XNNPACK Team | b455b12 | 2019-09-27 18:10:33 -0700 | [diff] [blame] | 1 | #!/bin/sh |
| 2 | # Copyright 2019 Google LLC |
| 3 | # |
| 4 | # This source code is licensed under the BSD-style license found in the |
| 5 | # LICENSE file in the root directory of this source tree. |
| 6 | |
| 7 | #################################### Scalar ################################### |
Marat Dukhan | 40a672f | 2019-11-25 03:08:22 -0800 | [diff] [blame] | 8 | tools/xngen src/f32-ppmm/scalar.c.in -D MR=4 -D NR=4 -o src/f32-ppmm/gen/4x4-scalar.c |
| 9 | tools/xngen src/f32-ppmm/scalar.c.in -D MR=2 -D NR=4 -o src/f32-ppmm/gen/2x4-scalar.c |
| 10 | tools/xngen src/f32-ppmm/scalar.c.in -D MR=4 -D NR=2 -o src/f32-ppmm/gen/4x2-scalar.c |
| 11 | tools/xngen src/f32-ppmm/scalar.c.in -D MR=3 -D NR=3 -o src/f32-ppmm/gen/3x3-scalar.c |
XNNPACK Team | b455b12 | 2019-09-27 18:10:33 -0700 | [diff] [blame] | 12 | |
| 13 | ################################### ARM NEON ################################## |
Marat Dukhan | 40a672f | 2019-11-25 03:08:22 -0800 | [diff] [blame] | 14 | tools/xngen src/f32-ppmm/neon.c.in -D MR=4 -D NR=8 -D FMA=0 -o src/f32-ppmm/gen/4x8-neon.c |
| 15 | tools/xngen src/f32-ppmm/neon.c.in -D MR=4 -D NR=8 -D FMA=1 -o src/f32-ppmm/gen/4x8-neonfma.c |
| 16 | tools/xngen src/f32-ppmm/neon.c.in -D MR=8 -D NR=8 -D FMA=0 -o src/f32-ppmm/gen/8x8-neon.c |
| 17 | tools/xngen src/f32-ppmm/neon.c.in -D MR=8 -D NR=8 -D FMA=1 -o src/f32-ppmm/gen/8x8-neonfma.c |
XNNPACK Team | b455b12 | 2019-09-27 18:10:33 -0700 | [diff] [blame] | 18 | |
| 19 | #################################### PSIMD #################################### |
Marat Dukhan | 40a672f | 2019-11-25 03:08:22 -0800 | [diff] [blame] | 20 | tools/xngen src/f32-ppmm/psimd.c.in -D MR=4 -D NR=8 -o src/f32-ppmm/gen/4x8-psimd.c |
XNNPACK Team | b455b12 | 2019-09-27 18:10:33 -0700 | [diff] [blame] | 21 | |
| 22 | ################################### x86 SSE ################################### |
Marat Dukhan | 40a672f | 2019-11-25 03:08:22 -0800 | [diff] [blame] | 23 | tools/xngen src/f32-ppmm/sse.c.in -D MR=4 -D NR=8 -o src/f32-ppmm/gen/4x8-sse.c |
XNNPACK Team | b455b12 | 2019-09-27 18:10:33 -0700 | [diff] [blame] | 24 | |
| 25 | ################################## Unit tests ################################# |
| 26 | tools/generate-gemm-test.py --spec test/f32-ppmm.yaml --output test/f32-ppmm.cc |