1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
|
// RUN: mlir-opt -test-tiling-interface=tile-consumer-fuse-and-yield-producer-using-scf-for -cse -split-input-file %s | FileCheck %s
func.func @gemm_gemm_fusion_yield_both(%lhs0 : tensor<?x?xf32>, %rhs0 : tensor<?x?xf32>, %rhs1 : tensor<?x?xf32>,
%init0 : tensor<?x?xf32>, %init1 : tensor<?x?xf32>)
-> (tensor<?x?xf32>, tensor<?x?xf32>) {
%c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index
%cst = arith.constant 0.0 : f32
%d0 = tensor.dim %lhs0, %c0 : tensor<?x?xf32>
%d1 = tensor.dim %rhs0, %c1 : tensor<?x?xf32>
%fill0 = linalg.fill ins(%cst : f32) outs(%init0 : tensor<?x?xf32>) -> tensor<?x?xf32>
%gemm0 = linalg.matmul
ins(%lhs0, %rhs0 : tensor<?x?xf32>, tensor<?x?xf32>) outs(%fill0 : tensor<?x?xf32>) -> tensor<?x?xf32>
%d2 = tensor.dim %rhs1, %c1 : tensor<?x?xf32>
%fill1 = linalg.fill ins(%cst : f32) outs(%init1 : tensor<?x?xf32>) -> tensor<?x?xf32>
%gemm1 = linalg.matmul {__internal_linalg_transform__ = "gemm_sequence_fusion_and_yield"}
ins(%gemm0, %rhs1 : tensor<?x?xf32>, tensor<?x?xf32>) outs(%fill1 : tensor<?x?xf32>) -> tensor<?x?xf32>
return %gemm0, %gemm1 : tensor<?x?xf32>, tensor<?x?xf32>
}
// CHECK: func.func @gemm_gemm_fusion_yield_both(
// CHECK-SAME: %[[LHS0:[a-zA-Z0-9]+]]: tensor<?x?xf32>
// CHECK-SAME: %[[RHS0:[a-zA-Z0-9]+]]: tensor<?x?xf32>,
// CHECK-SAME: %[[RHS1:[a-zA-Z0-9]+]]: tensor<?x?xf32>,
// CHECK-SAME: %[[INIT0:[a-zA-Z0-9]+]]: tensor<?x?xf32>,
// CHECK-SAME: %[[INIT1:[a-zA-Z0-9]+]]: tensor<?x?xf32>)
// CHECK-DAG: %[[C0:.+]] = arith.constant 0 : index
// CHECK-DAG: %[[C1:.+]] = arith.constant 1 : index
// CHECK: %[[RESULT:.+]]:2 = scf.for %[[IV:[a-zA-Z0-9]+]] =
// CHECK-SAME: iter_args(%[[ITERARG0:[a-zA-Z0-9]+]] = %[[INIT1]], %[[ITERARG1:[a-zA-Z0-9]+]] = %[[INIT0]])
// CHECK-DAG: %[[LHS0_TILE:.+]] = tensor.extract_slice %[[LHS0]][%[[IV]], 0]
// CHECK-DAG: %[[RHS0_TILE:.+]] = tensor.extract_slice %[[RHS0]][0, 0]
// CHECK-DAG: %[[INIT0_TILE:.+]] = tensor.extract_slice %[[ITERARG1]][%[[IV]], 0]
// CHECK: %[[FILL0_TILE:.+]] = linalg.fill
// CHECK-SAME: outs(%[[INIT0_TILE]] :
// CHECK: %[[GEMM0_TILE:.+]] = linalg.matmul
// CHECK-SAME: ins(%[[LHS0_TILE]], %[[RHS0_TILE]] :
// CHECK-SAME: outs(%[[FILL0_TILE]] :
// CHECK-DAG: %[[RHS1_TILE:.+]] = tensor.extract_slice %[[RHS1]][0, 0]
// CHECK-DAG: %[[INIT1_TILE:.+]] = tensor.extract_slice %[[ITERARG0]][%[[IV]], 0]
// CHECK: %[[FILL1_TILE:.+]] = linalg.fill
// CHECK-SAME: outs(%[[INIT1_TILE]] :
// CHECK: %[[GEMM1_TILE:.+]] = linalg.matmul
// CHECK-SAME: ins(%[[GEMM0_TILE]], %[[RHS1_TILE]] :
// CHECK-SAME: outs(%[[FILL1_TILE]] :
// CHECK: %[[INSERT0:.+]] = tensor.insert_slice %[[GEMM1_TILE]] into %[[ITERARG0]][%[[IV]], 0]
// CHECK: %[[INSERT1:.+]] = tensor.insert_slice %[[GEMM0_TILE]] into %[[ITERARG1]][%[[IV]], 0]
// CHECK: scf.yield %[[INSERT0]], %[[INSERT1]]
|
