vc4: Only build the NEON code on arm32.

NEON is sufficiently different on arm64 that we can't just reuse this
code.  Disable it on arm64 for now.

v2: Use PIPE_ARCH_ARM instead, as __ARM_ARCH may be 8 for a 32-bit build
    for a v8 CPU.

Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: <mesa-stable@lists.freedesktop.org>

diff --git a/src/gallium/drivers/vc4/vc4_tiling_lt.c b/src/gallium/drivers/vc4/vc4_tiling_lt.c
index c9cbc65e2dbc32519155f3513ec71226445eb7a3..f37a92e9390ea4e2e9d51ea86d711b23af78d811 100644 (file)
--- a/src/gallium/drivers/vc4/vc4_tiling_lt.c
+++ b/src/gallium/drivers/vc4/vc4_tiling_lt.c
@@ -61,7 +61,7 @@ static void
 vc4_load_utile(void *cpu, void *gpu, uint32_t cpu_stride, uint32_t cpp)
 {
         uint32_t gpu_stride = vc4_utile_stride(cpp);
-#if defined(VC4_BUILD_NEON) && defined(__ARM_ARCH)
+#if defined(VC4_BUILD_NEON) && defined(PIPE_ARCH_ARM)
         if (gpu_stride == 8) {
                 __asm__ volatile (
                         /* Load from the GPU in one shot, no interleave, to
@@ -118,7 +118,7 @@ vc4_store_utile(void *gpu, void *cpu, uint32_t cpu_stride, uint32_t cpp)
 {
         uint32_t gpu_stride = vc4_utile_stride(cpp);
 
-#if defined(VC4_BUILD_NEON) && defined(__ARM_ARCH)
+#if defined(VC4_BUILD_NEON) && defined(PIPE_ARCH_ARM)
         if (gpu_stride == 8) {
                 __asm__ volatile (
                         /* Load each 8-byte line from cpu-side source,