/external/boringssl/src/crypto/poly1305/ |
D | poly1305_vec.c | 194 p->S21.v = _mm_mul_epu32(p->R21.v, FIVE); in poly1305_first_block() 195 p->S22.v = _mm_mul_epu32(p->R22.v, FIVE); in poly1305_first_block() 196 p->S23.v = _mm_mul_epu32(p->R23.v, FIVE); in poly1305_first_block() 197 p->S24.v = _mm_mul_epu32(p->R24.v, FIVE); in poly1305_first_block() 248 T0 = _mm_mul_epu32(H0, p->R20.v); in poly1305_blocks() 249 T1 = _mm_mul_epu32(H0, p->R21.v); in poly1305_blocks() 250 T2 = _mm_mul_epu32(H0, p->R22.v); in poly1305_blocks() 251 T3 = _mm_mul_epu32(H0, p->R23.v); in poly1305_blocks() 252 T4 = _mm_mul_epu32(H0, p->R24.v); in poly1305_blocks() 253 T5 = _mm_mul_epu32(H1, p->S24.v); in poly1305_blocks() [all …]
|
/external/libvpx/libvpx/vpx_dsp/x86/ |
D | highbd_idct4x4_add_sse2.c | 43 temp1[0] = _mm_mul_epu32(temp1[0], cospi_p16_p16); // ([0] + [2])*cospi_16_64 in highbd_idct4_small_sse2() 44 temp1[1] = _mm_mul_epu32(temp1[1], cospi_p16_p16); // ([0] + [2])*cospi_16_64 in highbd_idct4_small_sse2() 45 temp2[0] = _mm_mul_epu32(temp2[0], cospi_p16_p16); // ([0] - [2])*cospi_16_64 in highbd_idct4_small_sse2() 46 temp2[1] = _mm_mul_epu32(temp2[1], cospi_p16_p16); // ([0] - [2])*cospi_16_64 in highbd_idct4_small_sse2() 52 temp1[0] = _mm_mul_epu32(io[1], cospi_p24_p24); // input[1] * cospi_24_64 in highbd_idct4_small_sse2() 53 temp1[1] = _mm_mul_epu32(temp1[3], cospi_p24_p24); // input[1] * cospi_24_64 in highbd_idct4_small_sse2() 54 temp2[0] = _mm_mul_epu32(io[1], cospi_p08_p08); // input[1] * cospi_8_64 in highbd_idct4_small_sse2() 55 temp2[1] = _mm_mul_epu32(temp1[3], cospi_p08_p08); // input[1] * cospi_8_64 in highbd_idct4_small_sse2() 56 temp1[2] = _mm_mul_epu32(io[3], cospi_p08_p08); // input[3] * cospi_8_64 in highbd_idct4_small_sse2() 57 temp1[3] = _mm_mul_epu32(temp2[3], cospi_p08_p08); // input[3] * cospi_8_64 in highbd_idct4_small_sse2() [all …]
|
D | fwd_txfm_sse2.h | 23 buf0 = _mm_mul_epu32(a, b); in k_madd_epi32() 26 buf1 = _mm_mul_epu32(a, b); in k_madd_epi32()
|
D | highbd_inv_txfm_sse2.h | 80 __m128i out = _mm_mul_epu32(in, cospi); in multiply_apply_sign_sse2()
|
/external/flac/libFLAC/ |
D | lpc_intrin_sse2.c | 443 …xmm7 = _mm_mul_epu32(xmm7, xmm5); /* we use _unsigned_ multiplication and discard high dword of th… in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 449 xmm6 = _mm_mul_epu32(xmm6, xmm4); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 456 xmm6 = _mm_mul_epu32(xmm6, xmm3); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 463 xmm6 = _mm_mul_epu32(xmm6, xmm2); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 470 xmm6 = _mm_mul_epu32(xmm6, xmm1); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 477 xmm6 = _mm_mul_epu32(xmm6, xmm0); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 503 xmm7 = _mm_mul_epu32(xmm7, xmm5); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 509 xmm6 = _mm_mul_epu32(xmm6, xmm4); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 516 xmm6 = _mm_mul_epu32(xmm6, xmm3); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() 523 xmm6 = _mm_mul_epu32(xmm6, xmm2); in FLAC__lpc_compute_residual_from_qlp_coefficients_intrin_sse2() [all …]
|
/external/webp/src/dsp/ |
D | rescaler_sse2.c | 153 const __m128i D1 = _mm_mul_epu32(frac, mult1); // 32b x 16b -> 64b in RescalerImportRowShrink_SSE2() 154 const __m128i D2 = _mm_mul_epu32(D0, mult1); in RescalerImportRowShrink_SSE2() 182 *out0 = _mm_mul_epu32(A0, *mult); in LoadDispatchAndMult_SSE2() 183 *out1 = _mm_mul_epu32(A1, *mult); in LoadDispatchAndMult_SSE2() 184 *out2 = _mm_mul_epu32(A2, *mult); in LoadDispatchAndMult_SSE2() 185 *out3 = _mm_mul_epu32(A3, *mult); in LoadDispatchAndMult_SSE2() 202 const __m128i B0 = _mm_mul_epu32(*A0, *mult); in ProcessRow_SSE2() 203 const __m128i B1 = _mm_mul_epu32(*A1, *mult); in ProcessRow_SSE2() 204 const __m128i B2 = _mm_mul_epu32(*A2, *mult); in ProcessRow_SSE2() 205 const __m128i B3 = _mm_mul_epu32(*A3, *mult); in ProcessRow_SSE2()
|
/external/mesa3d/src/gallium/auxiliary/util/ |
D | u_sse.h | 198 mul02 = _mm_mul_epu32(a, b); in mm_mullohi_epi32() 199 mul13 = _mm_mul_epu32(a13, b13); in mm_mullohi_epi32() 221 __m128i ba = _mm_mul_epu32(b, a); /* multply dwords 0, 2 */ in mm_mullo_epi32() 222 __m128i b4a4 = _mm_mul_epu32(b4, a4); /* multiply dwords 1, 3 */ in mm_mullo_epi32()
|
/external/libaom/libaom/aom_dsp/x86/ |
D | fwd_txfm_sse2.h | 21 buf0 = _mm_mul_epu32(a, b); in k_madd_epi32() 24 buf1 = _mm_mul_epu32(a, b); in k_madd_epi32()
|
/external/skia/include/private/ |
D | SkNx_sse.h | 236 __m128i mul20 = _mm_mul_epu32(a, b), in mullo32() 237 mul31 = _mm_mul_epu32(_mm_srli_si128(a, 4), _mm_srli_si128(b, 4)); in mullo32() 404 SkNx v20{_mm_mul_epu32(m.fVec, fVec)}; in mulHi() 405 SkNx v31{_mm_mul_epu32(_mm_srli_si128(m.fVec, 4), _mm_srli_si128(fVec, 4))}; in mulHi()
|
/external/skqp/include/private/ |
D | SkNx_sse.h | 236 __m128i mul20 = _mm_mul_epu32(a, b), in mullo32() 237 mul31 = _mm_mul_epu32(_mm_srli_si128(a, 4), _mm_srli_si128(b, 4)); in mullo32() 404 SkNx v20{_mm_mul_epu32(m.fVec, fVec)}; in mulHi() 405 SkNx v31{_mm_mul_epu32(_mm_srli_si128(m.fVec, 4), _mm_srli_si128(fVec, 4))}; in mulHi()
|
/external/libaom/libaom/aom_dsp/simd/ |
D | v64_intrinsics_x86.h | 366 _mm_mul_epu32(a, b), in v64_mullo_s32() 367 _mm_mul_epu32(_mm_srli_si128(a, 4), _mm_srli_si128(b, 4))); in v64_mullo_s32()
|
D | v128_intrinsics_x86.h | 408 _mm_shuffle_epi32(_mm_mul_epu32(a, b), 8), in v128_mullo_s32() 410 _mm_mul_epu32(_mm_srli_si128(a, 4), _mm_srli_si128(b, 4)), 8)); in v128_mullo_s32()
|
/external/libaom/libaom/av1/encoder/x86/ |
D | highbd_temporal_filter_sse4.c | 85 const __m128i mul_lo = _mm_mul_epu32(sum_lo, const_lo); in highbd_average_4() 87 const __m128i mul_hi = _mm_mul_epu32(sum_hi, const_hi); in highbd_average_4()
|
/external/eigen/Eigen/src/Core/arch/SSE/ |
D | PacketMath.h | 235 _mm_mul_epu32(a,b), 236 _mm_mul_epu32(vec4i_swizzle1(a,1,0,3,2),
|
/external/clang/test/CodeGen/ |
D | sse2-builtins.c | 812 return _mm_mul_epu32(A, B); in test_mm_mul_epu32()
|
/external/libopus/ |
D | configure.ac | 570 mtest = _mm_mul_epu32(mtest, mtest);
|
/external/clang/lib/Headers/ |
D | emmintrin.h | 812 _mm_mul_epu32(__m128i __a, __m128i __b) in _mm_mul_epu32() function
|
/external/neon_2_sse/ |
D | NEON_2_SSE.h | 2698 …mul_us = _mm_mul_epu32 (a_neg, b_neg); //uses 0 and 2nd data lanes, (abs), the multiplication give… in _MM_MUL_EPI32() 3760 …return _mm_mul_epu32 (ab, ba); //uses 1rst and 3rd data lanes, the multiplication gives 64 bit res… in vmull_u32()
|