forked from OSchip/llvm-project
[mlir][bufferize][NFC] Clean up test cases
Run `one-shot-bufferize` instead of `linalg-comprehensive-module-bufferize` and move some test cases to their respective dialects. Differential Revision: https://reviews.llvm.org/D124323
This commit is contained in:
Matthias Springer
parent
5996306c24
commit
940a3f6b3d
|
|
@ -0,0 +1,61 @@
|
|||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs bufferize-function-boundaries" -split-input-file | FileCheck %s
|
||||
|
||||
// Run fuzzer with different seeds.
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=23 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=59 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=91 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
|
||||
// Test bufferization using memref types that have no layout map.
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs fully-dynamic-layout-maps=0 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
|
||||
// CHECK-LABEL: func @write_to_select_op_source
|
||||
// CHECK-SAME: %[[t1:.*]]: memref<?xf32, #{{.*}}>, %[[t2:.*]]: memref<?xf32, #{{.*}}>
|
||||
func.func @write_to_select_op_source(
|
||||
%t1 : tensor<?xf32> {bufferization.writable = true},
|
||||
%t2 : tensor<?xf32> {bufferization.writable = true},
|
||||
%c : i1)
|
||||
-> (tensor<?xf32>, tensor<?xf32>)
|
||||
{
|
||||
%cst = arith.constant 0.0 : f32
|
||||
%idx = arith.constant 0 : index
|
||||
// CHECK: %[[alloc:.*]] = memref.alloc
|
||||
// CHECK: memref.copy %[[t1]], %[[alloc]]
|
||||
// CHECK: memref.store %{{.*}}, %[[alloc]]
|
||||
%w = tensor.insert %cst into %t1[%idx] : tensor<?xf32>
|
||||
// CHECK: %[[select:.*]] = arith.select %{{.*}}, %[[t1]], %[[t2]]
|
||||
%s = arith.select %c, %t1, %t2 : tensor<?xf32>
|
||||
// CHECK: return %[[select]], %[[alloc]]
|
||||
return %s, %w : tensor<?xf32>, tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// Due to the out-of-place bufferization of %t1, buffers with different layout
|
||||
// maps are passed to arith.select. A cast must be inserted.
|
||||
|
||||
// CHECK-LABEL: func @write_after_select_read_one
|
||||
// CHECK-SAME: %[[t1:.*]]: memref<?xf32, #{{.*}}>, %[[t2:.*]]: memref<?xf32, #{{.*}}>
|
||||
func.func @write_after_select_read_one(
|
||||
%t1 : tensor<?xf32> {bufferization.writable = true},
|
||||
%t2 : tensor<?xf32> {bufferization.writable = true},
|
||||
%c : i1)
|
||||
-> (f32, tensor<?xf32>)
|
||||
{
|
||||
%cst = arith.constant 0.0 : f32
|
||||
%idx = arith.constant 0 : index
|
||||
|
||||
// CHECK: %[[alloc:.*]] = memref.alloc
|
||||
// CHECK-DAG: %[[casted:.*]] = memref.cast %[[alloc]]
|
||||
// CHECK-DAG: memref.copy %[[t1]], %[[alloc]]
|
||||
// CHECK: %[[select:.*]] = arith.select %{{.*}}, %[[casted]], %[[t2]]
|
||||
%s = arith.select %c, %t1, %t2 : tensor<?xf32>
|
||||
|
||||
// CHECK: memref.store %{{.*}}, %[[select]]
|
||||
%w = tensor.insert %cst into %s[%idx] : tensor<?xf32>
|
||||
|
||||
// CHECK: %[[f:.*]] = memref.load %[[t1]]
|
||||
%f = tensor.extract %t1[%idx] : tensor<?xf32>
|
||||
|
||||
// CHECK: return %[[f]], %[[select]]
|
||||
return %f, %w : f32, tensor<?xf32>
|
||||
}
|
||||
|
|
@ -1,4 +1,4 @@
|
|||
// RUN: mlir-opt %s -linalg-comprehensive-module-bufferize=test-analysis-only -split-input-file | FileCheck %s
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="test-analysis-only bufferize-function-boundaries" -split-input-file | FileCheck %s
|
||||
|
||||
/// All combinations of matmul(fill(extract(init_tensor)), fill(extract(%init_tensor)), %arg2)
|
||||
/// These should all be inplaceable except the first op.
|
||||
|
|
@ -1,12 +1,14 @@
|
|||
// RUN: mlir-opt %s -linalg-comprehensive-module-bufferize=allow-return-allocs -split-input-file | FileCheck %s
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs bufferize-function-boundaries" -split-input-file | FileCheck %s
|
||||
|
||||
// Run fuzzer with different seeds.
|
||||
// RUN: mlir-opt %s -linalg-comprehensive-module-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=23" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -linalg-comprehensive-module-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=59" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -linalg-comprehensive-module-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=91" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=23 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=59 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=91 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
|
||||
// Test bufferization using memref types that have no layout map.
|
||||
// RUN: mlir-opt %s -linalg-comprehensive-module-bufferize="allow-return-allocs fully-dynamic-layout-maps=0" -split-input-file | FileCheck %s --check-prefix=CHECK-NO-LAYOUT-MAP
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs fully-dynamic-layout-maps=0 bufferize-function-boundaries" -split-input-file | FileCheck %s --check-prefix=CHECK-NO-LAYOUT-MAP
|
||||
|
||||
// TODO: Some test cases from this file should be moved to other dialects.
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
|
|
@ -32,19 +34,6 @@ func.func @fill_inplace(
|
|||
|
||||
// -----
|
||||
|
||||
// CHECK-LABEL: func @tensor_extract(%{{.*}}: memref<?xf32, #{{.*}}>) -> f32 {
|
||||
func.func @tensor_extract(%A : tensor<?xf32> {bufferization.writable = false}) -> (f32) {
|
||||
%c0 = arith.constant 0 : index
|
||||
|
||||
// CHECK: %[[RES:.*]] = memref.load {{.*}} : memref<?xf32, #{{.*}}>
|
||||
%0 = tensor.extract %A[%c0] : tensor<?xf32>
|
||||
|
||||
// CHECK: return %[[RES]] : f32
|
||||
return %0 : f32
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
/// No bufferization.writable flag, must allocate.
|
||||
|
|
@ -160,138 +149,6 @@ func.func @vec_not_inplace(
|
|||
|
||||
// -----
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
// CHECK-LABEL: func @insert_slice_fun
|
||||
// CHECK-SAME: %[[A0:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>,
|
||||
// CHECK-SAME: %[[A1:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>,
|
||||
// CHECK-SAME: %[[t0:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>,
|
||||
// CHECK-SAME: %[[t1:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>
|
||||
func.func @insert_slice_fun(
|
||||
%A0 : tensor<?xf32> {bufferization.writable = false},
|
||||
%A1 : tensor<?xf32> {bufferization.writable = true},
|
||||
%t0 : tensor<4xf32> {bufferization.writable = false},
|
||||
%t1 : tensor<4xf32> {bufferization.writable = true})
|
||||
-> (tensor<?xf32>, tensor<?xf32>, tensor<?xf32>, tensor<?xf32>)
|
||||
{
|
||||
// Hoisted allocs.
|
||||
// CHECK: %[[REALLOC1:.*]] = memref.alloc
|
||||
// CHECK: %[[REALLOC2:.*]] = memref.alloc
|
||||
// CHECK: %[[REALLOC3:.*]] = memref.alloc
|
||||
|
||||
// Alloc and copy the whole result tensor. Copy the tensor.extract_slice.
|
||||
// CHECK: memref.copy %[[A0]], %[[REALLOC3]]
|
||||
// CHECK: %[[SV_A0:.*]] = memref.subview %[[REALLOC3]]
|
||||
// CHECK: memref.copy %[[t0]], %[[SV_A0]]
|
||||
%r0 = tensor.insert_slice %t0 into %A0[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// Alloc and copy the whole result tensor. Copy the tensor.extract_slice.
|
||||
// CHECK: memref.copy %[[A0]]
|
||||
// CHECK: %[[SV_A0_2:.*]] = memref.subview %[[REALLOC2]]
|
||||
// CHECK: memref.copy %[[t1]], %[[SV_A0_2]]
|
||||
%r1 = tensor.insert_slice %t1 into %A0[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// Still alloc the large tensor because %A1 is read after. Copy the tensor.extract_slice.
|
||||
// CHECK: memref.copy %[[A1]]
|
||||
// CHECK: %[[SV_A1:.*]] = memref.subview %[[REALLOC1]]
|
||||
// CHECK: memref.copy %[[t0]], %[[SV_A1]]
|
||||
%r2 = tensor.insert_slice %t0 into %A1[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// Do not realloc the large tensor. Copy the tensor.extract_slice.
|
||||
// CHECK-NOT: alloc
|
||||
// CHECK: %[[SV_A1_2:.*]] = memref.subview %[[A1]]
|
||||
// CHECK: memref.copy %[[t1]], %[[SV_A1_2]]
|
||||
%r3 = tensor.insert_slice %t1 into %A1[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// CHECK: return %[[REALLOC3]], %[[REALLOC2]], %[[REALLOC1]] :
|
||||
// CHECK-SAME: memref<?xf32>, memref<?xf32>, memref<?xf32>
|
||||
return %r0, %r1, %r2, %r3: tensor<?xf32>, tensor<?xf32>, tensor<?xf32>, tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
// CHECK-LABEL: func @insert_slice_fun
|
||||
// CHECK-SAME: %[[A:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>
|
||||
// CHECK-SAME: %[[t:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>
|
||||
func.func @insert_slice_fun(
|
||||
%A : tensor<?xf32> {bufferization.writable = true},
|
||||
%t : tensor<4xf32> {bufferization.writable = false})
|
||||
-> tensor<?xf32>
|
||||
{
|
||||
%f0 = arith.constant 0.0 : f32
|
||||
|
||||
// CHECK-NOT: alloc
|
||||
// CHECK: %[[SV_A:.*]] = memref.subview %[[A]]
|
||||
// CHECK: memref.copy %[[t]], %[[SV_A]]
|
||||
%r0 = tensor.insert_slice %t into %A[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
/// Overwrite A inplace.
|
||||
// CHECK: linalg.fill ins({{.*}}{{.*}}outs(%[[A]]
|
||||
%r1 = linalg.fill ins(%f0 : f32) outs(%r0 : tensor<?xf32>) -> tensor<?xf32>
|
||||
|
||||
// CHECK: return
|
||||
// CHECK-NOT: tensor
|
||||
return %r1: tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
// CHECK-LABEL: func @insert_slice_fun
|
||||
// CHECK-SAME: %[[A:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>
|
||||
// CHECK-SAME: %[[t:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>
|
||||
func.func @insert_slice_fun(
|
||||
%A : tensor<?xf32> {bufferization.writable = true},
|
||||
%t : tensor<4xf32> {bufferization.writable = false})
|
||||
-> tensor<?xf32>
|
||||
{
|
||||
%f0 = arith.constant 0.0 : f32
|
||||
|
||||
// CHECK: linalg.fill ins({{.*}}{{.*}}outs(%[[A]]
|
||||
%r0 = linalg.fill ins(%f0 : f32) outs(%A : tensor<?xf32>) -> tensor<?xf32>
|
||||
|
||||
// CHECK-NOT: alloc
|
||||
// CHECK: %[[SV_A:.*]] = memref.subview %[[A]]
|
||||
/// Overwrite A inplace by copying into the subview.
|
||||
// CHECK: memref.copy %[[t]], %[[SV_A]]
|
||||
%r1 = tensor.insert_slice %t into %r0[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// CHECK: return
|
||||
// CHECK-NOT: tensor
|
||||
return %r1: tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
// CHECK-LABEL: func @insert_slice_fun_not_inplace
|
||||
// CHECK-SAME: %[[A:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>
|
||||
// CHECK-SAME: %[[t:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>
|
||||
func.func @insert_slice_fun_not_inplace(
|
||||
%A : tensor<?xf32> {bufferization.writable = false},
|
||||
%t : tensor<4xf32> {bufferization.writable = false})
|
||||
-> tensor<?xf32>
|
||||
{
|
||||
// CHECK: %[[ALLOC:.*]] = memref.alloc(%{{.*}}) {alignment = 128 : i64} : memref<?xf32>
|
||||
// CHECK: memref.copy %[[A]], %[[ALLOC]] : memref<?xf32{{.*}} to memref<?xf32>
|
||||
// CHECK: %[[SV:.*]] = memref.subview %[[ALLOC]][0] [4] [1] : memref<?xf32> to memref<4xf32>
|
||||
// CHECK: memref.copy %[[t]], %[[SV]] : memref<4xf32, #map> to memref<4xf32>
|
||||
%r0 = tensor.insert_slice %t into %A[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// CHECK: return %{{.*}} : memref<?xf32>
|
||||
return %r0: tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
//===----------------------------------------------------------------------===//
|
||||
// Cross function boundary cases.
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
||||
// CHECK: func @matmul(
|
||||
// CHECK-SAME: %[[A:[0-9a-zA-Z]*]]: memref<128x256xf32>
|
||||
// CHECK-SAME: %[[B:[0-9a-zA-Z]*]]: memref<256x192xf32>
|
||||
|
|
@ -364,29 +221,7 @@ func.func @matmul(
|
|||
|
||||
// -----
|
||||
|
||||
// CHECK-LABEL: func @tensor_cast_not_in_place(
|
||||
// CHECK-SAME: %[[A:.*]]: memref<?xf32{{.*}}>, %[[B:.*]]: memref<?xf32{{.*}}>
|
||||
// CHECK: %[[alloc:.*]] = memref.alloc
|
||||
// CHECK: memref.copy %[[A]], %[[alloc]]
|
||||
// CHECK: %[[subview:.*]] = memref.subview %[[A]][{{.*}}] [4] [1] : {{.*}} to memref<4xf32
|
||||
// CHECK: memref.copy %[[alloc]], %[[subview]]
|
||||
func.func @tensor_cast_not_in_place(
|
||||
%A : tensor<?xf32> {bufferization.writable = true},
|
||||
%B : tensor<?xf32> {bufferization.writable = false}, %idx: index)
|
||||
-> (tensor<?xf32>)
|
||||
{
|
||||
%r0 = tensor.cast %A : tensor<?xf32> to tensor<4xf32>
|
||||
%r1 = tensor.insert_slice %r0 into %A[%idx][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
return %r1 : tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
//===----------------------------------------------------------------------===//
|
||||
// Insertion point cases.
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
||||
/// These tests just check the produced IR is valid and does not have dominance
|
||||
/// This test just checks the produced IR is valid and does not have dominance
|
||||
/// errors in the def-use chains.
|
||||
|
||||
// CHECK-LABEL: func @dominance_violation_bug_1
|
||||
|
|
@ -406,19 +241,6 @@ func.func @dominance_violation_bug_1(
|
|||
return %rA : tensor<?x?xf32>
|
||||
}
|
||||
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-LABEL: func @insert_op
|
||||
// CHECK-SAME: %[[t1:.*]]: memref<?xf32, {{.*}}>, %[[s:.*]]: f32, %[[i:.*]]: index
|
||||
func.func @insert_op(%t1 : tensor<?xf32> {bufferization.writable = true},
|
||||
%s : f32, %i : index) -> tensor<?xf32> {
|
||||
// CHECK: memref.store %[[s]], %[[t1]][%[[i]]]
|
||||
%0 = tensor.insert %s into %t1[%i] : tensor<?xf32>
|
||||
// CHECK: return
|
||||
return %0 : tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
func.func @gather_like(
|
||||
|
|
@ -537,85 +359,3 @@ func.func @depthwise_conv_1d_nwc_wc(%arg0: index, %arg1: index, %arg2: tensor<8x
|
|||
return %3 : tensor<?x1x6x8xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-LABEL: func @write_to_select_op_source
|
||||
// CHECK-SAME: %[[t1:.*]]: memref<?xf32, #{{.*}}>, %[[t2:.*]]: memref<?xf32, #{{.*}}>
|
||||
func.func @write_to_select_op_source(
|
||||
%t1 : tensor<?xf32> {bufferization.writable = true},
|
||||
%t2 : tensor<?xf32> {bufferization.writable = true},
|
||||
%c : i1)
|
||||
-> (tensor<?xf32>, tensor<?xf32>)
|
||||
{
|
||||
%cst = arith.constant 0.0 : f32
|
||||
%idx = arith.constant 0 : index
|
||||
// CHECK: %[[alloc:.*]] = memref.alloc
|
||||
// CHECK: memref.copy %[[t1]], %[[alloc]]
|
||||
// CHECK: memref.store %{{.*}}, %[[alloc]]
|
||||
%w = tensor.insert %cst into %t1[%idx] : tensor<?xf32>
|
||||
// CHECK: %[[select:.*]] = arith.select %{{.*}}, %[[t1]], %[[t2]]
|
||||
%s = arith.select %c, %t1, %t2 : tensor<?xf32>
|
||||
// CHECK: return %[[select]], %[[alloc]]
|
||||
return %s, %w : tensor<?xf32>, tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-LABEL: func @write_after_select_read_one
|
||||
// CHECK-SAME: %[[t1:.*]]: memref<?xf32, #{{.*}}>, %[[t2:.*]]: memref<?xf32, #{{.*}}>
|
||||
func.func @write_after_select_read_one(
|
||||
%t1 : tensor<?xf32> {bufferization.writable = true},
|
||||
%t2 : tensor<?xf32> {bufferization.writable = true},
|
||||
%c : i1)
|
||||
-> (f32, tensor<?xf32>)
|
||||
{
|
||||
%cst = arith.constant 0.0 : f32
|
||||
%idx = arith.constant 0 : index
|
||||
|
||||
// CHECK: %[[alloc:.*]] = memref.alloc
|
||||
// CHECK-DAG: %[[casted:.*]] = memref.cast %[[alloc]]
|
||||
// CHECK-DAG: memref.copy %[[t1]], %[[alloc]]
|
||||
// CHECK: %[[select:.*]] = arith.select %{{.*}}, %[[casted]], %[[t2]]
|
||||
%s = arith.select %c, %t1, %t2 : tensor<?xf32>
|
||||
|
||||
// CHECK: memref.store %{{.*}}, %[[select]]
|
||||
%w = tensor.insert %cst into %s[%idx] : tensor<?xf32>
|
||||
|
||||
// CHECK: %[[f:.*]] = memref.load %[[t1]]
|
||||
%f = tensor.extract %t1[%idx] : tensor<?xf32>
|
||||
|
||||
// CHECK: return %[[f]], %[[select]]
|
||||
return %f, %w : f32, tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// A regression test to make sure that we handle rank-reducing extract_slice
|
||||
// correctly.
|
||||
|
||||
// CHECK-LABEL: func @rank_reducing
|
||||
func.func @rank_reducing(
|
||||
%i: index, %j: index,
|
||||
%arg0: tensor<8x18x32xf32>)
|
||||
-> tensor<?x1x6x8xf32> {
|
||||
%c1 = arith.constant 1 : index
|
||||
%c6 = arith.constant 6 : index
|
||||
%c8 = arith.constant 8 : index
|
||||
%c32 = arith.constant 32 : index
|
||||
%c0 = arith.constant 0 : index
|
||||
%0 = linalg.init_tensor [4, 1, 6, 8] : tensor<4x1x6x8xf32>
|
||||
%1 = tensor.cast %0 : tensor<4x1x6x8xf32> to tensor<?x1x6x8xf32>
|
||||
%2 = linalg.init_tensor [1, 6, 8] : tensor<1x6x8xf32>
|
||||
%5 = scf.for %arg7 = %c0 to %c32 step %c8 iter_args(%arg8 = %1) -> (tensor<?x1x6x8xf32>) {
|
||||
%7 = affine.apply affine_map<(d0) -> (d0 ceildiv 8)>(%arg7)
|
||||
%8 = tensor.extract_slice %arg0[%i, %j, %arg7] [1, 6, 8] [1, 1, 1] : tensor<8x18x32xf32> to tensor<1x6x8xf32>
|
||||
%9 = scf.for %arg9 = %c0 to %c6 step %c1 iter_args(%arg10 = %2) -> (tensor<1x6x8xf32>) {
|
||||
%11 = tensor.extract_slice %8[0, %arg9, 0] [1, 1, 8] [1, 1, 1] : tensor<1x6x8xf32> to tensor<1x1x8xf32>
|
||||
%12 = tensor.insert_slice %11 into %arg10[0, %arg9, 0] [1, 1, 8] [1, 1, 1] : tensor<1x1x8xf32> into tensor<1x6x8xf32>
|
||||
scf.yield %12 : tensor<1x6x8xf32>
|
||||
}
|
||||
%10 = tensor.insert_slice %9 into %arg8[%7, 0, 0, 0] [1, 1, 6, 8] [1, 1, 1, 1] : tensor<1x6x8xf32> into tensor<?x1x6x8xf32>
|
||||
scf.yield %10 : tensor<?x1x6x8xf32>
|
||||
}
|
||||
return %5: tensor<?x1x6x8xf32>
|
||||
}
|
||||
|
|
@ -0,0 +1,197 @@
|
|||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs bufferize-function-boundaries" -split-input-file | FileCheck %s
|
||||
|
||||
// Run fuzzer with different seeds.
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=23 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=59 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs test-analysis-only analysis-fuzzer-seed=91 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
|
||||
// Test bufferization using memref types that have no layout map.
|
||||
// RUN: mlir-opt %s -one-shot-bufferize="allow-return-allocs fully-dynamic-layout-maps=0 bufferize-function-boundaries" -split-input-file -o /dev/null
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
// CHECK-LABEL: func @insert_slice_fun
|
||||
// CHECK-SAME: %[[A0:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>,
|
||||
// CHECK-SAME: %[[A1:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>,
|
||||
// CHECK-SAME: %[[t0:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>,
|
||||
// CHECK-SAME: %[[t1:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>
|
||||
func.func @insert_slice_fun(
|
||||
%A0 : tensor<?xf32> {bufferization.writable = false},
|
||||
%A1 : tensor<?xf32> {bufferization.writable = true},
|
||||
%t0 : tensor<4xf32> {bufferization.writable = false},
|
||||
%t1 : tensor<4xf32> {bufferization.writable = true})
|
||||
-> (tensor<?xf32>, tensor<?xf32>, tensor<?xf32>, tensor<?xf32>)
|
||||
{
|
||||
// Hoisted allocs.
|
||||
// CHECK: %[[REALLOC1:.*]] = memref.alloc
|
||||
// CHECK: %[[REALLOC2:.*]] = memref.alloc
|
||||
// CHECK: %[[REALLOC3:.*]] = memref.alloc
|
||||
|
||||
// Alloc and copy the whole result tensor. Copy the tensor.extract_slice.
|
||||
// CHECK: memref.copy %[[A0]], %[[REALLOC3]]
|
||||
// CHECK: %[[SV_A0:.*]] = memref.subview %[[REALLOC3]]
|
||||
// CHECK: memref.copy %[[t0]], %[[SV_A0]]
|
||||
%r0 = tensor.insert_slice %t0 into %A0[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// Alloc and copy the whole result tensor. Copy the tensor.extract_slice.
|
||||
// CHECK: memref.copy %[[A0]]
|
||||
// CHECK: %[[SV_A0_2:.*]] = memref.subview %[[REALLOC2]]
|
||||
// CHECK: memref.copy %[[t1]], %[[SV_A0_2]]
|
||||
%r1 = tensor.insert_slice %t1 into %A0[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// Still alloc the large tensor because %A1 is read after. Copy the tensor.extract_slice.
|
||||
// CHECK: memref.copy %[[A1]]
|
||||
// CHECK: %[[SV_A1:.*]] = memref.subview %[[REALLOC1]]
|
||||
// CHECK: memref.copy %[[t0]], %[[SV_A1]]
|
||||
%r2 = tensor.insert_slice %t0 into %A1[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// Do not realloc the large tensor. Copy the tensor.extract_slice.
|
||||
// CHECK-NOT: alloc
|
||||
// CHECK: %[[SV_A1_2:.*]] = memref.subview %[[A1]]
|
||||
// CHECK: memref.copy %[[t1]], %[[SV_A1_2]]
|
||||
%r3 = tensor.insert_slice %t1 into %A1[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// CHECK: return %[[REALLOC3]], %[[REALLOC2]], %[[REALLOC1]] :
|
||||
// CHECK-SAME: memref<?xf32>, memref<?xf32>, memref<?xf32>
|
||||
return %r0, %r1, %r2, %r3: tensor<?xf32>, tensor<?xf32>, tensor<?xf32>, tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
// CHECK-LABEL: func @insert_slice_fun
|
||||
// CHECK-SAME: %[[A:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>
|
||||
// CHECK-SAME: %[[t:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>
|
||||
func.func @insert_slice_fun(
|
||||
%A : tensor<?xf32> {bufferization.writable = true},
|
||||
%t : tensor<4xf32> {bufferization.writable = false})
|
||||
-> tensor<?xf32>
|
||||
{
|
||||
%f0 = arith.constant 0.0 : f32
|
||||
|
||||
// CHECK-NOT: alloc
|
||||
// CHECK: %[[SV_A:.*]] = memref.subview %[[A]]
|
||||
// CHECK: memref.copy %[[t]], %[[SV_A]]
|
||||
%r0 = tensor.insert_slice %t into %A[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
/// Overwrite A inplace.
|
||||
// CHECK: linalg.fill ins({{.*}}{{.*}}outs(%[[A]]
|
||||
%r1 = linalg.fill ins(%f0 : f32) outs(%r0 : tensor<?xf32>) -> tensor<?xf32>
|
||||
|
||||
// CHECK: return
|
||||
// CHECK-NOT: tensor
|
||||
return %r1: tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
// CHECK-LABEL: func @insert_slice_fun
|
||||
// CHECK-SAME: %[[A:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>
|
||||
// CHECK-SAME: %[[t:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>
|
||||
func.func @insert_slice_fun(
|
||||
%A : tensor<?xf32> {bufferization.writable = true},
|
||||
%t : tensor<4xf32> {bufferization.writable = false})
|
||||
-> tensor<?xf32>
|
||||
{
|
||||
%f0 = arith.constant 0.0 : f32
|
||||
|
||||
// CHECK: linalg.fill ins({{.*}}{{.*}}outs(%[[A]]
|
||||
%r0 = linalg.fill ins(%f0 : f32) outs(%A : tensor<?xf32>) -> tensor<?xf32>
|
||||
|
||||
// CHECK-NOT: alloc
|
||||
// CHECK: %[[SV_A:.*]] = memref.subview %[[A]]
|
||||
/// Overwrite A inplace by copying into the subview.
|
||||
// CHECK: memref.copy %[[t]], %[[SV_A]]
|
||||
%r1 = tensor.insert_slice %t into %r0[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// CHECK: return
|
||||
// CHECK-NOT: tensor
|
||||
return %r1: tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-DAG: #[[$map_1d_dyn:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
|
||||
|
||||
// CHECK-LABEL: func @insert_slice_fun_not_inplace
|
||||
// CHECK-SAME: %[[A:[a-zA-Z0-9]*]]: memref<?xf32, #[[$map_1d_dyn]]>
|
||||
// CHECK-SAME: %[[t:[a-zA-Z0-9]*]]: memref<4xf32, #[[$map_1d_dyn]]>
|
||||
func.func @insert_slice_fun_not_inplace(
|
||||
%A : tensor<?xf32> {bufferization.writable = false},
|
||||
%t : tensor<4xf32> {bufferization.writable = false})
|
||||
-> tensor<?xf32>
|
||||
{
|
||||
// CHECK: %[[ALLOC:.*]] = memref.alloc(%{{.*}}) {alignment = 128 : i64} : memref<?xf32>
|
||||
// CHECK: memref.copy %[[A]], %[[ALLOC]] : memref<?xf32{{.*}} to memref<?xf32>
|
||||
// CHECK: %[[SV:.*]] = memref.subview %[[ALLOC]][0] [4] [1] : memref<?xf32> to memref<4xf32>
|
||||
// CHECK: memref.copy %[[t]], %[[SV]] : memref<4xf32, #map> to memref<4xf32>
|
||||
%r0 = tensor.insert_slice %t into %A[0][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
|
||||
// CHECK: return %{{.*}} : memref<?xf32>
|
||||
return %r0: tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-LABEL: func @tensor_cast_not_in_place(
|
||||
// CHECK-SAME: %[[A:.*]]: memref<?xf32{{.*}}>, %[[B:.*]]: memref<?xf32{{.*}}>
|
||||
// CHECK: %[[alloc:.*]] = memref.alloc
|
||||
// CHECK: memref.copy %[[A]], %[[alloc]]
|
||||
// CHECK: %[[subview:.*]] = memref.subview %[[A]][{{.*}}] [4] [1] : {{.*}} to memref<4xf32
|
||||
// CHECK: memref.copy %[[alloc]], %[[subview]]
|
||||
func.func @tensor_cast_not_in_place(
|
||||
%A : tensor<?xf32> {bufferization.writable = true},
|
||||
%B : tensor<?xf32> {bufferization.writable = false}, %idx: index)
|
||||
-> (tensor<?xf32>)
|
||||
{
|
||||
%r0 = tensor.cast %A : tensor<?xf32> to tensor<4xf32>
|
||||
%r1 = tensor.insert_slice %r0 into %A[%idx][4][1] : tensor<4xf32> into tensor<?xf32>
|
||||
return %r1 : tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// CHECK-LABEL: func @insert_op
|
||||
// CHECK-SAME: %[[t1:.*]]: memref<?xf32, {{.*}}>, %[[s:.*]]: f32, %[[i:.*]]: index
|
||||
func.func @insert_op(%t1 : tensor<?xf32> {bufferization.writable = true},
|
||||
%s : f32, %i : index) -> tensor<?xf32> {
|
||||
// CHECK: memref.store %[[s]], %[[t1]][%[[i]]]
|
||||
%0 = tensor.insert %s into %t1[%i] : tensor<?xf32>
|
||||
// CHECK: return
|
||||
return %0 : tensor<?xf32>
|
||||
}
|
||||
|
||||
// -----
|
||||
|
||||
// A regression test to make sure that we handle rank-reducing extract_slice
|
||||
// correctly.
|
||||
|
||||
// CHECK-LABEL: func @rank_reducing
|
||||
func.func @rank_reducing(
|
||||
%i: index, %j: index,
|
||||
%arg0: tensor<8x18x32xf32>)
|
||||
-> tensor<?x1x6x8xf32> {
|
||||
%c1 = arith.constant 1 : index
|
||||
%c6 = arith.constant 6 : index
|
||||
%c8 = arith.constant 8 : index
|
||||
%c32 = arith.constant 32 : index
|
||||
%c0 = arith.constant 0 : index
|
||||
%0 = linalg.init_tensor [4, 1, 6, 8] : tensor<4x1x6x8xf32>
|
||||
%1 = tensor.cast %0 : tensor<4x1x6x8xf32> to tensor<?x1x6x8xf32>
|
||||
%2 = linalg.init_tensor [1, 6, 8] : tensor<1x6x8xf32>
|
||||
%5 = scf.for %arg7 = %c0 to %c32 step %c8 iter_args(%arg8 = %1) -> (tensor<?x1x6x8xf32>) {
|
||||
%7 = affine.apply affine_map<(d0) -> (d0 ceildiv 8)>(%arg7)
|
||||
%8 = tensor.extract_slice %arg0[%i, %j, %arg7] [1, 6, 8] [1, 1, 1] : tensor<8x18x32xf32> to tensor<1x6x8xf32>
|
||||
%9 = scf.for %arg9 = %c0 to %c6 step %c1 iter_args(%arg10 = %2) -> (tensor<1x6x8xf32>) {
|
||||
%11 = tensor.extract_slice %8[0, %arg9, 0] [1, 1, 8] [1, 1, 1] : tensor<1x6x8xf32> to tensor<1x1x8xf32>
|
||||
%12 = tensor.insert_slice %11 into %arg10[0, %arg9, 0] [1, 1, 8] [1, 1, 1] : tensor<1x1x8xf32> into tensor<1x6x8xf32>
|
||||
scf.yield %12 : tensor<1x6x8xf32>
|
||||
}
|
||||
%10 = tensor.insert_slice %9 into %arg8[%7, 0, 0, 0] [1, 1, 6, 8] [1, 1, 1, 1] : tensor<1x6x8xf32> into tensor<?x1x6x8xf32>
|
||||
scf.yield %10 : tensor<?x1x6x8xf32>
|
||||
}
|
||||
return %5: tensor<?x1x6x8xf32>
|
||||
}
|
||||
Loading…
Reference in New Issue