Re: [libav-devel] [PATCH] x86: dcadsp: Avoid SSE2 instructions in SSE functions

2015-08-01 Thread Anton Khirnov
Quoting Henrik Gramner (2015-08-01 17:10:22) --- libavcodec/x86/dcadsp.asm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavcodec/x86/dcadsp.asm b/libavcodec/x86/dcadsp.asm index c42ee23..c99df12 100644 --- a/libavcodec/x86/dcadsp.asm +++

[libav-devel] [PATCH] x86: dcadsp: Avoid SSE2 instructions in SSE functions

2015-08-01 Thread Henrik Gramner
--- libavcodec/x86/dcadsp.asm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavcodec/x86/dcadsp.asm b/libavcodec/x86/dcadsp.asm index c42ee23..c99df12 100644 --- a/libavcodec/x86/dcadsp.asm +++ b/libavcodec/x86/dcadsp.asm @@ -148,7 +148,7 @@ DECODE_HF addps m4,

Re: [libav-devel] [PATCH] x86: dcadsp: Avoid SSE2 instructions in SSE functions

2015-08-01 Thread Henrik Gramner
On Sat, Aug 1, 2015 at 8:49 PM, James Almer jamr...@gmail.com wrote: I however think movq/sd should be used here for sse2 and above instead of movlps. That's a moot point in this case since the code in question is SSE only (and even if it wasn't I'm skeptical to the claim that it would be

Re: [libav-devel] [PATCH] x86: dcadsp: Avoid SSE2 instructions in SSE functions

2015-08-01 Thread James Almer
On 01/08/15 4:11 PM, Henrik Gramner wrote: On Sat, Aug 1, 2015 at 8:49 PM, James Almer jamr...@gmail.com wrote: I however think movq/sd should be used here for sse2 and above instead of movlps. That's a moot point in this case since the code in question is SSE Ah right, i was thinking about

Re: [libav-devel] [PATCH] x86: dcadsp: Avoid SSE2 instructions in SSE functions

2015-08-01 Thread James Almer
On 01/08/15 3:24 PM, Anton Khirnov wrote: Quoting Henrik Gramner (2015-08-01 17:10:22) --- libavcodec/x86/dcadsp.asm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavcodec/x86/dcadsp.asm b/libavcodec/x86/dcadsp.asm index c42ee23..c99df12 100644 ---