ffdbecccaf
This change adds a new op `alloc_tensor` to the bufferization dialect. During bufferization, this op is always lowered to a buffer allocation (unless it is "eliminated" by a pre-processing pass). It is useful to have such an op in tensor land, because it allows users to model tensor SSA use-def chains (which drive bufferization decisions) and because tensor SSA use-def chains can be analyzed by One-Shot Bufferize, while memref values cannot. This change also replaces all uses of linalg.init_tensor in bufferization-related code with bufferization.alloc_tensor. linalg.init_tensor and bufferization.alloc_tensor are similar, but the purpose of the former one is just to carry a shape. It does not indicate a memory allocation. linalg.init_tensor is not suitable for modelling SSA use-def chains for bufferization purposes, because linalg.init_tensor is marked as not having side effects (in contrast to alloc_tensor). As such, it is legal to move linalg.init_tensor ops around/CSE them/etc. This is not desirable for alloc_tensor; it represents an explicit buffer allocation while still in tensor land and such allocations should not suddenly disappear or get moved around when running the canonicalizer/CSE/etc. BEGIN_PUBLIC No public commit message needed for presubmit. END_PUBLIC Differential Revision: https://reviews.llvm.org/D126003
35 lines
1.7 KiB
MLIR
35 lines
1.7 KiB
MLIR
// RUN: mlir-opt %s -test-linalg-transform-patterns=test-linalg-to-vector-patterns \
|
|
// RUN: -linalg-init-tensor-to-alloc-tensor -linalg-bufferize -arith-bufferize \
|
|
// RUN: -bufferization-bufferize -tensor-bufferize -func-bufferize \
|
|
// RUN: -finalizing-bufferize -buffer-deallocation \
|
|
// RUN: -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
|
|
// RUN: mlir-cpu-runner -e main -entry-point-result=void \
|
|
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext,%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
|
|
// RUN: | FileCheck %s
|
|
|
|
|
|
func.func @main() {
|
|
%const = arith.constant dense<[[[1.0, 2.0, 3.0], [2.0, 3.0, 4.0]]]> : tensor<1x2x3xf32>
|
|
%dynamic = tensor.cast %const: tensor<1x2x3xf32> to tensor<1x?x3xf32>
|
|
%offset = arith.constant 2 : index
|
|
%cst = arith.constant 2.3 : f32
|
|
%c0 = arith.constant 0 : index
|
|
%out = tensor.pad %dynamic low[%c0, %offset, %c0] high[%c0, %c0, %offset] {
|
|
^bb0(%gen_arg1: index, %gen_arg2: index, %gen_arg3: index):
|
|
tensor.yield %cst : f32
|
|
} : tensor<1x?x3xf32> to tensor<1x?x?xf32>
|
|
%unranked = tensor.cast %out: tensor<1x?x?xf32> to tensor<*xf32>
|
|
call @printMemrefF32(%unranked) : (tensor<*xf32>) -> ()
|
|
|
|
// CHECK: Unranked Memref base@ = {{0x[-9a-f]*}}
|
|
// CHECK-SAME: rank = 3 offset = 0 sizes = [1, 4, 5] strides = [20, 5, 1] data =
|
|
// CHECK-NEXT{LITERAL}: [[[2.3, 2.3, 2.3, 2.3, 2.3],
|
|
// CHECK-NEXT: [2.3, 2.3, 2.3, 2.3, 2.3],
|
|
// CHECK-NEXT: [1, 2, 3, 2.3, 2.3],
|
|
// CHECK-NEXT: [2, 3, 4, 2.3, 2.3]]]
|
|
|
|
return
|
|
}
|
|
|
|
func.func private @printMemrefF32(%ptr : tensor<*xf32>)
|