/external/libaom/libaom/aom_dsp/x86/ |
D | quantize_ssse3_x86_64.asm | 37 pcmpeqw m5, m5 38 psrlw m5, 15 39 paddw m0, m5 40 paddw m1, m5 51 pxor m5, m5 ; m5 = dedicated zero 79 pmullw m5, m8, m4 ; store the lower 16 bits of m8*qsh 84 psrlw m5, 15 85 por m8, m5 89 pmullw m5, m13, m4 ; store the lower 16 bits of m13*qsh 94 psrlw m5, 15 [all …]
|
D | highbd_sad_sse2.asm | 77 mova m5, [srcq] 78 psubusw m5, m1 80 por m1, m5 81 mova m5, [srcq+16] 82 psubusw m5, m2 84 por m2, m5 85 mova m5, [srcq+32] 86 psubusw m5, m3 88 por m3, m5 89 mova m5, [srcq+48] [all …]
|
D | fwd_txfm_ssse3_x86_64.asm | 64 mova m5, [inputq + r3] 75 psllw m5, 2 87 paddw m7, m2, m5 88 psubw m2, m5 94 paddw m5, m9, m7 104 paddw m6, m4, m5 105 psubw m4, m5 113 pmaddwd m5, m2, [GLOBAL(pw_15137_6270)] 117 paddd m5, m8 121 psrad m5, 14 [all …]
|
D | subpel_variance_sse2.asm | 69 pcmpgtw m5, m6 ; mask for 0 > x 71 punpcklwd m4, m6, m5 72 punpckhwd m6, m5 ; sign-extend m6 word->dword 89 pcmpgtw m5, m6 ; mask for 0 > x 91 punpcklwd m6, m5 ; sign-extend m6 word->dword 401 punpckhbw m2, m0, m5 402 punpckhbw m3, m4, m5 403 punpcklbw m0, m5 404 punpcklbw m4, m5 425 punpckhbw m2, m0, m5 [all …]
|
D | aom_subpixel_8t_ssse3.asm | 120 movu m5, [srcq + sstrideq - 3] 123 punpckhbw m3, m5, m5 124 punpcklbw m5, m5 129 palignr m2, m3, m5, 1 131 palignr m3, m5, 5 135 punpckhqdq m5, m1, m3 138 paddsw m1, m5 141 movd m5, [dstq + dstrideq] 149 movu m5, [srcq + sstrideq] 150 punpckldq m4, m5 ; Bytes 0,1,2,3 from row 0, then 0,1,2,3 from row 2 [all …]
|
D | sad4d_sse2.asm | 25 movd m5, [ref4q+%3] 35 punpckldq m5, m3 38 movlhps m7, m5 43 movd m5, [ref1q+%5] 46 punpckldq m1, m5 49 movd m5, [ref3q+%5] 50 punpckldq m3, m5 52 movd m5, [ref4q+%5] 53 punpckldq m4, m5 54 movd m5, [srcq +%4] [all …]
|
D | quantize_avx_x86_64.asm | 53 pxor m5, m5 ; m5 = dedicated zero 114 pcmpgtw m6, m5, m8 119 pcmpgtw m6, m5, m13 130 pcmpgtw m6, m5, m8 135 pcmpgtw m6, m5, m13 144 pcmpeqw m8, m8, m5 ; m8 = c[i] == 0 145 pcmpeqw m13, m13, m5 ; m13 = c[i] == 0 201 pxor m5, m5 ; m5 = dedicated zero 256 pmullw m5, m8, m4 ; store the lower 16 bits of m8*qsh 261 psrlw m5, 15 [all …]
|
D | highbd_subpel_variance_impl_sse2.asm | 231 movu m5, [srcq+src_strideq*2+16] 235 pavgw m1, m5 250 movu m5, [srcq+src_strideq*4] 254 pavgw m1, m5 307 movu m5, [srcq+src_strideq*2+16] 316 pmullw m5, filter_y_b 321 paddw m1, m5 339 movu m5, [srcq+src_strideq*4] 344 pmullw m5, filter_y_b 349 paddw m1, m5 [all …]
|
D | highbd_sad4d_sse2.asm | 23 movu m5, [ref2q+%3*2] 28 movhps m5, [ref2q+%5*2] 34 psubusw m2, m5 36 psubusw m5, m0 38 por m5, m2 40 pmaddwd m5, m1 69 paddd m5, m2 104 movu m5, [ref2q+%3*2] 110 psubusw m2, m5 112 psubusw m5, m0 [all …]
|
/external/libvpx/libvpx/vpx_dsp/x86/ |
D | highbd_sad_sse2.asm | 74 mova m5, [srcq] 75 psubusw m5, m1 77 por m1, m5 78 mova m5, [srcq+16] 79 psubusw m5, m2 81 por m2, m5 82 mova m5, [srcq+32] 83 psubusw m5, m3 85 por m3, m5 86 mova m5, [srcq+48] [all …]
|
D | fwd_txfm_ssse3_x86_64.asm | 46 mova m5, [inputq + r3] 57 psllw m5, 2 69 paddw m7, m2, m5 70 psubw m2, m5 76 paddw m5, m9, m7 86 paddw m6, m4, m5 87 psubw m4, m5 95 pmaddwd m5, m2, [GLOBAL(pw_15137_6270)] 99 paddd m5, m8 103 psrad m5, 14 [all …]
|
D | subpel_variance_sse2.asm | 66 pcmpgtw m5, m6 ; mask for 0 > x 68 punpcklwd m4, m6, m5 69 punpckhwd m6, m5 ; sign-extend m6 word->dword 86 pcmpgtw m5, m6 ; mask for 0 > x 88 punpcklwd m6, m5 ; sign-extend m6 word->dword 398 punpckhbw m2, m0, m5 399 punpckhbw m3, m4, m5 400 punpcklbw m0, m5 401 punpcklbw m4, m5 422 punpckhbw m2, m0, m5 [all …]
|
D | sad4d_sse2.asm | 22 movd m5, [ref4q+%3] 32 punpckldq m5, m3 35 movlhps m7, m5 40 movd m5, [ref1q+%5] 43 punpckldq m1, m5 46 movd m5, [ref3q+%5] 47 punpckldq m3, m5 49 movd m5, [ref4q+%5] 50 punpckldq m4, m5 51 movd m5, [srcq +%4] [all …]
|
D | highbd_subpel_variance_impl_sse2.asm | 228 movu m5, [srcq+src_strideq*2+16] 232 pavgw m1, m5 247 movu m5, [srcq+src_strideq*4] 251 pavgw m1, m5 304 movu m5, [srcq+src_strideq*2+16] 313 pmullw m5, filter_y_b 318 paddw m1, m5 336 movu m5, [srcq+src_strideq*4] 341 pmullw m5, filter_y_b 346 paddw m1, m5 [all …]
|
D | vpx_subpixel_8t_ssse3.asm | 116 movu m5, [srcq + sstrideq - 3] 119 punpckhbw m3, m5, m5 120 punpcklbw m5, m5 125 palignr m2, m3, m5, 1 127 palignr m3, m5, 5 131 punpckhqdq m5, m1, m3 134 paddsw m1, m5 137 movd m5, [dstq + dstrideq] 147 pavgb m1, m5 202 palignr m5, m1, m0, 13 [all …]
|
D | intrapred_ssse3.asm | 98 palignr m5, m4, m0, 1 108 pavgb m5, m3 113 mova [dstq ], m5 116 palignr m3, m4, m5, 1 121 palignr m5, m4, m3, 1 123 mova [dstq +strideq*2 ], m5 126 palignr m3, m4, m5, 1 131 palignr m5, m4, m3, 1 281 palignr m5, m7, m0, 2 284 X_PLUS_2Y_PLUS_Z_PLUS_2_RSH_2 m0, m6, m5, m2 [all …]
|
D | highbd_intrapred_sse2.asm | 133 mova m5, [leftq+32] 136 paddw m5, m6 138 paddw m2, m5 275 pshuflw m5, m1, 0x55 276 movlhps m2, m5 ; l1 l1 l1 l1 l2 l2 l2 l2 286 pshuflw m5, m1, 0xff 287 movlhps m2, m5 352 pcmpeqw m5, m5 354 pxor m3, m5 ; max possible value 361 pshuflw m5, m7, 0x0 [all …]
|
D | highbd_sad4d_sse2.asm | 20 movu m5, [ref2q+%3*2] 25 movhps m5, [ref2q+%5*2] 31 psubusw m2, m5 33 psubusw m5, m0 35 por m5, m2 37 pmaddwd m5, m1 66 paddd m5, m2 101 movu m5, [ref2q+%3*2] 107 psubusw m2, m5 109 psubusw m5, m0 [all …]
|
/external/python/cpython3/Modules/_blake2/impl/ |
D | blake2b-load-sse41.h | 38 b0 = _mm_unpacklo_epi64(m4, m5); \ 46 b0 = _mm_unpackhi_epi64(m4, m5); \ 62 b0 = _mm_unpacklo_epi64(m5, m4); \ 71 b1 = _mm_unpackhi_epi64(m5, m2); \ 86 b0 = _mm_alignr_epi8(m6, m5, 8); \ 102 b0 = _mm_blend_epi16(m5, m1, 0xF0); \ 119 b1 = _mm_unpackhi_epi64(m6, m5); \ 142 b0 = _mm_unpacklo_epi64(m3, m5); \ 151 b1 = _mm_unpacklo_epi64(m1, m5); \ 166 b0 = _mm_blend_epi16(m7, m5, 0xF0); \ [all …]
|
D | blake2s-load-sse2.h | 20 #define LOAD_MSG_0_2(buf) buf = _mm_set_epi32(m7,m5,m3,m1) 25 #define LOAD_MSG_1_3(buf) buf = _mm_set_epi32(m5,m11,m0,m1) 27 #define LOAD_MSG_2_1(buf) buf = _mm_set_epi32(m15,m5,m12,m11) 33 #define LOAD_MSG_3_3(buf) buf = _mm_set_epi32(m15,m4,m5,m2) 35 #define LOAD_MSG_4_1(buf) buf = _mm_set_epi32(m10,m2,m5,m9) 42 #define LOAD_MSG_5_4(buf) buf = _mm_set_epi32(m9,m14,m5,m13) 44 #define LOAD_MSG_6_2(buf) buf = _mm_set_epi32(m10,m13,m15,m5) 49 #define LOAD_MSG_7_3(buf) buf = _mm_set_epi32(m2,m8,m15,m5) 54 #define LOAD_MSG_8_4(buf) buf = _mm_set_epi32(m5,m4,m7,m2) 56 #define LOAD_MSG_9_2(buf) buf = _mm_set_epi32(m5,m6,m4,m2)
|
D | blake2b-load-sse2.h | 20 #define LOAD_MSG_0_2(b0, b1) b0 = _mm_set_epi64x(m3, m1); b1 = _mm_set_epi64x(m7, m5) 25 #define LOAD_MSG_1_3(b0, b1) b0 = _mm_set_epi64x(m0, m1); b1 = _mm_set_epi64x(m5, m11) 27 #define LOAD_MSG_2_1(b0, b1) b0 = _mm_set_epi64x(m12, m11); b1 = _mm_set_epi64x(m15, m5) 33 #define LOAD_MSG_3_3(b0, b1) b0 = _mm_set_epi64x(m5, m2); b1 = _mm_set_epi64x(m15, m4) 35 #define LOAD_MSG_4_1(b0, b1) b0 = _mm_set_epi64x(m5, m9); b1 = _mm_set_epi64x(m10, m2) 42 #define LOAD_MSG_5_4(b0, b1) b0 = _mm_set_epi64x(m5, m13); b1 = _mm_set_epi64x(m9, m14) 44 #define LOAD_MSG_6_2(b0, b1) b0 = _mm_set_epi64x(m15, m5); b1 = _mm_set_epi64x(m10, m13) 49 #define LOAD_MSG_7_3(b0, b1) b0 = _mm_set_epi64x(m15, m5); b1 = _mm_set_epi64x(m2, m8) 54 #define LOAD_MSG_8_4(b0, b1) b0 = _mm_set_epi64x(m7, m2); b1 = _mm_set_epi64x(m5, m4) 56 #define LOAD_MSG_9_2(b0, b1) b0 = _mm_set_epi64x(m4, m2); b1 = _mm_set_epi64x(m5, m6) [all …]
|
/external/libvpx/libvpx/vp9/encoder/x86/ |
D | vp9_error_sse2.asm | 25 pxor m5, m5 ; dedicated zero register 46 punpckldq m7, m0, m5 47 punpckhdq m0, m5 49 punpckldq m7, m2, m5 51 punpckhdq m2, m5 57 movhlps m5, m4 59 paddq m4, m5 66 pshufd m5, m4, 0x1 69 movd edx, m5 81 pxor m5, m5 ; dedicated zero register [all …]
|
/external/libaom/libaom/av1/encoder/x86/ |
D | error_sse2.asm | 27 pxor m5, m5 ; dedicated zero register 45 punpckldq m7, m0, m5 46 punpckhdq m0, m5 48 punpckldq m7, m1, m5 50 punpckhdq m1, m5 52 punpckldq m7, m2, m5 54 punpckhdq m2, m5 56 punpckldq m7, m3, m5 58 punpckhdq m3, m5 65 movhlps m5, m4 [all …]
|
D | av1_quantize_ssse3_x86_64.asm | 40 pcmpeqw m5, m5 41 psrlw m5, 15 42 paddw m1, m5 52 pxor m5, m5 ; m5 = dedicated zero 95 pcmpeqw m8, m5 ; m8 = c[i] == 0 96 pcmpeqw m13, m5 ; m13 = c[i] == 0 145 pcmpeqw m14, m5 ; m14 = c[i] == 0 146 pcmpeqw m13, m5 ; m13 = c[i] == 0 160 mova [r3q+ncoeffq*2+ 0], m5 161 mova [r3q+ncoeffq*2+16], m5 [all …]
|
/external/mesa3d/src/mesa/math/ |
D | m_xform_tmp.h | 249 const GLfloat m1 = m[1], m5 = m[5], m13 = m[13]; in TAG() local 256 to[i][1] = m1 * ox + m5 * oy + m13; in TAG() 295 const GLfloat m0 = m[0], m1 = m[1], m4 = m[4], m5 = m[5]; in TAG() local 301 to[i][1] = m1 * ox + m5 * oy + m13; in TAG() 317 const GLfloat m0 = m[0], m5 = m[5], m12 = m[12], m13 = m[13]; in TAG() local 322 to[i][1] = m5 * oy + m13; in TAG() 338 const GLfloat m0 = m[0], m1 = m[1], m2 = m[2], m4 = m[4], m5 = m[5]; in TAG() local 344 to[i][1] = m1 * ox + m5 * oy + m13; in TAG() 365 const GLfloat m0 = m[0], m5 = m[5]; in TAG() local 371 to[i][1] = m5 * oy + m13; in TAG() [all …]
|