|
| 1 | +/******************************************************************************* |
| 2 | +Copyright (c) 2015, The OpenBLAS Project |
| 3 | +All rights reserved. |
| 4 | +Redistribution and use in source and binary forms, with or without |
| 5 | +modification, are permitted provided that the following conditions are |
| 6 | +met: |
| 7 | +1. Redistributions of source code must retain the above copyright |
| 8 | +notice, this list of conditions and the following disclaimer. |
| 9 | +2. Redistributions in binary form must reproduce the above copyright |
| 10 | +notice, this list of conditions and the following disclaimer in |
| 11 | +the documentation and/or other materials provided with the |
| 12 | +distribution. |
| 13 | +3. Neither the name of the OpenBLAS project nor the names of |
| 14 | +its contributors may be used to endorse or promote products |
| 15 | +derived from this software without specific prior written permission. |
| 16 | +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" |
| 17 | +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
| 18 | +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
| 19 | +ARE DISCLAIMED. IN NO EVENT SHALL THE OPENBLAS PROJECT OR CONTRIBUTORS BE |
| 20 | +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL |
| 21 | +DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR |
| 22 | +SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
| 23 | +CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, |
| 24 | +OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE |
| 25 | +USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 26 | +*******************************************************************************/ |
| 27 | +#include "common.h" |
| 28 | +#include <arm_sve.h> |
| 29 | + |
| 30 | +#ifdef DOUBLE |
| 31 | +#define SVE_TYPE svfloat64_t |
| 32 | +#define SVE_ZERO svdup_f64(0.0) |
| 33 | +#define SVE_WHILELT svwhilelt_b64 |
| 34 | +#define SVE_ALL svptrue_b64() |
| 35 | +#define SVE_WIDTH svcntd() |
| 36 | +#else |
| 37 | +#define SVE_TYPE svfloat32_t |
| 38 | +#define SVE_ZERO svdup_f32(0.0) |
| 39 | +#define SVE_WHILELT svwhilelt_b32 |
| 40 | +#define SVE_ALL svptrue_b32() |
| 41 | +#define SVE_WIDTH svcntw() |
| 42 | +#endif |
| 43 | + |
| 44 | +static int rot_kernel_sve(BLASLONG n, FLOAT *x, FLOAT *y, FLOAT c, FLOAT s) |
| 45 | +{ |
| 46 | + for (int i = 0; i < n; i += SVE_WIDTH) |
| 47 | + { |
| 48 | + svbool_t pg = SVE_WHILELT((uint32_t)i, (uint32_t)n); |
| 49 | + SVE_TYPE x_vec = svld1(pg, &x[i]); |
| 50 | + SVE_TYPE y_vec = svld1(pg, &y[i]); |
| 51 | + SVE_TYPE cx_vec = svmul_z(pg, x_vec, c); |
| 52 | + SVE_TYPE sy_vec = svmul_z(pg, y_vec, s); |
| 53 | + SVE_TYPE sx_vec = svmul_z(pg, x_vec, s); |
| 54 | + SVE_TYPE cy_vec = svmul_z(pg, y_vec, c); |
| 55 | + svst1(pg, &x[i], svadd_z(pg, cx_vec, sy_vec)); |
| 56 | + svst1(pg, &y[i], svsub_z(pg, cy_vec, sx_vec)); |
| 57 | + } |
| 58 | + return (0); |
| 59 | +} |
0 commit comments