On Thu, 2014-11-06 at 19:30 -0500, Frank Henigman wrote:
I tested your patch with the teximage program in mesa demos, the
same thing I used to benchmark when I developed this code.
As Matt and Chad point out, the odd-looking _faster functions are
there for a reason. Your change causes a huge
Also cleans up some if statements in the *faster functions.
Callgrind cpu usage results from pts benchmarks:
For ytile_copy_faster()
Nexuiz 1.6.1: 2.16% - 1.20%
Signed-off-by: Timothy Arceri t_arc...@yahoo.com.au
---
src/mesa/Makefile.am | 8 +++
On Thu, Nov 6, 2014 at 4:20 AM, Timothy Arceri t_arc...@yahoo.com.au wrote:
Also cleans up some if statements in the *faster functions.
Callgrind cpu usage results from pts benchmarks:
For ytile_copy_faster()
Nexuiz 1.6.1: 2.16% - 1.20%
Signed-off-by: Timothy Arceri t_arc...@yahoo.com.au
On Thu, 2014-11-06 at 10:03 -0800, Matt Turner wrote:
On Thu, Nov 6, 2014 at 4:20 AM, Timothy Arceri t_arc...@yahoo.com.au wrote:
Also cleans up some if statements in the *faster functions.
Callgrind cpu usage results from pts benchmarks:
For ytile_copy_faster()
Nexuiz 1.6.1: 2.16%
On Thu, Nov 6, 2014 at 1:22 PM, Timothy Arceri t_arc...@yahoo.com.au wrote:
On Thu, 2014-11-06 at 10:03 -0800, Matt Turner wrote:
On Thu, Nov 6, 2014 at 4:20 AM, Timothy Arceri t_arc...@yahoo.com.au wrote:
Also cleans up some if statements in the *faster functions.
Callgrind cpu usage
On 11/06/2014 02:12 PM, Matt Turner wrote:
On Thu, Nov 6, 2014 at 1:22 PM, Timothy Arceri t_arc...@yahoo.com.au wrote:
On Thu, 2014-11-06 at 10:03 -0800, Matt Turner wrote:
On Thu, Nov 6, 2014 at 4:20 AM, Timothy Arceri t_arc...@yahoo.com.au
wrote:
+#include assert.h
+#include stdint.h
On Thu 06 Nov 2014, Timothy Arceri wrote:
Also cleans up some if statements in the *faster functions.
I have comments about the cleanup below.
diff --git a/src/mesa/drivers/dri/i965/intel_tex_subimage.c
b/src/mesa/drivers/dri/i965/intel_tex_subimage.c
index cb5738a..0deeb75 100644
---
I tested your patch with the teximage program in mesa demos, the
same thing I used to benchmark when I developed this code.
As Matt and Chad point out, the odd-looking _faster functions are
there for a reason. Your change causes a huge slowdown.
I tested on a sandybridge system with a Intel(R)
On Thu, Nov 6, 2014 at 7:30 PM, Frank Henigman fjhenig...@google.com wrote:
Also I couldn't configure the build after your patch. I think you
left out a change to configure.ac to define SSSE3_SUPPORTED.
Ah, that was in patch 1/2.
___
mesa-dev