diff mbox series

[FFmpeg-devel] tests/checkasm/sw_scale: Fix alignment for movdqa

Message ID 1657f1e0-116a-92e2-033f-4a9493f9de92@mail.de
State Accepted
Commit b7f6a933fa4873c7523586d6e203cfd1798decd6
Headers show
Series [FFmpeg-devel] tests/checkasm/sw_scale: Fix alignment for movdqa | expand

Checks

Context Check Description
andriy/commit_msg_armv7_RPi4 warning Please wrap lines in the body of the commit message between 60 and 72 characters.
andriy/commit_msg_x86 warning Please wrap lines in the body of the commit message between 60 and 72 characters.
andriy/make_x86 success Make finished
andriy/make_fate_x86 success Make fate finished
andriy/make_armv7_RPi4 success Make finished
andriy/make_fate_armv7_RPi4 success Make fate finished

Commit Message

Thilo Borgmann June 16, 2022, 8:59 a.m. UTC
Hi,

movdqa in ff_yuv2yuvX_sse3() expects a 16-byte alignment according to its documentation causing segfaults in fate-checkasm-sw_scale.

-Thilo
From ed84410b2371a758dad03d3830bfb4f3d86cd4ed Mon Sep 17 00:00:00 2001
From: Michael Goulet <mgoulet@fb.com>
Date: Thu, 16 Jun 2022 10:14:50 +0200
Subject: [PATCH] tests/checkasm/sw_scale: Fix alignment for movdqa

SSE3 instruction movdqa in ff_yuv2yuvX_sse3() expects a 16-byte aligned address for a memory address, or else a segfault is generated.
The src_pixels buffer below was not aligned to 16 bytes on the stack necessarily, so we got segfaults during fate-checkasm-sw_scale.

Therefore 16-byte align all of these local variables, aligning them too much shouldn't hurt.
---
 tests/checkasm/sw_scale.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

Comments

Martin Storsjö June 18, 2022, 9:50 p.m. UTC | #1
On Thu, 16 Jun 2022, Thilo Borgmann wrote:

> Hi,
>
> movdqa in ff_yuv2yuvX_sse3() expects a 16-byte alignment according to its 
> documentation causing segfaults in fate-checkasm-sw_scale.

LGTM, thanks!

// Martin
Thilo Borgmann June 20, 2022, 9:09 a.m. UTC | #2
Am 18.06.22 um 23:50 schrieb Martin Storsjö:
> On Thu, 16 Jun 2022, Thilo Borgmann wrote:
> 
>> Hi,
>>
>> movdqa in ff_yuv2yuvX_sse3() expects a 16-byte alignment according to its documentation causing segfaults in fate-checkasm-sw_scale.
> 
> LGTM, thanks!

Pushed, Thanks!

-Thilo
diff mbox series

Patch

diff --git a/tests/checkasm/sw_scale.c b/tests/checkasm/sw_scale.c
index 31d9a525e9..b643a47c30 100644
--- a/tests/checkasm/sw_scale.c
+++ b/tests/checkasm/sw_scale.c
@@ -75,11 +75,11 @@  static void check_yuv2yuvX(void)
                       int dstW, const uint8_t *dither, int offset);
 
     const int16_t **src;
-    LOCAL_ALIGNED_8(int16_t, src_pixels, [LARGEST_FILTER * LARGEST_INPUT_SIZE]);
-    LOCAL_ALIGNED_8(int16_t, filter_coeff, [LARGEST_FILTER]);
-    LOCAL_ALIGNED_8(uint8_t, dst0, [LARGEST_INPUT_SIZE]);
-    LOCAL_ALIGNED_8(uint8_t, dst1, [LARGEST_INPUT_SIZE]);
-    LOCAL_ALIGNED_8(uint8_t, dither, [LARGEST_INPUT_SIZE]);
+    LOCAL_ALIGNED_16(int16_t, src_pixels, [LARGEST_FILTER * LARGEST_INPUT_SIZE]);
+    LOCAL_ALIGNED_16(int16_t, filter_coeff, [LARGEST_FILTER]);
+    LOCAL_ALIGNED_16(uint8_t, dst0, [LARGEST_INPUT_SIZE]);
+    LOCAL_ALIGNED_16(uint8_t, dst1, [LARGEST_INPUT_SIZE]);
+    LOCAL_ALIGNED_16(uint8_t, dither, [LARGEST_INPUT_SIZE]);
     union VFilterData{
         const int16_t *src;
         uint16_t coeff[8];