fdct_partial_neon.c: work around VS2022 Arm64 issue

cl.exe targeting AArch64 with optimizations enabled
will fail with an internal compiler error.
See:
https://developercommunity.visualstudio.com/t/Compiler-crash-C1001-when-building-a-for/10346110

Bug: b/277255076
Bug: webm:1788
Change-Id: I55caf34e910dab47a7775f07280677cdfe606f5b

diff --git a/vpx_dsp/arm/fdct_partial_neon.c b/vpx_dsp/arm/fdct_partial_neon.c
index 718dba0..df0da54 100644 (file)
--- a/vpx_dsp/arm/fdct_partial_neon.c
+++ b/vpx_dsp/arm/fdct_partial_neon.c
@@ -37,6 +37,15 @@ void vpx_fdct4x4_1_neon(const int16_t *input, tran_low_t *output, int stride) {
   output[1] = 0;
 }
 
+// Visual Studio 2022 (cl.exe) targeting AArch64 with optimizations enabled
+// will fail with an internal compiler error.
+// See:
+// https://developercommunity.visualstudio.com/t/Compiler-crash-C1001-when-building-a-for/10346110
+// TODO(jzern): check the compiler version after a fix for the issue is
+// released.
+#if defined(_MSC_VER) && defined(_M_ARM64) && !defined(__clang__)
+#pragma optimize("", off)
+#endif
 void vpx_fdct8x8_1_neon(const int16_t *input, tran_low_t *output, int stride) {
   int r;
   int16x8_t sum = vld1q_s16(&input[0]);
@@ -49,6 +58,9 @@ void vpx_fdct8x8_1_neon(const int16_t *input, tran_low_t *output, int stride) {
   output[0] = (tran_low_t)horizontal_add_int16x8(sum);
   output[1] = 0;
 }
+#if defined(_MSC_VER) && defined(_M_ARM64) && !defined(__clang__)
+#pragma optimize("", on)
+#endif
 
 void vpx_fdct16x16_1_neon(const int16_t *input, tran_low_t *output,
                           int stride) {