summaryrefslogtreecommitdiffstats
path: root/third_party/aom/aom_dsp/mips/aom_convolve_copy_msa.c
diff options
context:
space:
mode:
Diffstat (limited to 'third_party/aom/aom_dsp/mips/aom_convolve_copy_msa.c')
-rw-r--r--third_party/aom/aom_dsp/mips/aom_convolve_copy_msa.c248
1 files changed, 0 insertions, 248 deletions
diff --git a/third_party/aom/aom_dsp/mips/aom_convolve_copy_msa.c b/third_party/aom/aom_dsp/mips/aom_convolve_copy_msa.c
deleted file mode 100644
index f7f116f4d..000000000
--- a/third_party/aom/aom_dsp/mips/aom_convolve_copy_msa.c
+++ /dev/null
@@ -1,248 +0,0 @@
-/*
- * Copyright (c) 2016, Alliance for Open Media. All rights reserved
- *
- * This source code is subject to the terms of the BSD 2 Clause License and
- * the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
- * was not distributed with this source code in the LICENSE file, you can
- * obtain it at www.aomedia.org/license/software. If the Alliance for Open
- * Media Patent License 1.0 was not distributed with this source code in the
- * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
- */
-
-#include <string.h>
-#include "aom_dsp/mips/macros_msa.h"
-
-static void copy_width8_msa(const uint8_t *src, int32_t src_stride,
- uint8_t *dst, int32_t dst_stride, int32_t height) {
- int32_t cnt;
- uint64_t out0, out1, out2, out3, out4, out5, out6, out7;
- v16u8 src0, src1, src2, src3, src4, src5, src6, src7;
-
- if (0 == height % 12) {
- for (cnt = (height / 12); cnt--;) {
- LD_UB8(src, src_stride, src0, src1, src2, src3, src4, src5, src6, src7);
- src += (8 * src_stride);
-
- out0 = __msa_copy_u_d((v2i64)src0, 0);
- out1 = __msa_copy_u_d((v2i64)src1, 0);
- out2 = __msa_copy_u_d((v2i64)src2, 0);
- out3 = __msa_copy_u_d((v2i64)src3, 0);
- out4 = __msa_copy_u_d((v2i64)src4, 0);
- out5 = __msa_copy_u_d((v2i64)src5, 0);
- out6 = __msa_copy_u_d((v2i64)src6, 0);
- out7 = __msa_copy_u_d((v2i64)src7, 0);
-
- SD4(out0, out1, out2, out3, dst, dst_stride);
- dst += (4 * dst_stride);
- SD4(out4, out5, out6, out7, dst, dst_stride);
- dst += (4 * dst_stride);
-
- LD_UB4(src, src_stride, src0, src1, src2, src3);
- src += (4 * src_stride);
-
- out0 = __msa_copy_u_d((v2i64)src0, 0);
- out1 = __msa_copy_u_d((v2i64)src1, 0);
- out2 = __msa_copy_u_d((v2i64)src2, 0);
- out3 = __msa_copy_u_d((v2i64)src3, 0);
- SD4(out0, out1, out2, out3, dst, dst_stride);
- dst += (4 * dst_stride);
- }
- } else if (0 == height % 8) {
- for (cnt = height >> 3; cnt--;) {
- LD_UB8(src, src_stride, src0, src1, src2, src3, src4, src5, src6, src7);
- src += (8 * src_stride);
-
- out0 = __msa_copy_u_d((v2i64)src0, 0);
- out1 = __msa_copy_u_d((v2i64)src1, 0);
- out2 = __msa_copy_u_d((v2i64)src2, 0);
- out3 = __msa_copy_u_d((v2i64)src3, 0);
- out4 = __msa_copy_u_d((v2i64)src4, 0);
- out5 = __msa_copy_u_d((v2i64)src5, 0);
- out6 = __msa_copy_u_d((v2i64)src6, 0);
- out7 = __msa_copy_u_d((v2i64)src7, 0);
-
- SD4(out0, out1, out2, out3, dst, dst_stride);
- dst += (4 * dst_stride);
- SD4(out4, out5, out6, out7, dst, dst_stride);
- dst += (4 * dst_stride);
- }
- } else if (0 == height % 4) {
- for (cnt = (height / 4); cnt--;) {
- LD_UB4(src, src_stride, src0, src1, src2, src3);
- src += (4 * src_stride);
- out0 = __msa_copy_u_d((v2i64)src0, 0);
- out1 = __msa_copy_u_d((v2i64)src1, 0);
- out2 = __msa_copy_u_d((v2i64)src2, 0);
- out3 = __msa_copy_u_d((v2i64)src3, 0);
-
- SD4(out0, out1, out2, out3, dst, dst_stride);
- dst += (4 * dst_stride);
- }
- } else if (0 == height % 2) {
- for (cnt = (height / 2); cnt--;) {
- LD_UB2(src, src_stride, src0, src1);
- src += (2 * src_stride);
- out0 = __msa_copy_u_d((v2i64)src0, 0);
- out1 = __msa_copy_u_d((v2i64)src1, 0);
-
- SD(out0, dst);
- dst += dst_stride;
- SD(out1, dst);
- dst += dst_stride;
- }
- }
-}
-
-static void copy_16multx8mult_msa(const uint8_t *src, int32_t src_stride,
- uint8_t *dst, int32_t dst_stride,
- int32_t height, int32_t width) {
- int32_t cnt, loop_cnt;
- const uint8_t *src_tmp;
- uint8_t *dst_tmp;
- v16u8 src0, src1, src2, src3, src4, src5, src6, src7;
-
- for (cnt = (width >> 4); cnt--;) {
- src_tmp = src;
- dst_tmp = dst;
-
- for (loop_cnt = (height >> 3); loop_cnt--;) {
- LD_UB8(src_tmp, src_stride, src0, src1, src2, src3, src4, src5, src6,
- src7);
- src_tmp += (8 * src_stride);
-
- ST_UB8(src0, src1, src2, src3, src4, src5, src6, src7, dst_tmp,
- dst_stride);
- dst_tmp += (8 * dst_stride);
- }
-
- src += 16;
- dst += 16;
- }
-}
-
-static void copy_width16_msa(const uint8_t *src, int32_t src_stride,
- uint8_t *dst, int32_t dst_stride, int32_t height) {
- int32_t cnt;
- v16u8 src0, src1, src2, src3, src4, src5, src6, src7;
-
- if (0 == height % 12) {
- for (cnt = (height / 12); cnt--;) {
- LD_UB8(src, src_stride, src0, src1, src2, src3, src4, src5, src6, src7);
- src += (8 * src_stride);
- ST_UB8(src0, src1, src2, src3, src4, src5, src6, src7, dst, dst_stride);
- dst += (8 * dst_stride);
-
- LD_UB4(src, src_stride, src0, src1, src2, src3);
- src += (4 * src_stride);
- ST_UB4(src0, src1, src2, src3, dst, dst_stride);
- dst += (4 * dst_stride);
- }
- } else if (0 == height % 8) {
- copy_16multx8mult_msa(src, src_stride, dst, dst_stride, height, 16);
- } else if (0 == height % 4) {
- for (cnt = (height >> 2); cnt--;) {
- LD_UB4(src, src_stride, src0, src1, src2, src3);
- src += (4 * src_stride);
-
- ST_UB4(src0, src1, src2, src3, dst, dst_stride);
- dst += (4 * dst_stride);
- }
- }
-}
-
-static void copy_width32_msa(const uint8_t *src, int32_t src_stride,
- uint8_t *dst, int32_t dst_stride, int32_t height) {
- int32_t cnt;
- v16u8 src0, src1, src2, src3, src4, src5, src6, src7;
-
- if (0 == height % 12) {
- for (cnt = (height / 12); cnt--;) {
- LD_UB4(src, src_stride, src0, src1, src2, src3);
- LD_UB4(src + 16, src_stride, src4, src5, src6, src7);
- src += (4 * src_stride);
- ST_UB4(src0, src1, src2, src3, dst, dst_stride);
- ST_UB4(src4, src5, src6, src7, dst + 16, dst_stride);
- dst += (4 * dst_stride);
-
- LD_UB4(src, src_stride, src0, src1, src2, src3);
- LD_UB4(src + 16, src_stride, src4, src5, src6, src7);
- src += (4 * src_stride);
- ST_UB4(src0, src1, src2, src3, dst, dst_stride);
- ST_UB4(src4, src5, src6, src7, dst + 16, dst_stride);
- dst += (4 * dst_stride);
-
- LD_UB4(src, src_stride, src0, src1, src2, src3);
- LD_UB4(src + 16, src_stride, src4, src5, src6, src7);
- src += (4 * src_stride);
- ST_UB4(src0, src1, src2, src3, dst, dst_stride);
- ST_UB4(src4, src5, src6, src7, dst + 16, dst_stride);
- dst += (4 * dst_stride);
- }
- } else if (0 == height % 8) {
- copy_16multx8mult_msa(src, src_stride, dst, dst_stride, height, 32);
- } else if (0 == height % 4) {
- for (cnt = (height >> 2); cnt--;) {
- LD_UB4(src, src_stride, src0, src1, src2, src3);
- LD_UB4(src + 16, src_stride, src4, src5, src6, src7);
- src += (4 * src_stride);
- ST_UB4(src0, src1, src2, src3, dst, dst_stride);
- ST_UB4(src4, src5, src6, src7, dst + 16, dst_stride);
- dst += (4 * dst_stride);
- }
- }
-}
-
-static void copy_width64_msa(const uint8_t *src, int32_t src_stride,
- uint8_t *dst, int32_t dst_stride, int32_t height) {
- copy_16multx8mult_msa(src, src_stride, dst, dst_stride, height, 64);
-}
-
-void aom_convolve_copy_msa(const uint8_t *src, ptrdiff_t src_stride,
- uint8_t *dst, ptrdiff_t dst_stride,
- const int16_t *filter_x, int32_t filter_x_stride,
- const int16_t *filter_y, int32_t filter_y_stride,
- int32_t w, int32_t h) {
- (void)filter_x;
- (void)filter_y;
- (void)filter_x_stride;
- (void)filter_y_stride;
-
- switch (w) {
- case 4: {
- uint32_t cnt, tmp;
- /* 1 word storage */
- for (cnt = h; cnt--;) {
- tmp = LW(src);
- SW(tmp, dst);
- src += src_stride;
- dst += dst_stride;
- }
- break;
- }
- case 8: {
- copy_width8_msa(src, src_stride, dst, dst_stride, h);
- break;
- }
- case 16: {
- copy_width16_msa(src, src_stride, dst, dst_stride, h);
- break;
- }
- case 32: {
- copy_width32_msa(src, src_stride, dst, dst_stride, h);
- break;
- }
- case 64: {
- copy_width64_msa(src, src_stride, dst, dst_stride, h);
- break;
- }
- default: {
- uint32_t cnt;
- for (cnt = h; cnt--;) {
- memcpy(dst, src, w);
- src += src_stride;
- dst += dst_stride;
- }
- break;
- }
- }
-}
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-30 08:34:03 +0000