diff options
| -rw-r--r-- | numpy/core/src/umath/simd.inc.src | 18 |
1 files changed, 11 insertions, 7 deletions
diff --git a/numpy/core/src/umath/simd.inc.src b/numpy/core/src/umath/simd.inc.src index 92dc0c659..7944d5f47 100644 --- a/numpy/core/src/umath/simd.inc.src +++ b/numpy/core/src/umath/simd.inc.src @@ -480,14 +480,18 @@ sse2_binary_scalar2_@kind@_@TYPE@(@type@ * op, @type@ * ip1, @type@ * ip2, npy_i /**end repeat1**/ -/* compress 4 vectors to 4/8 bytes in op with filled with 0 or 1 */ +/* + * compress 4 vectors to 4/8 bytes in op with filled with 0 or 1 + * the last vector is passed as a pointer as MSVC 2010 is unable to ignore the + * calling convention leading to C2719 on 32 bit, see #4795 + */ static NPY_INLINE void -sse2_compress4_to_byte_@TYPE@(@vtype@ r1, @vtype@ r2, @vtype@ r3, @vtype@ r4, +sse2_compress4_to_byte_@TYPE@(@vtype@ r1, @vtype@ r2, @vtype@ r3, @vtype@ * r4, npy_bool * op) { const __m128i mask = @vpre@_set1_epi8(0x1); __m128i ir1 = @vpre@_packs_epi32(@cast@(r1), @cast@(r2)); - __m128i ir2 = @vpre@_packs_epi32(@cast@(r3), @cast@(r4)); + __m128i ir2 = @vpre@_packs_epi32(@cast@(r3), @cast@(*r4)); __m128i rr = @vpre@_packs_epi16(ir1, ir2); #if @double@ rr = @vpre@_packs_epi16(rr, rr); @@ -535,7 +539,7 @@ sse2_binary_@kind@_@TYPE@(npy_bool * op, @type@ * ip1, @type@ * ip2, npy_intp n) @vtype@ r2 = @vpre@_@VOP@_@vsuf@(b, b); @vtype@ r3 = @vpre@_@VOP@_@vsuf@(c, c); @vtype@ r4 = @vpre@_@VOP@_@vsuf@(d, d); - sse2_compress4_to_byte_@TYPE@(r1, r2, r3, r4, &op[i]); + sse2_compress4_to_byte_@TYPE@(r1, r2, r3, &r4, &op[i]); } } else { @@ -552,7 +556,7 @@ sse2_binary_@kind@_@TYPE@(npy_bool * op, @type@ * ip1, @type@ * ip2, npy_intp n) @vtype@ r2 = @vpre@_@VOP@_@vsuf@(b1, b2); @vtype@ r3 = @vpre@_@VOP@_@vsuf@(c1, c2); @vtype@ r4 = @vpre@_@VOP@_@vsuf@(d1, d2); - sse2_compress4_to_byte_@TYPE@(r1, r2, r3, r4, &op[i]); + sse2_compress4_to_byte_@TYPE@(r1, r2, r3, &r4, &op[i]); } } LOOP_BLOCKED_END { @@ -577,7 +581,7 @@ sse2_binary_scalar1_@kind@_@TYPE@(npy_bool * op, @type@ * ip1, @type@ * ip2, npy @vtype@ r2 = @vpre@_@VOP@_@vsuf@(s, b); @vtype@ r3 = @vpre@_@VOP@_@vsuf@(s, c); @vtype@ r4 = @vpre@_@VOP@_@vsuf@(s, d); - sse2_compress4_to_byte_@TYPE@(r1, r2, r3, r4, &op[i]); + sse2_compress4_to_byte_@TYPE@(r1, r2, r3, &r4, &op[i]); } LOOP_BLOCKED_END { op[i] = sse2_ordered_cmp_@kind@_@TYPE@(ip1[0], ip2[i]); @@ -601,7 +605,7 @@ sse2_binary_scalar2_@kind@_@TYPE@(npy_bool * op, @type@ * ip1, @type@ * ip2, npy @vtype@ r2 = @vpre@_@VOP@_@vsuf@(b, s); @vtype@ r3 = @vpre@_@VOP@_@vsuf@(c, s); @vtype@ r4 = @vpre@_@VOP@_@vsuf@(d, s); - sse2_compress4_to_byte_@TYPE@(r1, r2, r3, r4, &op[i]); + sse2_compress4_to_byte_@TYPE@(r1, r2, r3, &r4, &op[i]); } LOOP_BLOCKED_END { op[i] = sse2_ordered_cmp_@kind@_@TYPE@(ip1[i], ip2[0]); |