| /third_party/mindspore/mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/assembly/opt/ |
| D | MatmulDpInt8Opt.S | 46 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
47 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
64 mov x23, #4
66 mov x24, #4
82 dup v16.4s, wzr
83 dup v17.4s, wzr
84 dup v18.4s, wzr
85 dup v19.4s, wzr
86 dup v20.4s, wzr
87 dup v21.4s, wzr
[all …]
|
| D | MatmulDpInt8.S | 47 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
48 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
84 dup v16.4s, wzr
85 dup v17.4s, wzr
86 dup v18.4s, wzr
87 dup v19.4s, wzr
88 dup v20.4s, wzr
89 dup v21.4s, wzr
90 dup v22.4s, wzr
91 dup v23.4s, wzr
[all …]
|
| /third_party/mindspore/mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/assembly/arm64/ |
| D | PostFuncBiasReluC8.S | 37 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
38 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
40 movi v26.4s, #6
41 scvtf v26.4s, v26.4s
42 dup v27.4s, wzr
48 mov x15, #4
53 ld1 {v16.4s, v17.4s}, [x2], #32
59 ld1 {v0.4s, v1.4s, v2.4s, v3.4s}, [x1], #64
60 ld1 {v4.4s, v5.4s, v6.4s, v7.4s}, [x1], #64
61 ld1 {v8.4s, v9.4s, v10.4s, v11.4s}, [x1], #64
[all …]
|
| D | AdderFp32.S | 37 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
38 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
46 mov x20, #4
50 cmp x6, #4
66 ld1 {v0.4s, v1.4s, v2.4s}, [x10], #48
67 ld1 {v3.4s}, [x14], #16
69 dup v8.4s, v0.s[0]
70 fabd v9.4s, v3.4s, v8.4s
71 dup v10.4s, v0.s[1]
72 fabd v11.4s, v3.4s, v10.4s
[all …]
|
| D | ConvDw3x3Int8.S | 47 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
48 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
71 ld1r {v27.4s}, [x11] // out_multiplier
72 ld1r {v26.4s}, [x12] // left_shift
73 ld1r {v28.4s}, [x13] // right_shift
76 ld1 {v27.4s}, [x11]
77 ld1 {v26.4s}, [x12]
78 ld1 {v28.4s}, [x13]
80 dup v29.4s, w10
81 dup v30.4s, w14
[all …]
|
| D | TiledC4MatmulFp32.S | 32 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
33 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
35 mov x7, #4 //sizeof(float)
47 ld1 {v0.4s, v1.4s, v2.4s, v3.4s}, [x8], #64
48 ld1 {v8.4s, v9.4s, v10.4s, v11.4s}, [x2], #64
49 fmul v16.4s, v8.4s, v0.s[0]
50 fmul v17.4s, v8.4s, v1.s[0]
51 ld1 {v4.4s, v5.4s, v6.4s, v7.4s}, [x8], #64
52 fmul v18.4s, v8.4s, v2.s[0]
53 fmul v19.4s, v8.4s, v3.s[0]
[all …]
|
| D | ConvDw3x3Int8Stride2.S | 47 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
48 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
69 dup v29.4s, w10
70 dup v30.4s, w14
71 dup v31.4s, w15
105 ld1 {v24.4s}, [x3]
106 ld1 {v25.4s}, [x19]
107 ld1 {v26.4s}, [x3]
108 ld1 {v27.4s}, [x19]
116 smlal v24.4s, v0.4h, v9.4h
[all …]
|
| D | ConvFp32Center.S | 34 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
35 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
54 ld1 {v25.4s}, [x3]
55 movi v26.4s, #6
56 scvtf v26.4s, v26.4s
57 dup v27.4s, wzr
99 ld1 {v28.4s}, [x16], x15
100 ld1 {v29.4s}, [x16], x15
101 ld1 {v30.4s}, [x16], x15
102 ld1 {v31.4s}, [x16], x15
[all …]
|
| D | MatmulFp32Opt.S | 37 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
38 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
56 mov x22, #4
59 // col >= 4 , block stride 192, otherwise 12 * 4 * col
60 cmp x7, #4
72 mov x21, #4
78 mov x21, #4
86 cmp x6, #4
108 cmp x13, #4
112 ld1 {v0.4s, v1.4s, v2.4s}, [x10], #48
[all …]
|
| D | ConvDwInt8PostAlign4.S | 34 dup v26.4s, w5
35 dup v27.4s, w4
36 dup v28.4s, w6
38 dup v29.4s, w3
39 dup v30.4s, w7
40 dup v31.4s, w8
46 ld1 {v0.4s}, [x1], #16
47 ld1 {v1.4s}, [x1], #16
48 ld1 {v2.4s}, [x1], #16
49 ld1 {v3.4s}, [x1], #16
[all …]
|
| D | ConvDw3x3Fp32Stride2.S | 39 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
40 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
46 mov w11, #4
47 mul w15, w4, w11 // col_size * 4
48 mul w16, w6, w11 // channel * 4
49 mul w17, w5, w11 // row_size * 4
51 mul w14, w11, w15 // col_size * 2 * 4
53 movi v26.4s, #6
54 scvtf v26.4s, v26.4s
55 dup v27.4s, wzr
[all …]
|
| D | PostFuncInt8C4Neon64.S | 64 dup v26.4s, w7
65 dup v27.4s, w8
66 dup v28.4s, w9
67 dup v29.4s, w10
68 dup v30.4s, w11
69 dup v31.4s, w12
76 mov x25, #4
79 add w15, w15, #4
81 ld1 {v16.4s}, [x1], #16
84 cmp w16, #4
[all …]
|
| D | ConvDw3x3Fp32Stride1.S | 39 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
40 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
46 mov w11, #4
47 mul w15, w4, w11 // col_size * 4
48 mul w16, w6, w11 // channel * 4
49 mul w17, w5, w11 // row_size * 4
51 mul w14, w11, w15 // col_size * 2 * 4
53 movi v23.4s, #6
54 scvtf v23.4s, v23.4s
55 dup v24.4s, wzr
[all …]
|
| D | ConvDwFp32Center.S | 34 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
35 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
50 ld1 {v24.4s}, [x3]
51 movi v26.4s, #6
52 scvtf v26.4s, v26.4s
53 dup v27.4s, wzr
91 ld1 {v25.4s}, [x17], #16
92 ld1 {v16.4s}, [x22], x11
93 ld1 {v17.4s}, [x22], x11
94 fmla v0.4s, v16.4s, v25.4s
[all …]
|
| D | PostFuncBiasReluC4.S | 39 movi v26.4s, #6
40 scvtf v26.4s, v26.4s
41 dup v27.4s, wzr
43 mov x10, #4
52 mov x15, #4
55 add w10, w10, #4
57 ld1 {v16.4s}, [x2], #16
63 ld1 {v0.4s, v1.4s, v2.4s, v3.4s}, [x1], #64
64 ld1 {v4.4s, v5.4s, v6.4s, v7.4s}, [x1], #64
66 fadd v0.4s, v0.4s, v16.4s
[all …]
|
| D | ConvDwInt8Center.S | 37 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
38 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
55 ld1 {v20.4s}, [x15], #16
56 ld1 {v21.4s}, [x15], #16
59 ld1 {v22.4s}, [x16], #16
60 ld1 {v23.4s}, [x16], #16
63 ld1 {v24.4s}, [x17], #16
64 ld1 {v25.4s}, [x17], #16
67 ld1 {v26.4s}, [x25], #16
68 ld1 {v27.4s}, [x25], #16
[all …]
|
| D | MatmulFp32.S | 37 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
38 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
46 mov x19, #4
65 dup v8.4s, wzr
66 dup v9.4s, wzr
67 dup v10.4s, wzr
68 dup v11.4s, wzr
69 dup v12.4s, wzr
70 dup v13.4s, wzr
71 dup v14.4s, wzr
[all …]
|
| D | ConvDwFp32Indirect5x5.S | 40 movi v31.4s, #6
41 scvtf v31.4s, v31.4s
42 dup v30.4s, wzr
50 ld1 {v29.4s}, [x4], #16
67 ld1 {v0.4s}, [x6], #16
68 ld1 {v1.4s}, [x7], #16
69 ld1 {v2.4s}, [x8], #16
70 ld1 {v3.4s}, [x9], #16
71 ld1 {v4.4s}, [x10], #16
73 ld1 {v18.4s}, [x5], #16
[all …]
|
| D | MatmulFp32OptRow12.S | 37 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
38 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
56 mov x22, #4
59 // col >= 4 , block stride 192, otherwise 12 * 4 * col
60 cmp x7, #4
71 mov x21, #4
77 mov x21, #4
101 cmp x13, #4
105 ld1 {v0.4s, v1.4s, v2.4s}, [x10], #48
106 ld1 {v3.4s, v4.4s}, [x14], #32
[all …]
|
| /third_party/mindspore/mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/assembly/fp16/ |
| D | TiledC4MatmulFp16.S | 25 st1 {v8.4s, v9.4s, v10.4s, v11.4s}, [sp], #64
26 st1 {v12.4s, v13.4s, v14.4s, v15.4s}, [sp], #64
40 ld1 {v0.4h, v1.4h, v2.4h, v3.4h}, [x8], #32
41 ld1 {v8.4h, v9.4h, v10.4h, v11.4h}, [x2], #32
42 fmul v16.4h, v8.4h, v0.h[0]
43 fmul v17.4h, v8.4h, v1.h[0]
44 ld1 {v4.4h, v5.4h, v6.4h, v7.4h}, [x8], #32
45 fmul v18.4h, v8.4h, v2.h[0]
46 fmul v19.4h, v8.4h, v3.h[0]
47 ld1 {v12.4h, v13.4h, v14.4h, v15.4h}, [x6], #32
[all …]
|
| D | PostFuncBiasReluC4Fp16.S | 30 movi v26.4h, #6
31 scvtf v26.4h, v26.4h
32 dup v27.4h, wzr
46 add w10, w10, #4
48 ld1 {v16.4h}, [x2], #8
54 ld1 {v0.4h, v1.4h, v2.4h, v3.4h}, [x1], #32
55 ld1 {v4.4h, v5.4h, v6.4h, v7.4h}, [x1], #32
57 fadd v0.4h, v0.4h, v16.4h
58 fadd v1.4h, v1.4h, v16.4h
59 fadd v2.4h, v2.4h, v16.4h
[all …]
|
| /third_party/typescript/tests/baselines/reference/ |
| D | templateStringBinaryOperationsInvalid.types | 16 var c = 1 - `${ 3 }4`;
18 >1 - `${ 3 }4` : number
20 >`${ 3 }4` : string
23 var d = 1 - `2${ 3 }4`;
25 >1 - `2${ 3 }4` : number
27 >`2${ 3 }4` : string
44 var g = `${ 3 }4` - 5;
46 >`${ 3 }4` - 5 : number
47 >`${ 3 }4` : string
51 var h = `2${ 3 }4` - 5;
[all …]
|
| D | templateStringBinaryOperationsES6Invalid.types | 16 var c = 1 - `${ 3 }4`;
18 >1 - `${ 3 }4` : number
20 >`${ 3 }4` : string
23 var d = 1 - `2${ 3 }4`;
25 >1 - `2${ 3 }4` : number
27 >`2${ 3 }4` : string
44 var g = `${ 3 }4` - 5;
46 >`${ 3 }4` - 5 : number
47 >`${ 3 }4` : string
51 var h = `2${ 3 }4` - 5;
[all …]
|
| /third_party/boost/libs/graph/test/ |
| D | weighted_matching.dat | 1 55 13 20 5 12 12 9 3 3 4 1 5 10 11 13 5 4 13 5 10 2 3 2 1 8 9 0 4 6 11 3 8 9 7 1 7 10 4 1 11 12 8 1…
2 …6 9 8 1 10 8 11 9 0 9 4 8 3 9 6 11 0 2 1 3 6 11 0 4 4 7 5 9 10 2 7 10 7 8 4 10 1 1 5 2 7 4 3 5 8 6…
3 … 9 3 1 3 11 1 7 6 1 10 3 4 14 8 15 12 16 4 10 12 7 15 11 12 3 9 3 15 5 11 0 7 5 7 10 10 2 8 6 13 0…
4 43 11 21 9 5 3 4 0 1 8 3 5 3 9 7 0 7 3 7 8 11 6 2 11 5 7 1 10 9 0 10 2 8 5 2 5 9 4 7 0 8 3 10 6 5 3…
5 30 10 22 0 4 5 7 4 7 6 3 5 1 9 5 6 0 9 6 5 2 0 5 2 2 6 2 9 2 2 2 4 4 4 8 4 0 1 3 5 4 4 7 2 3 5 8 6 …
6 …4 13 0 9 2 7 6 4 3 0 7 6 12 0 8 6 2 1 10 2 6 10 3 10 3 1 3 7 4 4 11 4 5 1 9 1 3 4 9 3 10 7 4 6 6 0…
7 … 5 7 4 6 1 4 0 3 1 5 1 5 2 8 7 5 8 3 6 3 4 0 5 6 10 8 6 1 7 2 7 6 2 1 9 1 0 1 8 9 4 5 1 1 6 10 2 4…
8 …4 2 1 1 0 3 12 8 7 5 12 0 2 10 3 1 6 4 11 13 13 13 3 1 2 12 12 4 7 2 0 6 15 2 14 15 3 10 6 2 8 15 …
9 …4 3 0 9 2 11 5 9 9 7 8 1 10 6 3 9 11 6 4 10 2 8 2 9 4 2 4 9 4 0 7 5 7 2 5 8 11 0 10 5 8 7 10 9 7 5…
10 16 7 9 4 5 7 1 2 1 0 2 1 1 0 1 3 1 7 3 2 3 6 5 7 2 6 2 6 3 5
[all …]
|
| /third_party/ffmpeg/libavcodec/aarch64/ |
| D | aacpsdsp_neon.S | 22 1: ld1 {v0.4S,v1.4S}, [x1], #32
23 fmul v0.4S, v0.4S, v0.4S
24 fmul v1.4S, v1.4S, v1.4S
25 faddp v2.4S, v0.4S, v1.4S
26 ld1 {v3.4S}, [x0]
27 fadd v3.4S, v3.4S, v2.4S
28 st1 {v3.4S}, [x0], #16
29 subs w2, w2, #4
35 1: ld1 {v0.4S,v1.4S}, [x1], #32
36 ld1 {v2.4S}, [x2], #16
[all …]
|