From 15c0ee445f603033c82f357fedfc7737d198d7b3 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Sun, 24 Jun 2012 19:28:03 +0100 Subject: [PATCH] sna/gen5: Tweak thread allocations Bump the alloted number of threads to their max. Using more threads than cores helps hide the stalls due to sampler fetch, math functions and urb write. Specifying too many threads seems to not incur a performance regression, suggesting that the hardware scheduler is sane enough not to overpopulate the EU. A small but significant boost, peak x11perf -aa10text on an i3-330m is raised from 1.93Mglyphs/s to 2.35Mglyphs/s. Signed-off-by: Chris Wilson --- src/sna/gen5_render.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/src/sna/gen5_render.c b/src/sna/gen5_render.c index 27ba04d4..0fd51d0d 100644 --- a/src/sna/gen5_render.c +++ b/src/sna/gen5_render.c @@ -65,7 +65,7 @@ #define URB_CS_ENTRIES 0 #define URB_VS_ENTRY_SIZE 1 -#define URB_VS_ENTRIES 128 /* minimum of 8 */ +#define URB_VS_ENTRIES 256 /* minimum of 8 */ #define URB_GS_ENTRY_SIZE 0 #define URB_GS_ENTRIES 0 @@ -74,7 +74,7 @@ #define URB_CLIP_ENTRIES 0 #define URB_SF_ENTRY_SIZE 2 -#define URB_SF_ENTRIES 32 +#define URB_SF_ENTRIES 64 /* * this program computes dA/dx and dA/dy for the texture coordinates along @@ -82,10 +82,10 @@ */ #define SF_KERNEL_NUM_GRF 16 -#define SF_MAX_THREADS 2 +#define SF_MAX_THREADS 48 #define PS_KERNEL_NUM_GRF 32 -#define PS_MAX_THREADS 48 +#define PS_MAX_THREADS 72 static const uint32_t sf_kernel[][4] = { #include "exa_sf.g5b"