| /llvm-project-15.0.7/llvm/lib/Support/BLAKE3/ |
| H A D | blake3_sse41.c | 48 INLINE void g1(__m128i *row0, __m128i *row1, __m128i *row2, __m128i *row3, in g1() argument
50 *row0 = addv(addv(*row0, m), *row1); in g1()
51 *row3 = xorv(*row3, *row0); in g1()
58 INLINE void g2(__m128i *row0, __m128i *row1, __m128i *row2, __m128i *row3, in g2() argument
60 *row0 = addv(addv(*row0, m), *row1); in g2()
61 *row3 = xorv(*row3, *row0); in g2()
71 INLINE void diagonalize(__m128i *row0, __m128i *row2, __m128i *row3) { in diagonalize() argument
72 *row0 = _mm_shuffle_epi32(*row0, _MM_SHUFFLE(2, 1, 0, 3)); in diagonalize()
77 INLINE void undiagonalize(__m128i *row0, __m128i *row2, __m128i *row3) { in undiagonalize() argument
78 *row0 = _mm_shuffle_epi32(*row0, _MM_SHUFFLE(0, 3, 2, 1)); in undiagonalize()
|
| H A D | blake3_sse2.c | 46 INLINE void g1(__m128i *row0, __m128i *row1, __m128i *row2, __m128i *row3, in g1() argument
48 *row0 = addv(addv(*row0, m), *row1); in g1()
49 *row3 = xorv(*row3, *row0); in g1()
56 INLINE void g2(__m128i *row0, __m128i *row1, __m128i *row2, __m128i *row3, in g2() argument
58 *row0 = addv(addv(*row0, m), *row1); in g2()
59 *row3 = xorv(*row3, *row0); in g2()
69 INLINE void diagonalize(__m128i *row0, __m128i *row2, __m128i *row3) { in diagonalize() argument
70 *row0 = _mm_shuffle_epi32(*row0, _MM_SHUFFLE(2, 1, 0, 3)); in diagonalize()
75 INLINE void undiagonalize(__m128i *row0, __m128i *row2, __m128i *row3) { in undiagonalize() argument
76 *row0 = _mm_shuffle_epi32(*row0, _MM_SHUFFLE(0, 3, 2, 1)); in undiagonalize()
|
| H A D | blake3_avx512.c | 81 INLINE void g1(__m128i *row0, __m128i *row1, __m128i *row2, __m128i *row3, in g1() argument
83 *row0 = add_128(add_128(*row0, m), *row1); in g1()
84 *row3 = xor_128(*row3, *row0); in g1()
91 INLINE void g2(__m128i *row0, __m128i *row1, __m128i *row2, __m128i *row3, in g2() argument
93 *row0 = add_128(add_128(*row0, m), *row1); in g2()
94 *row3 = xor_128(*row3, *row0); in g2()
104 INLINE void diagonalize(__m128i *row0, __m128i *row2, __m128i *row3) { in diagonalize() argument
105 *row0 = _mm_shuffle_epi32(*row0, _MM_SHUFFLE(2, 1, 0, 3)); in diagonalize()
110 INLINE void undiagonalize(__m128i *row0, __m128i *row2, __m128i *row3) { in undiagonalize() argument
111 *row0 = _mm_shuffle_epi32(*row0, _MM_SHUFFLE(0, 3, 2, 1)); in undiagonalize()
|
| /llvm-project-15.0.7/clang/lib/Headers/ |
| H A D | xmmintrin.h | 2980 #define _MM_TRANSPOSE4_PS(row0, row1, row2, row3) \ argument
2983 tmp0 = _mm_unpacklo_ps((row0), (row1)); \
2985 tmp1 = _mm_unpackhi_ps((row0), (row1)); \
2987 (row0) = _mm_movelh_ps(tmp0, tmp2); \
|
| /llvm-project-15.0.7/clang/lib/Headers/ppc_wrappers/ |
| H A D | xmmintrin.h | 1802 #define _MM_TRANSPOSE4_PS(row0, row1, row2, row3) \ argument
1804 __v4sf __r0 = (row0), __r1 = (row1), __r2 = (row2), __r3 = (row3); \
1809 (row0) = (__v4sf)vec_mergeh((__vector long long)__t0, \
|
| /llvm-project-15.0.7/llvm/test/CodeGen/X86/ |
| H A D | sse-intrinsics-fast-isel.ll | 3325 %row0 = load <4 x float>, <4 x float>* %a0, align 16
3329 %tmp0 = shufflevector <4 x float> %row0, <4 x float> %row1, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
3331 %tmp1 = shufflevector <4 x float> %row0, <4 x float> %row1, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
|