Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

On 02/22/2016 02:10 PM, Matt Turner wrote: > On Mon, Feb 22, 2016 at 1:05 PM, Ian Romanick wrote: >> On 02/19/2016 02:57 AM, Iago Toral wrote: >>> I don't know much about this, but using shader_samples_identical should >>> only give a benefit if we actually get identical

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

On 02/22/2016 02:10 PM, Matt Turner wrote: > On Mon, Feb 22, 2016 at 1:05 PM, Ian Romanick wrote: >> On 02/19/2016 02:57 AM, Iago Toral wrote: >>> I don't know much about this, but using shader_samples_identical should >>> only give a benefit if we actually get identical

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

On Mon, Feb 22, 2016 at 1:05 PM, Ian Romanick wrote: > On 02/19/2016 02:57 AM, Iago Toral wrote: >> I don't know much about this, but using shader_samples_identical should >> only give a benefit if we actually get identical samples, otherwise it >> means more work, right? >

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

On 02/19/2016 02:57 AM, Iago Toral wrote: > I don't know much about this, but using shader_samples_identical should > only give a benefit if we actually get identical samples, otherwise it > means more work, right? It is possible to do more work. Assuming the backend compiler does everything

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

Am 19.02.2016 um 11:57 schrieb Iago Toral: > On Thu, 2016-02-18 at 16:13 -0800, Ian Romanick wrote: >> On 02/18/2016 01:47 PM, Ian Romanick wrote: >>> On 02/18/2016 08:44 AM, Neil Roberts wrote: I made a pathological test case (attached) which repeatedly renders into an MSAA FBO and then

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

On Fri, 2016-02-19 at 11:47 +, Neil Roberts wrote: > Iago Toral writes: > > > I don't know much about this, but using shader_samples_identical > > should only give a benefit if we actually get identical samples, > > otherwise it means more work, right? I noticed that the

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

Iago Toral writes: > I don't know much about this, but using shader_samples_identical > should only give a benefit if we actually get identical samples, > otherwise it means more work, right? I noticed that the test renders a > quad with random colors for each vertex that will

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

On Thu, 2016-02-18 at 16:13 -0800, Ian Romanick wrote: > On 02/18/2016 01:47 PM, Ian Romanick wrote: > > On 02/18/2016 08:44 AM, Neil Roberts wrote: > >> I made a pathological test case (attached) which repeatedly renders into > >> an MSAA FBO and then blits it to the screen and measures the

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

On 02/18/2016 01:47 PM, Ian Romanick wrote: > On 02/18/2016 08:44 AM, Neil Roberts wrote: >> I made a pathological test case (attached) which repeatedly renders into >> an MSAA FBO and then blits it to the screen and measures the framerate. >> It checks it with a range of different sample counts.

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

On 02/18/2016 08:44 AM, Neil Roberts wrote: > I made a pathological test case (attached) which repeatedly renders into > an MSAA FBO and then blits it to the screen and measures the framerate. > It checks it with a range of different sample counts. The rendering is > done either by rendering two

Re: [Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

I made a pathological test case (attached) which repeatedly renders into an MSAA FBO and then blits it to the screen and measures the framerate. It checks it with a range of different sample counts. The rendering is done either by rendering two triangles to fill the framebuffer or by calling

[Mesa-dev] [PATCH 22/22] meta/blit: Use GL_EXT_shader_samples_identical in MSAA-SS resolve blit

From: Ian Romanick Somewhat surprisingly, this didn't have any affect on performance in the benchmarks that Martin tried for me. Signed-off-by: Ian Romanick --- src/mesa/drivers/common/meta_blit.c | 10 +- 1 file changed, 9