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
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
|
// RUN: mlir-opt %s -pass-pipeline="builtin.module(func.func(test-match-reduction))" -verify-diagnostics -split-input-file
// Verify that the generic reduction detection utility works on different
// dialects.
// expected-remark@below {{Testing function}}
func.func @linalg_red_add(%in0t : tensor<?xf32>, %out0t : tensor<1xf32>) {
// expected-remark@below {{Reduction found in output #0!}}
// expected-remark@below {{Reduced Value: <block argument> of type 'f32' at index: 0}}
// expected-remark@below {{Combiner Op: %1 = arith.addf }}
%red = linalg.generic {indexing_maps = [affine_map<(d0) -> (d0)>,
affine_map<(d0) -> (0)>],
iterator_types = ["reduction"]}
ins(%in0t : tensor<?xf32>)
outs(%out0t : tensor<1xf32>) {
^bb0(%in0: f32, %out0: f32):
%add = arith.addf %in0, %out0 : f32
linalg.yield %add : f32
} -> tensor<1xf32>
return
}
// -----
// expected-remark@below {{Testing function}}
func.func @affine_red_add(%in: memref<256x512xf32>, %out: memref<256xf32>) {
%cst = arith.constant 0.000000e+00 : f32
affine.for %i = 0 to 256 {
// expected-remark@below {{Reduction found in output #0!}}
// expected-remark@below {{Reduced Value: %1 = affine.load }}
// expected-remark@below {{Combiner Op: %2 = arith.addf }}
%final_red = affine.for %j = 0 to 512 iter_args(%red_iter = %cst) -> (f32) {
%ld = affine.load %in[%i, %j] : memref<256x512xf32>
%add = arith.addf %red_iter, %ld : f32
affine.yield %add : f32
}
affine.store %final_red, %out[%i] : memref<256xf32>
}
return
}
// -----
// TODO: Iteration-carried values with multiple uses are not supported yet.
// expected-remark@below {{Testing function}}
func.func @linalg_red_max(%in0t: tensor<4x4xf32>, %out0t: tensor<4xf32>) {
// expected-remark@below {{Reduction NOT found in output #0!}}
%red = linalg.generic {indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
affine_map<(d0, d1) -> (d0)>],
iterator_types = ["parallel", "reduction"]}
ins(%in0t : tensor<4x4xf32>)
outs(%out0t : tensor<4xf32>) {
^bb0(%in0: f32, %out0: f32):
%cmp = arith.cmpf ogt, %in0, %out0 : f32
%sel = arith.select %cmp, %in0, %out0 : f32
linalg.yield %sel : f32
} -> tensor<4xf32>
return
}
// -----
// expected-remark@below {{Testing function}}
func.func @linalg_fused_red_add(%in0t: tensor<4x4xf32>, %out0t: tensor<4xf32>) {
// expected-remark@below {{Reduction found in output #0!}}
// expected-remark@below {{Reduced Value: %2 = arith.subf}}
// expected-remark@below {{Combiner Op: %3 = arith.addf}}
%red = linalg.generic {indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
affine_map<(d0, d1) -> (d0)>],
iterator_types = ["parallel", "reduction"]}
ins(%in0t : tensor<4x4xf32>)
outs(%out0t : tensor<4xf32>) {
^bb0(%in0: f32, %out0: f32):
%mul = arith.mulf %in0, %in0 : f32
%sub = arith.subf %mul, %in0 : f32
%add = arith.addf %sub, %out0 : f32
linalg.yield %add : f32
} -> tensor<4xf32>
return
}
// -----
// expected-remark@below {{Testing function}}
func.func @affine_no_red_rec(%in: memref<512xf32>) {
%cst = arith.constant 0.000000e+00 : f32
// %rec is the value loaded in the previous iteration.
// expected-remark@below {{Reduction NOT found in output #0!}}
%final_val = affine.for %j = 0 to 512 iter_args(%rec = %cst) -> (f32) {
%ld = affine.load %in[%j] : memref<512xf32>
%add = arith.addf %ld, %rec : f32
affine.yield %ld : f32
}
return
}
// -----
// expected-remark@below {{Testing function}}
func.func @affine_output_dep(%in: memref<512xf32>) {
%cst = arith.constant 0.000000e+00 : f32
// Reduction %red is not supported because it depends on another
// loop-carried dependence.
// expected-remark@below {{Reduction NOT found in output #0!}}
// expected-remark@below {{Reduction NOT found in output #1!}}
%final_red, %final_dep = affine.for %j = 0 to 512
iter_args(%red = %cst, %dep = %cst) -> (f32, f32) {
%ld = affine.load %in[%j] : memref<512xf32>
%add = arith.addf %dep, %red : f32
affine.yield %add, %ld : f32, f32
}
return
}
|
