1#!/bin/sh 2# Copyright 2020 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 ################################### 8tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=1 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-lut16-p3-x1.c & 9tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=2 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-lut16-p3-x2.c & 10tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=3 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-lut16-p3-x3.c & 11tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=4 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-lut16-p3-x4.c & 12tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=5 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-lut16-p3-x5.c & 13tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=6 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-lut16-p3-x6.c & 14 15tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=1 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-p6-x1.c & 16tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=2 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-p6-x2.c & 17tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=3 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-p6-x3.c & 18tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=4 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-p6-x4.c & 19tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=5 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-p6-x5.c & 20tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=6 -D WASM=0 -o src/f32-velu/gen/velu-scalar-rr2-p6-x6.c & 21 22##################################### WAsm #################################### 23tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=1 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-lut16-p3-x1.c & 24tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=2 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-lut16-p3-x2.c & 25tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=3 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-lut16-p3-x3.c & 26tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=4 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-lut16-p3-x4.c & 27tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=5 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-lut16-p3-x5.c & 28tools/xngen src/f32-velu/scalar-rr2-lut16-p3.c.in -D BATCH_TILE=6 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-lut16-p3-x6.c & 29 30tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=1 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-p6-x1.c & 31tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=2 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-p6-x2.c & 32tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=3 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-p6-x3.c & 33tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=4 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-p6-x4.c & 34tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=5 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-p6-x5.c & 35tools/xngen src/f32-velu/scalar-rr2-p6.c.in -D BATCH_TILE=6 -D WASM=1 -o src/f32-velu/gen/velu-wasm-rr2-p6-x6.c & 36 37################################## WAsm SIMD ################################## 38tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=4 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-lut16-p3-x4.c & 39tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=8 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-lut16-p3-x8.c & 40tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=12 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-lut16-p3-x12.c & 41tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=16 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-lut16-p3-x16.c & 42tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=20 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-lut16-p3-x20.c & 43tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=24 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-lut16-p3-x24.c & 44 45tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=4 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-lut16-p3-x4.c & 46tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=8 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-lut16-p3-x8.c & 47tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=12 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-lut16-p3-x12.c & 48tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=16 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-lut16-p3-x16.c & 49tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=20 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-lut16-p3-x20.c & 50tools/xngen src/f32-velu/wasmsimd-rr2-lut16-p3.c.in -D BATCH_TILE=24 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-lut16-p3-x24.c & 51 52tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=4 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-p6-x4.c & 53tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=8 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-p6-x8.c & 54tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=12 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-p6-x12.c & 55tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=16 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-p6-x16.c & 56tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=20 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-p6-x20.c & 57tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=24 -D X86=0 -o src/f32-velu/gen/velu-wasmsimd-arm-rr2-p6-x24.c & 58 59tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=4 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-p6-x4.c & 60tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=8 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-p6-x8.c & 61tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=12 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-p6-x12.c & 62tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=16 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-p6-x16.c & 63tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=20 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-p6-x20.c & 64tools/xngen src/f32-velu/wasmsimd-rr2-p6.c.in -D BATCH_TILE=24 -D X86=1 -o src/f32-velu/gen/velu-wasmsimd-x86-rr2-p6-x24.c & 65 66################################### ARM NEON ################################## 67tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=4 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-lut16-p3-x4.c & 68tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=8 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-lut16-p3-x8.c & 69tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=12 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-lut16-p3-x12.c & 70tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=16 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-lut16-p3-x16.c & 71tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=20 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-lut16-p3-x20.c & 72tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=24 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-lut16-p3-x24.c & 73 74tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=4 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-p6-x4.c & 75tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=8 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-p6-x8.c & 76tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=12 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-p6-x12.c & 77tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=16 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-p6-x16.c & 78tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=20 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-p6-x20.c & 79tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=24 -D FMA=0 -o src/f32-velu/gen/velu-neon-rr2-p6-x24.c & 80 81tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=4 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-lut16-p3-x4.c & 82tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=8 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-lut16-p3-x8.c & 83tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=12 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-lut16-p3-x12.c & 84tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=16 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-lut16-p3-x16.c & 85tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=20 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-lut16-p3-x20.c & 86tools/xngen src/f32-velu/neon-lut16-p3.c.in -D BATCH_TILE=24 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-lut16-p3-x24.c & 87 88tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=4 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-p6-x4.c & 89tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=8 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-p6-x8.c & 90tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=12 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-p6-x12.c & 91tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=16 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-p6-x16.c & 92tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=20 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-p6-x20.c & 93tools/xngen src/f32-velu/neon-p6.c.in -D BATCH_TILE=24 -D FMA=1 -o src/f32-velu/gen/velu-neonfma-rr1-p6-x24.c & 94 95################################# x86 128-bit ################################# 96tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=4 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-lut16-p3-x4.c & 97tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=8 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-lut16-p3-x8.c & 98tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=12 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-lut16-p3-x12.c & 99tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=16 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-lut16-p3-x16.c & 100tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=20 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-lut16-p3-x20.c & 101tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=24 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-lut16-p3-x24.c & 102 103tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=4 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-p6-x4.c & 104tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=8 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-p6-x8.c & 105tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=12 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-p6-x12.c & 106tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=16 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-p6-x16.c & 107tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=20 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-p6-x20.c & 108tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=24 -D SSE=2 -o src/f32-velu/gen/velu-sse2-rr2-p6-x24.c & 109 110tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=4 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-lut16-p3-x4.c & 111tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=8 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-lut16-p3-x8.c & 112tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=12 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-lut16-p3-x12.c & 113tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=16 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-lut16-p3-x16.c & 114tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=20 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-lut16-p3-x20.c & 115tools/xngen src/f32-velu/sse-rr2-lut16-p3.c.in -D BATCH_TILE=24 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-lut16-p3-x24.c & 116 117tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=4 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-p6-x4.c & 118tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=8 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-p6-x8.c & 119tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=12 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-p6-x12.c & 120tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=16 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-p6-x16.c & 121tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=20 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-p6-x20.c & 122tools/xngen src/f32-velu/sse-rr2-p6.c.in -D BATCH_TILE=24 -D SSE=4 -o src/f32-velu/gen/velu-sse41-rr2-p6-x24.c & 123 124################################# x86 256-bit ################################# 125tools/xngen src/f32-velu/avx-rr2-lut4-p4-perm.c.in -D BATCH_TILE=8 -o src/f32-velu/gen/velu-avx-rr2-lut4-p4-perm-x8.c & 126tools/xngen src/f32-velu/avx-rr2-lut4-p4-perm.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx-rr2-lut4-p4-perm-x16.c & 127tools/xngen src/f32-velu/avx-rr2-lut4-p4-perm.c.in -D BATCH_TILE=24 -o src/f32-velu/gen/velu-avx-rr2-lut4-p4-perm-x24.c & 128tools/xngen src/f32-velu/avx-rr2-lut4-p4-perm.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx-rr2-lut4-p4-perm-x32.c & 129tools/xngen src/f32-velu/avx-rr2-lut4-p4-perm.c.in -D BATCH_TILE=40 -o src/f32-velu/gen/velu-avx-rr2-lut4-p4-perm-x40.c & 130tools/xngen src/f32-velu/avx-rr2-lut4-p4-perm.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx-rr2-lut4-p4-perm-x48.c & 131 132tools/xngen src/f32-velu/avx-rr2-lut16-p3.c.in -D BATCH_TILE=8 -o src/f32-velu/gen/velu-avx-rr2-lut16-p3-x8.c & 133tools/xngen src/f32-velu/avx-rr2-lut16-p3.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx-rr2-lut16-p3-x16.c & 134tools/xngen src/f32-velu/avx-rr2-lut16-p3.c.in -D BATCH_TILE=24 -o src/f32-velu/gen/velu-avx-rr2-lut16-p3-x24.c & 135tools/xngen src/f32-velu/avx-rr2-lut16-p3.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx-rr2-lut16-p3-x32.c & 136tools/xngen src/f32-velu/avx-rr2-lut16-p3.c.in -D BATCH_TILE=40 -o src/f32-velu/gen/velu-avx-rr2-lut16-p3-x40.c & 137tools/xngen src/f32-velu/avx-rr2-lut16-p3.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx-rr2-lut16-p3-x48.c & 138 139tools/xngen src/f32-velu/avx-rr2-p6.c.in -D BATCH_TILE=8 -o src/f32-velu/gen/velu-avx-rr2-p6-x8.c & 140tools/xngen src/f32-velu/avx-rr2-p6.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx-rr2-p6-x16.c & 141tools/xngen src/f32-velu/avx-rr2-p6.c.in -D BATCH_TILE=24 -o src/f32-velu/gen/velu-avx-rr2-p6-x24.c & 142tools/xngen src/f32-velu/avx-rr2-p6.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx-rr2-p6-x32.c & 143tools/xngen src/f32-velu/avx-rr2-p6.c.in -D BATCH_TILE=40 -o src/f32-velu/gen/velu-avx-rr2-p6-x40.c & 144tools/xngen src/f32-velu/avx-rr2-p6.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx-rr2-p6-x48.c & 145 146tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=8 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x8.c & 147tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x16.c & 148tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=24 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x24.c & 149tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x32.c & 150tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=40 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x40.c & 151tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x48.c & 152tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=56 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x56.c & 153tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=64 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x64.c & 154tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=72 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x72.c & 155tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=80 -o src/f32-velu/gen/velu-avx2-rr1-lut4-p4-perm-x80.c & 156 157tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=8 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x8.c & 158tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x16.c & 159tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=24 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x24.c & 160tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x32.c & 161tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=40 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x40.c & 162tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x48.c & 163tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=56 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x56.c & 164tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=64 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x64.c & 165tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=72 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x72.c & 166tools/xngen src/f32-velu/avx2-rr1-lut8-p4-perm.c.in -D BATCH_TILE=80 -o src/f32-velu/gen/velu-avx2-rr1-lut8-p4-perm-x80.c & 167 168tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=8 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x8.c & 169tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x16.c & 170tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=24 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x24.c & 171tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x32.c & 172tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=40 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x40.c & 173tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x48.c & 174tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=56 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x56.c & 175tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=64 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x64.c & 176tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=72 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x72.c & 177tools/xngen src/f32-velu/avx2-rr1-lut16-p3-gather.c.in -D BATCH_TILE=80 -o src/f32-velu/gen/velu-avx2-rr1-lut16-p3-gather-x80.c & 178 179tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=8 -o src/f32-velu/gen/velu-avx2-rr1-p6-x8.c & 180tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx2-rr1-p6-x16.c & 181tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=24 -o src/f32-velu/gen/velu-avx2-rr1-p6-x24.c & 182tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx2-rr1-p6-x32.c & 183tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=40 -o src/f32-velu/gen/velu-avx2-rr1-p6-x40.c & 184tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx2-rr1-p6-x48.c & 185tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=56 -o src/f32-velu/gen/velu-avx2-rr1-p6-x56.c & 186tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=64 -o src/f32-velu/gen/velu-avx2-rr1-p6-x64.c & 187tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=72 -o src/f32-velu/gen/velu-avx2-rr1-p6-x72.c & 188tools/xngen src/f32-velu/avx2-rr1-p6.c.in -D BATCH_TILE=80 -o src/f32-velu/gen/velu-avx2-rr1-p6-x80.c & 189 190################################# x86 512-bit ################################# 191tools/xngen src/f32-velu/avx512f-rr1-lut16-p3-perm.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx512f-rr1-lut16-p3-perm-x16.c & 192tools/xngen src/f32-velu/avx512f-rr1-lut16-p3-perm.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx512f-rr1-lut16-p3-perm-x32.c & 193tools/xngen src/f32-velu/avx512f-rr1-lut16-p3-perm.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx512f-rr1-lut16-p3-perm-x48.c & 194tools/xngen src/f32-velu/avx512f-rr1-lut16-p3-perm.c.in -D BATCH_TILE=64 -o src/f32-velu/gen/velu-avx512f-rr1-lut16-p3-perm-x64.c & 195tools/xngen src/f32-velu/avx512f-rr1-lut16-p3-perm.c.in -D BATCH_TILE=80 -o src/f32-velu/gen/velu-avx512f-rr1-lut16-p3-perm-x80.c & 196tools/xngen src/f32-velu/avx512f-rr1-lut16-p3-perm.c.in -D BATCH_TILE=96 -o src/f32-velu/gen/velu-avx512f-rr1-lut16-p3-perm-x96.c & 197tools/xngen src/f32-velu/avx512f-rr1-lut16-p3-perm.c.in -D BATCH_TILE=112 -o src/f32-velu/gen/velu-avx512f-rr1-lut16-p3-perm-x112.c & 198tools/xngen src/f32-velu/avx512f-rr1-lut16-p3-perm.c.in -D BATCH_TILE=128 -o src/f32-velu/gen/velu-avx512f-rr1-lut16-p3-perm-x128.c & 199 200tools/xngen src/f32-velu/avx512f-rr1-p6.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx512f-rr1-p6-x16.c & 201tools/xngen src/f32-velu/avx512f-rr1-p6.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx512f-rr1-p6-x32.c & 202tools/xngen src/f32-velu/avx512f-rr1-p6.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx512f-rr1-p6-x48.c & 203tools/xngen src/f32-velu/avx512f-rr1-p6.c.in -D BATCH_TILE=64 -o src/f32-velu/gen/velu-avx512f-rr1-p6-x64.c & 204tools/xngen src/f32-velu/avx512f-rr1-p6.c.in -D BATCH_TILE=80 -o src/f32-velu/gen/velu-avx512f-rr1-p6-x80.c & 205tools/xngen src/f32-velu/avx512f-rr1-p6.c.in -D BATCH_TILE=96 -o src/f32-velu/gen/velu-avx512f-rr1-p6-x96.c & 206tools/xngen src/f32-velu/avx512f-rr1-p6.c.in -D BATCH_TILE=112 -o src/f32-velu/gen/velu-avx512f-rr1-p6-x112.c & 207tools/xngen src/f32-velu/avx512f-rr1-p6.c.in -D BATCH_TILE=128 -o src/f32-velu/gen/velu-avx512f-rr1-p6-x128.c & 208 209################################## Unit tests ################################# 210tools/generate-vunary-test.py --spec test/f32-velu.yaml --output test/f32-velu.cc & 211 212wait 213