BLD: workaround msvc being stupid

Apparently it tries to respect calling conventions for static inline
functions so the 4th variable can't be passed over the stack as it needs
16 byte alignment.
Work around this by passing the variable as a pointer.
Closes gh-4795

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]);