
|
// Check that we divide by step.
|
|
// CHECK: %[[range_i:.*]] = divi_signed {{.*}}, %{{.*}}
|
|
// CHECK: %[[range_j:.*]] = divi_signed {{.*}}, %{{.*}}
|
|
|
|
// CHECK: gpu.launch
|
|
// CHECK-SAME: blocks(%{{[^)]*}}, %{{[^)]*}}, %{{[^)]*}}) in (%{{[^)]*}} = %[[range_i]], %{{[^)]*}} = %{{[^)]*}}, %{{[^)]*}} = %{{[^)]*}})
|
|
// CHECK-SAME: threads(%{{[^)]*}}, %{{[^)]*}}, %{{[^)]*}}) in (%{{[^)]*}} = %[[range_j]], %{{[^)]*}} = %{{[^)]*}}, %{{[^)]*}} = %{{[^)]*}})
|
|
affine.for %i = 5 to 15 step 4 {
|
|
affine.for %j = 3 to 19 step 7 {
|
|
// Loop induction variable remapping:
|
|
// iv = thread(block)_id * step + lower_bound
|
|
// CHECK: %[[prod_i:.*]] = muli %{{.*}}, %{{.*}} : index
|
|
// CHECK-NEXT: %[[i:.*]] = addi %{{.*}}, %[[prod_i]] : index
|
|
// CHECK-NEXT: %[[prod_j:.*]] = muli %{{.*}}, %{{.*}} : index
|
|
// CHECK-NEXT: %[[j:.*]] = addi %{{.*}}, %[[prod_j]] : index
|
|
|
|
// CHECK: {{.*}} = memref.load %{{.*}}[%[[i]], %[[j]]] : memref<?x?xf32>
|
|
%0 = memref.load %A[%i, %j] : memref<?x?xf32>
|
|
// CHECK: memref.store {{.*}}, %{{.*}}[%[[i]], %[[j]]] : memref<?x?xf32>
|
|
memref.store %0, %B[%i, %j] : memref<?x?xf32>
|
|
}
|
|
}
|
|
return
|
|
}
|