| /external/boringssl/src/crypto/poly1305/ |
| poly1305_vec.c | 194 p->S21.v = _mm_mul_epu32(p->R21.v, FIVE);
195 p->S22.v = _mm_mul_epu32(p->R22.v, FIVE);
196 p->S23.v = _mm_mul_epu32(p->R23.v, FIVE);
197 p->S24.v = _mm_mul_epu32(p->R24.v, FIVE);
248 T0 = _mm_mul_epu32(H0, p->R20.v);
249 T1 = _mm_mul_epu32(H0, p->R21.v);
250 T2 = _mm_mul_epu32(H0, p->R22.v);
251 T3 = _mm_mul_epu32(H0, p->R23.v);
252 T4 = _mm_mul_epu32(H0, p->R24.v);
253 T5 = _mm_mul_epu32(H1, p->S24.v)
[all...] |
| /external/libvpx/libvpx/vpx_dsp/x86/ |
| highbd_idct4x4_add_sse2.c | 35 // _mm_mul_epu32() is used which can only guarantee the lower 32-bit
43 temp1[0] = _mm_mul_epu32(temp1[0], cospi_p16_p16); // ([0] + [2])*cospi_16_64
44 temp1[1] = _mm_mul_epu32(temp1[1], cospi_p16_p16); // ([0] + [2])*cospi_16_64
45 temp2[0] = _mm_mul_epu32(temp2[0], cospi_p16_p16); // ([0] - [2])*cospi_16_64
46 temp2[1] = _mm_mul_epu32(temp2[1], cospi_p16_p16); // ([0] - [2])*cospi_16_64
52 temp1[0] = _mm_mul_epu32(io[1], cospi_p24_p24); // input[1] * cospi_24_64
53 temp1[1] = _mm_mul_epu32(temp1[3], cospi_p24_p24); // input[1] * cospi_24_64
54 temp2[0] = _mm_mul_epu32(io[1], cospi_p08_p08); // input[1] * cospi_8_64
55 temp2[1] = _mm_mul_epu32(temp1[3], cospi_p08_p08); // input[1] * cospi_8_64
56 temp1[2] = _mm_mul_epu32(io[3], cospi_p08_p08); // input[3] * cospi_8_6
[all...] |
| fwd_txfm_sse2.h | 23 buf0 = _mm_mul_epu32(a, b);
26 buf1 = _mm_mul_epu32(a, b);
|
| highbd_inv_txfm_sse2.h | 76 __m128i out = _mm_mul_epu32(in, cospi);
|
| /external/flac/libFLAC/ |
| lpc_intrin_sse2.c | 443 xmm7 = _mm_mul_epu32(xmm7, xmm5); /* we use _unsigned_ multiplication and discard high dword of the result values */
449 xmm6 = _mm_mul_epu32(xmm6, xmm4);
456 xmm6 = _mm_mul_epu32(xmm6, xmm3);
463 xmm6 = _mm_mul_epu32(xmm6, xmm2);
470 xmm6 = _mm_mul_epu32(xmm6, xmm1);
477 xmm6 = _mm_mul_epu32(xmm6, xmm0);
503 xmm7 = _mm_mul_epu32(xmm7, xmm5);
509 xmm6 = _mm_mul_epu32(xmm6, xmm4);
516 xmm6 = _mm_mul_epu32(xmm6, xmm3);
523 xmm6 = _mm_mul_epu32(xmm6, xmm2)
[all...] |
| /external/mesa3d/src/gallium/auxiliary/util/ |
| u_sse.h | 171 * _mm_mul_epu32().
198 mul02 = _mm_mul_epu32(a, b);
199 mul13 = _mm_mul_epu32(a13, b13);
208 * _mm_mul_epu32().
221 __m128i ba = _mm_mul_epu32(b, a); /* multply dwords 0, 2 */
222 __m128i b4a4 = _mm_mul_epu32(b4, a4); /* multiply dwords 1, 3 */
|
| /external/webp/src/dsp/ |
| rescaler_sse2.c | 154 const __m128i D1 = _mm_mul_epu32(frac, mult1); // 32b x 16b -> 64b
155 const __m128i D2 = _mm_mul_epu32(D0, mult1);
183 *out0 = _mm_mul_epu32(A0, *mult);
184 *out1 = _mm_mul_epu32(A1, *mult);
185 *out2 = _mm_mul_epu32(A2, *mult);
186 *out3 = _mm_mul_epu32(A3, *mult);
203 const __m128i B0 = _mm_mul_epu32(*A0, *mult);
204 const __m128i B1 = _mm_mul_epu32(*A1, *mult);
205 const __m128i B2 = _mm_mul_epu32(*A2, *mult);
206 const __m128i B3 = _mm_mul_epu32(*A3, *mult)
[all...] |
| /external/skia/src/opts/ |
| SkColor_opts_SSE2.h | 21 __m128i r1 = _mm_mul_epu32(a, b);
23 __m128i r2 = _mm_mul_epu32(_mm_srli_si128(a, 4), _mm_srli_si128(b, 4));
|
| SkNx_sse.h | 193 __m128i mul20 = _mm_mul_epu32(a, b),
194 mul31 = _mm_mul_epu32(_mm_srli_si128(a, 4), _mm_srli_si128(b, 4));
312 SkNx v20{_mm_mul_epu32(m.fVec, fVec)};
313 SkNx v31{_mm_mul_epu32(_mm_srli_si128(m.fVec, 4), _mm_srli_si128(fVec, 4))};
|
| /external/skqp/src/opts/ |
| SkColor_opts_SSE2.h | 21 __m128i r1 = _mm_mul_epu32(a, b);
23 __m128i r2 = _mm_mul_epu32(_mm_srli_si128(a, 4), _mm_srli_si128(b, 4));
|
| SkNx_sse.h | 186 __m128i mul20 = _mm_mul_epu32(a, b),
187 mul31 = _mm_mul_epu32(_mm_srli_si128(a, 4), _mm_srli_si128(b, 4));
305 SkNx v20{_mm_mul_epu32(m.fVec, fVec)};
306 SkNx v31{_mm_mul_epu32(_mm_srli_si128(m.fVec, 4), _mm_srli_si128(fVec, 4))};
|
| /external/eigen/Eigen/src/Core/arch/SSE/ |
| PacketMath.h | 235 _mm_mul_epu32(a,b),
236 _mm_mul_epu32(vec4i_swizzle1(a,1,0,3,2),
605 // TODO try to call _mm_mul_epu32 directly
[all...] |
| /external/clang/test/CodeGen/ |
| sse2-builtins.c | 812 return _mm_mul_epu32(A, B);
[all...] |
| /frameworks/rs/cpu_ref/ |
| rsCpuIntrinsics_x86.cpp | 57 __m128i even = _mm_mul_epu32(x, y);
58 __m128i odd = _mm_mul_epu32(_mm_srli_si128(x, 4),
[all...] |
| /external/clang/lib/Headers/ |
| emmintrin.h | 812 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-3289846/lib64/clang/3.8/include/ |
| emmintrin.h | 812 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-3859424/lib64/clang/4.0/include/ |
| emmintrin.h | 2361 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-4053586/lib64/clang/5.0/include/ |
| emmintrin.h | 2387 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-4393122/lib64/clang/5.0.1/include/ |
| emmintrin.h | 2483 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-4479392/lib64/clang/5.0.2/include/ |
| emmintrin.h | 2483 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-4579689/lib64/clang/6.0.1/include/ |
| emmintrin.h | 2491 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-4630689/lib64/clang/6.0.1/include/ |
| emmintrin.h | 2491 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-4639204/lib64/clang/6.0.1/include/ |
| emmintrin.h | 2491 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/darwin-x86/clang-4691093/lib64/clang/6.0.2/include/ |
| emmintrin.h | 2491 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
| /prebuilts/clang/host/linux-x86/clang-3289846/lib64/clang/3.8/include/ |
| emmintrin.h | 812 _mm_mul_epu32(__m128i __a, __m128i __b) function
[all...] |
