Mesa (master): i915: Fix streaming loads for intel_tiled_memcpy
Kenneth Graunke
kwg at kemper.freedesktop.org
Sat May 26 04:36:03 UTC 2018
Module: Mesa
Branch: master
Commit: f5e8b13f78a085bc95a1c0895e4a38ff6b87b375
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=f5e8b13f78a085bc95a1c0895e4a38ff6b87b375
Author: Chris Wilson <chris at chris-wilson.co.uk>
Date: Sat May 26 00:33:56 2018 +0100
i915: Fix streaming loads for intel_tiled_memcpy
We stream from a tiled and aligned source into an unaligned user buffer,
so we need to use _mm_storeu_si128.
Fixes: d21c086d819d78fb3f6abcbb14aa492970f442aa (i965/tiled_memcpy: inline movntdqa loads in tiled_to_linear)
Reviewed-by: Kenneth Graunke <kenneth at whitecape.org>
---
src/mesa/drivers/dri/i965/intel_tiled_memcpy.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c b/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
index fac5427d2e..6440dceac3 100644
--- a/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
+++ b/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
@@ -223,17 +223,17 @@ _memcpy_streaming_load(void *dest, const void *src, size_t count)
{
if (count == 16) {
__m128i val = _mm_stream_load_si128((__m128i *)src);
- _mm_store_si128((__m128i *)dest, val);
+ _mm_storeu_si128((__m128i *)dest, val);
return dest;
} else if (count == 64) {
__m128i val0 = _mm_stream_load_si128(((__m128i *)src) + 0);
__m128i val1 = _mm_stream_load_si128(((__m128i *)src) + 1);
__m128i val2 = _mm_stream_load_si128(((__m128i *)src) + 2);
__m128i val3 = _mm_stream_load_si128(((__m128i *)src) + 3);
- _mm_store_si128(((__m128i *)dest) + 0, val0);
- _mm_store_si128(((__m128i *)dest) + 1, val1);
- _mm_store_si128(((__m128i *)dest) + 2, val2);
- _mm_store_si128(((__m128i *)dest) + 3, val3);
+ _mm_storeu_si128(((__m128i *)dest) + 0, val0);
+ _mm_storeu_si128(((__m128i *)dest) + 1, val1);
+ _mm_storeu_si128(((__m128i *)dest) + 2, val2);
+ _mm_storeu_si128(((__m128i *)dest) + 3, val3);
return dest;
} else {
assert(count < 64); /* and (count < 16) for ytiled */
More information about the mesa-commit
mailing list