Home
last modified time | relevance | path

Searched refs:row3 (Results 1 - 25 of 31) sorted by relevance

12

/third_party/python/Modules/_blake2/impl/
H A Dblake2s-round.h44 #define G1(row1,row2,row3,row4,buf) \
48 row3 = _mm_add_epi32( row3, row4 ); \
49 row2 = _mm_xor_si128( row2, row3 ); \
52 #define G2(row1,row2,row3,row4,buf) \
56 row3 = _mm_add_epi32( row3, row4 ); \
57 row2 = _mm_xor_si128( row2, row3 ); \
60 #define DIAGONALIZE(row1,row2,row3,row4) \
62 row3
[all...]
H A Dblake2s.c268 __m128i row1, row2, row3, row4; in blake2s_compress() local
306 row3 = _mm_setr_epi32( 0x6A09E667, 0xBB67AE85, 0x3C6EF372, 0xA54FF53A ); in blake2s_compress()
318 STOREU( &S->h[0], _mm_xor_si128( ff0, _mm_xor_si128( row1, row3 ) ) ); in blake2s_compress()
/third_party/skia/third_party/externals/libjpeg-turbo/simd/arm/
H A Djquanti-neon.c63 int16x8_t row3 = in jsimd_convsamp_neon() local
77 vst1q_s16(workspace + 3 * DCTSIZE, row3); in jsimd_convsamp_neon()
108 int16x8_t row3 = vld1q_s16(workspace + (i + 3) * DCTSIZE); in jsimd_quantize_neon() local
127 int16x8_t sign_row3 = vshrq_n_s16(row3, 15); in jsimd_quantize_neon()
132 uint16x8_t abs_row3 = vreinterpretq_u16_s16(vabsq_s16(row3)); in jsimd_quantize_neon()
160 row3 = vcombine_s16(vshrn_n_s32(row3_l, 16), vshrn_n_s32(row3_h, 16)); in jsimd_quantize_neon()
171 row3 = vreinterpretq_s16_u16(vshlq_u16(vreinterpretq_u16_s16(row3), in jsimd_quantize_neon()
181 row3 = veorq_s16(row3, sign_row in jsimd_quantize_neon()
[all...]
H A Djidctred-neon.c84 int16x8_t row3 = vld1q_s16(coef_block + 3 * DCTSIZE); in jsimd_idct_2x2_neon() local
98 row3 = vmulq_s16(row3, quant_row3); in jsimd_idct_2x2_neon()
115 tmp0_l = vmlal_lane_s16(tmp0_l, vget_low_s16(row3), consts, 2); in jsimd_idct_2x2_neon()
119 tmp0_h = vmlal_lane_s16(tmp0_h, vget_high_s16(row3), consts, 2); in jsimd_idct_2x2_neon()
205 int16x8_t row3 = vld1q_s16(coef_block + 3 * DCTSIZE); in jsimd_idct_4x4_neon() local
217 bitmap = vorrq_s16(bitmap, row3); in jsimd_idct_4x4_neon()
244 row3 = dcval; in jsimd_idct_4x4_neon()
276 z3 = vmul_s16(vget_high_s16(row3), quant_row3); in jsimd_idct_4x4_neon()
292 row3 in jsimd_idct_4x4_neon()
[all...]
H A Djidctint-neon.c100 int16x4_t row3,
119 int16x4_t row3,
204 int16x4_t row3 = vld1_s16(coef_block + 3 * DCTSIZE); in jsimd_idct_islow_neon() local
227 bitmap = vorr_s16(bitmap, row3); in jsimd_idct_islow_neon()
239 jsimd_idct_islow_pass1_sparse(row0, row1, row2, row3, quant_row0, in jsimd_idct_islow_neon()
244 jsimd_idct_islow_pass1_regular(row0, row1, row2, row3, row4, row5, in jsimd_idct_islow_neon()
257 row3 = vld1_s16(coef_block + 3 * DCTSIZE + 4); in jsimd_idct_islow_neon()
278 bitmap = vorr_s16(bitmap, row3); in jsimd_idct_islow_neon()
299 jsimd_idct_islow_pass1_sparse(row0, row1, row2, row3, quant_row0, in jsimd_idct_islow_neon()
304 jsimd_idct_islow_pass1_regular(row0, row1, row2, row3, row in jsimd_idct_islow_neon()
338 jsimd_idct_islow_pass1_regular(int16x4_t row0, int16x4_t row1, int16x4_t row2, int16x4_t row3, int16x4_t row4, int16x4_t row5, int16x4_t row6, int16x4_t row7, int16x4_t quant_row0, int16x4_t quant_row1, int16x4_t quant_row2, int16x4_t quant_row3, int16x4_t quant_row4, int16x4_t quant_row5, int16x4_t quant_row6, int16x4_t quant_row7, int16_t *workspace_1, int16_t *workspace_2) jsimd_idct_islow_pass1_regular() argument
473 jsimd_idct_islow_pass1_sparse(int16x4_t row0, int16x4_t row1, int16x4_t row2, int16x4_t row3, int16x4_t quant_row0, int16x4_t quant_row1, int16x4_t quant_row2, int16x4_t quant_row3, int16_t *workspace_1, int16_t *workspace_2) jsimd_idct_islow_pass1_sparse() argument
[all...]
H A Djfdctfst-neon.c155 int16x8_t row3 = vreinterpretq_s16_s32(rows_37.val[0]); in jsimd_fdct_ifast_neon() local
169 tmp3 = vaddq_s16(row3, row4); in jsimd_fdct_ifast_neon()
170 tmp4 = vsubq_s16(row3, row4); in jsimd_fdct_ifast_neon()
202 row3 = vsubq_s16(z13, z2); in jsimd_fdct_ifast_neon()
209 vst1q_s16(data + 3 * DCTSIZE, row3); in jsimd_fdct_ifast_neon()
H A Djidctfst-neon.c72 int16x8_t row3 = vld1q_s16(coef_block + 3 * DCTSIZE); in jsimd_idct_ifast_neon() local
85 bitmap = vorrq_s16(bitmap, row3); in jsimd_idct_ifast_neon()
104 row3 = dcval; in jsimd_idct_ifast_neon()
148 int16x4_t tmp5 = vmul_s16(vget_high_s16(row3), quant_row3); in jsimd_idct_ifast_neon()
183 row3 = vcombine_s16(dcval, vsub_s16(tmp3, tmp4)); in jsimd_idct_ifast_neon()
223 int16x4_t tmp5 = vmul_s16(vget_low_s16(row3), quant_row3); in jsimd_idct_ifast_neon()
258 row3 = vcombine_s16(vsub_s16(tmp3, tmp4), dcval); in jsimd_idct_ifast_neon()
293 int16x8_t tmp5 = vmulq_s16(row3, quant_row3); in jsimd_idct_ifast_neon()
328 row3 = vsubq_s16(tmp3, tmp4); in jsimd_idct_ifast_neon()
333 int16x8x2_t rows_23 = vtrnq_s16(row2, row3); in jsimd_idct_ifast_neon()
[all...]
H A Djfdctint-neon.c254 int16x8_t row3 = vreinterpretq_s16_s32(rows_37.val[0]); in jsimd_fdct_islow_neon() local
268 tmp3 = vaddq_s16(row3, row4); in jsimd_fdct_islow_neon()
269 tmp4 = vsubq_s16(row3, row4); in jsimd_fdct_islow_neon()
358 row3 = vcombine_s16(vrshrn_n_s32(tmp6_l, DESCALE_P2), in jsimd_fdct_islow_neon()
371 vst1q_s16(data + 3 * DCTSIZE, row3); in jsimd_fdct_islow_neon()
H A Djcphuff-neon.c201 int16x8_t row3 = vld1q_s16(values + 3 * DCTSIZE); in jsimd_encode_mcu_AC_first_prepare_neon() local
210 uint8x8_t row3_eq0 = vmovn_u16(vceqq_s16(row3, vdupq_n_s16(0))); in jsimd_encode_mcu_AC_first_prepare_neon()
/third_party/skia/third_party/externals/libjpeg-turbo/simd/arm/aarch32/
H A Djchuff-neon.c79 int16x8_t row3 = vld1q_dup_s16(block + 27); in jsimd_huff_encode_one_block_neon() local
80 row3 = vld1q_lane_s16(block + 20, row3, 1); in jsimd_huff_encode_one_block_neon()
81 row3 = vld1q_lane_s16(block + 13, row3, 2); in jsimd_huff_encode_one_block_neon()
82 row3 = vld1q_lane_s16(block + 6, row3, 3); in jsimd_huff_encode_one_block_neon()
83 row3 = vld1q_lane_s16(block + 7, row3, 4); in jsimd_huff_encode_one_block_neon()
84 row3 in jsimd_huff_encode_one_block_neon()
[all...]
/third_party/skia/third_party/externals/swiftshader/src/Pipeline/
H A DShaderCore.cpp472 void transpose4x4(Short4 &row0, Short4 &row1, Short4 &row2, Short4 &row3) in transpose4x4() argument
475 Int2 tmp1 = UnpackHigh(row2, row3); in transpose4x4()
477 Int2 tmp3 = UnpackLow(row2, row3); in transpose4x4()
482 row3 = UnpackHigh(tmp0, tmp1); in transpose4x4()
485 void transpose4x3(Short4 &row0, Short4 &row1, Short4 &row2, Short4 &row3) in transpose4x3() argument
488 Int2 tmp1 = UnpackHigh(row2, row3); in transpose4x3()
490 Int2 tmp3 = UnpackLow(row2, row3); in transpose4x3()
497 void transpose4x4(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) in transpose4x4() argument
500 Float4 tmp1 = UnpackLow(row2, row3); in transpose4x4()
502 Float4 tmp3 = UnpackHigh(row2, row3); in transpose4x4()
510 transpose4x3(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) transpose4x3() argument
522 transpose4x2(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) transpose4x2() argument
531 transpose4x1(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) transpose4x1() argument
539 transpose2x4(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) transpose2x4() argument
550 transpose4xN(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3, int N) transpose4xN() argument
[all...]
H A DShaderCore.hpp214 void transpose4x4(Short4 &row0, Short4 &row1, Short4 &row2, Short4 &row3);
215 void transpose4x3(Short4 &row0, Short4 &row1, Short4 &row2, Short4 &row3);
216 void transpose4x4(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
217 void transpose4x3(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
218 void transpose4x2(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
219 void transpose4x1(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
220 void transpose2x4(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
221 void transpose4xN(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3, int N);
/third_party/ffmpeg/libavcodec/mips/
H A Dvp8_lpf_msa.c380 v16u8 row0, row1, row2, row3, row4, row5, row6, row7, row8; in ff_vp8_h_loop_filter16_msa() local
388 LD_UB8(temp_src, pitch, row0, row1, row2, row3, row4, row5, row6, row7); in ff_vp8_h_loop_filter16_msa()
392 TRANSPOSE16x8_UB_UB(row0, row1, row2, row3, row4, row5, row6, row7, in ff_vp8_h_loop_filter16_msa()
445 v16u8 row0, row1, row2, row3, row4, row5, row6, row7, row8; in ff_vp8_h_loop_filter8uv_msa() local
453 LD_UB8(src_u - 4, pitch, row0, row1, row2, row3, row4, row5, row6, row7); in ff_vp8_h_loop_filter8uv_msa()
456 TRANSPOSE16x8_UB_UB(row0, row1, row2, row3, row4, row5, row6, row7, in ff_vp8_h_loop_filter8uv_msa()
525 v16u8 row0, row1, row2, row3, row4, row5, row6, row7, row8; in ff_vp8_h_loop_filter_simple_msa() local
531 LD_UB8(temp_src, pitch, row0, row1, row2, row3, row4, row5, row6, row7); in ff_vp8_h_loop_filter_simple_msa()
535 TRANSPOSE16x4_UB_UB(row0, row1, row2, row3, row4, row5, row6, row7, in ff_vp8_h_loop_filter_simple_msa()
595 v16u8 row0, row1, row2, row3, row in ff_vp8_h_loop_filter8uv_inner_msa() local
649 v16u8 row0, row1, row2, row3, row4, row5, row6, row7; ff_vp8_h_loop_filter16_inner_msa() local
[all...]
H A Dh264dsp_msa.c829 v16u8 row0, row1, row2, row3, row4, row5, row6, row7; in avc_loopfilter_luma_intra_edge_ver_msa() local
832 LD_UB8(src, img_width, row0, row1, row2, row3, row4, row5, row6, row7); in avc_loopfilter_luma_intra_edge_ver_msa()
836 TRANSPOSE16x8_UB_UB(row0, row1, row2, row3, in avc_loopfilter_luma_intra_edge_ver_msa()
1240 v16u8 row0, row1, row2, row3, row4, row5, row6, row7; in avc_loopfilter_cb_or_cr_intra_edge_ver_msa() local
1243 row0, row1, row2, row3, row4, row5, row6, row7); in avc_loopfilter_cb_or_cr_intra_edge_ver_msa()
1245 TRANSPOSE8x4_UB_UB(row0, row1, row2, row3, row4, row5, row6, row7, in avc_loopfilter_cb_or_cr_intra_edge_ver_msa()
1926 v16u8 row0, row1, row2, row3, row4, row5, row6, row7; in avc_loopfilter_cb_or_cr_inter_edge_ver_msa() local
1952 row0, row1, row2, row3, row4, row5, row6, row7); in avc_loopfilter_cb_or_cr_inter_edge_ver_msa()
1954 TRANSPOSE8x4_UB_UB(row0, row1, row2, row3, in avc_loopfilter_cb_or_cr_inter_edge_ver_msa()
/third_party/skia/third_party/externals/swiftshader/src/Shader/
H A DShaderCore.hpp87 void transpose4x4(Short4 &row0, Short4 &row1, Short4 &row2, Short4 &row3);
88 void transpose4x3(Short4 &row0, Short4 &row1, Short4 &row2, Short4 &row3);
89 void transpose4x4(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
90 void transpose4x3(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
91 void transpose4x2(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
92 void transpose4x1(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
93 void transpose2x4(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3);
94 void transpose4xN(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3, int N);
H A DShaderCore.cpp488 void transpose4x4(Short4 &row0, Short4 &row1, Short4 &row2, Short4 &row3) in transpose4x4() argument
491 Int2 tmp1 = UnpackHigh(row2, row3); in transpose4x4()
493 Int2 tmp3 = UnpackLow(row2, row3); in transpose4x4()
498 row3 = UnpackHigh(tmp0, tmp1); in transpose4x4()
501 void transpose4x3(Short4 &row0, Short4 &row1, Short4 &row2, Short4 &row3) in transpose4x3() argument
504 Int2 tmp1 = UnpackHigh(row2, row3); in transpose4x3()
506 Int2 tmp3 = UnpackLow(row2, row3); in transpose4x3()
513 void transpose4x4(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) in transpose4x4() argument
516 Float4 tmp1 = UnpackLow(row2, row3); in transpose4x4()
518 Float4 tmp3 = UnpackHigh(row2, row3); in transpose4x4()
526 transpose4x3(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) transpose4x3() argument
538 transpose4x2(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) transpose4x2() argument
547 transpose4x1(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) transpose4x1() argument
555 transpose2x4(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3) transpose2x4() argument
566 transpose4xN(Float4 &row0, Float4 &row1, Float4 &row2, Float4 &row3, int N) transpose4xN() argument
[all...]
/third_party/skia/gm/
H A Dhardstop_gradients.cpp117 SkScalar row3[] = {0.00f, 0.25f, 1.00f}; variable
127 row3,
/third_party/ffmpeg/libavcodec/loongarch/
H A Dh264dsp_lasx.c96 __m256i row0, row1, row2, row3, row4, row5, row6, row7; in ff_h264_h_lpf_luma_8_lasx() local
100 src, img_width_3x, row0, row1, row2, row3); in ff_h264_h_lpf_luma_8_lasx()
114 LASX_TRANSPOSE16x8_B(row0, row1, row2, row3, row4, row5, row6, in ff_h264_h_lpf_luma_8_lasx()
201 __m256i row0, row1, row2, row3, row4, row5, row6, row7; in ff_h264_h_lpf_luma_8_lasx() local
211 row1, row3); in ff_h264_h_lpf_luma_8_lasx()
212 DUP2_ARG2(__lasx_xvilvl_b, row2, row0, row3, row1, row4, row6); in ff_h264_h_lpf_luma_8_lasx()
213 DUP2_ARG2(__lasx_xvilvh_b, row2, row0, row3, row1, row5, row7); in ff_h264_h_lpf_luma_8_lasx()
393 __m256i row0, row1, row2, row3, row4, row5, row6, row7; in ff_h264_h_lpf_chroma_8_lasx() local
396 src, img_width_3x, row0, row1, row2, row3); in ff_h264_h_lpf_chroma_8_lasx()
402 DUP4_ARG2(__lasx_xvilvl_b, row2, row0, row3, row in ff_h264_h_lpf_chroma_8_lasx()
597 __m256i row0, row1, row2, row3, row4, row5, row6, row7; ff_h264_h_lpf_luma_intra_8_lasx() local
717 __m256i row0, row1, row2, row3, row4, row5, row6, row7; ff_h264_h_lpf_luma_intra_8_lasx() local
892 __m256i row0, row1, row2, row3, row4, row5, row6, row7; ff_h264_h_lpf_chroma_intra_8_lasx() local
[all...]
H A Dvp8_lpf_lsx.c335 __m128i row0, row1, row2, row3, row4, row5, row6, row7, row8; in ff_vp8_h_loop_filter16_lsx() local
349 temp_src + stride3, 0, row0, row1, row2, row3); in ff_vp8_h_loop_filter16_lsx()
360 LSX_TRANSPOSE16x8_B(row0, row1, row2, row3, row4, row5, row6, row7, row8, row9, row10, in ff_vp8_h_loop_filter16_lsx()
422 __m128i row0, row1, row2, row3, row4, row5, row6, row7, row8; in ff_vp8_h_loop_filter8uv_lsx() local
436 temp_src + stride3, 0, row0, row1, row2, row3); in ff_vp8_h_loop_filter8uv_lsx()
448 LSX_TRANSPOSE16x8_B(row0, row1, row2, row3, row4, row5, row6, row7, in ff_vp8_h_loop_filter8uv_lsx()
/third_party/skia/third_party/externals/libwebp/src/dsp/
H A Ddec_msa.c364 v16u8 row0, row1, row2, row3, row4, row5, row6, row7, row8; in HFilter16() local
371 LD_UB8(ptmp, stride, row0, row1, row2, row3, row4, row5, row6, row7); in HFilter16()
374 TRANSPOSE16x8_UB_UB(row0, row1, row2, row3, row4, row5, row6, row7, in HFilter16()
446 v16u8 row0, row1, row2, row3, row4, row5, row6, row7; in HFilterVertEdge16i() local
453 LD_UB8(src - 4, stride, row0, row1, row2, row3, row4, row5, row6, row7); in HFilterVertEdge16i()
456 TRANSPOSE16x8_UB_UB(row0, row1, row2, row3, row4, row5, row6, row7, in HFilterVertEdge16i()
530 v16u8 row0, row1, row2, row3, row4, row5, row6, row7, row8; in HFilter8() local
537 LD_UB8(ptmp_src_u, stride, row0, row1, row2, row3, row4, row5, row6, row7); in HFilter8()
540 TRANSPOSE16x8_UB_UB(row0, row1, row2, row3, row4, row5, row6, row7, in HFilter8()
595 v16u8 row0, row1, row2, row3, row in HFilter8i() local
636 v16u8 p1, p0, q1, q0, mask, row0, row1, row2, row3, row4, row5, row6, row7; SimpleHFilter16() local
[all...]
H A Denc_sse2.c406 __m128i row0, row1, row2, row3; in FTransformWHT_SSE2() local
411 FTransformWHTRow_SSE2(in + 3 * 64, &row3); in FTransformWHT_SSE2()
416 const __m128i a1 = _mm_add_epi32(row1, row3); in FTransformWHT_SSE2()
417 const __m128i a2 = _mm_sub_epi32(row1, row3); in FTransformWHT_SSE2()
/third_party/skia/third_party/externals/d3d12allocator/src/
H A DCommon.h186 const vec4& row3, in mat4()
190 _31(row3.x), _32(row3.y), _33(row3.z), _34(row3.w), in mat4()
/third_party/skia/third_party/externals/libjpeg-turbo/simd/arm/aarch64/
H A Djchuff-neon.c127 int16x8_t row3 = in jsimd_huff_encode_one_block_neon() local
164 int16x8_t abs_row3 = vabsq_s16(row3); in jsimd_huff_encode_one_block_neon()
178 vreinterpretq_u16_s16(veorq_s16(abs_row3, vshrq_n_s16(row3, 15))); in jsimd_huff_encode_one_block_neon()
/third_party/skia/third_party/externals/swiftshader/third_party/llvm-10.0/llvm/lib/MC/
H A DMCWin64EH.cpp611 uint32_t row3 = EpilogOffset; in ARM64EmitUnwindInfo() local
612 row3 |= (EpilogIndex & 0x3FF) << 22; in ARM64EmitUnwindInfo()
613 streamer.EmitIntValue(row3, 4); in ARM64EmitUnwindInfo()
/third_party/astc-encoder/Source/
H A Dstb_image.h2531 __m128i row0, row1, row2, row3, row4, row5, row6, row7; in stbi__idct_simd() local
2598 dct_rot(y0o,y2o, row7,row3, rot2_0,rot2_1); \ in stbi__idct_simd()
2601 __m128i sum35 = _mm_add_epi16(row3, row5); \ in stbi__idct_simd()
2610 dct_bfly32o(row3,row4, x3,x4,bias,shift); \ in stbi__idct_simd()
2630 row3 = _mm_load_si128((const __m128i *) (data + 3*8)); in stbi__idct_simd()
2644 dct_interleave16(row3, row7); in stbi__idct_simd()
2648 dct_interleave16(row1, row3); in stbi__idct_simd()
2654 dct_interleave16(row2, row3); in stbi__idct_simd()
2665 __m128i p1 = _mm_packus_epi16(row2, row3); in stbi__idct_simd()
2711 int16x8_t row0, row1, row2, row3, row in stbi__idct_simd() local
[all...]

Completed in 38 milliseconds

12