drm/radeon: Use two-ended allocation by size
Subsystems (2)
PATCH 2/2 drm/radeon: Use two-ended allocation by size
This decreases eviction by up to 20%, by improving the fragmentation quality. No harm in normal cases that fit VRAM fully (PTS gaming suite).
In some cases, even the VRAM-fitting cases improved slightly (openarena, urban terror).
512kb was measured as the most optimal threshold for 3d workloads common to radeon. Other drivers may need different thresholds according to their workloads.
--- drivers/gpu/drm/radeon/radeon_object.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)
drivers/gpu/drm/radeon/radeon_object.c +10 -1
@@ -104,7 +104,7 @@ bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo)void radeon_ttm_placement_from_domain (struct radeon_bo *rbo,u32 domain) { -u32 c =0 ; +u32 c =0 , i; rbo->placement.fpfn =0 ; rbo->placement.lpfn =0 ;
@@ -131,6 +131,15 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain) rbo->placements[c++] =TTM_PL_MASK_CACHING |TTM_PL_FLAG_SYSTEM ; rbo->placement.num_placement = c; rbo->placement.num_busy_placement = c; + +/* +* Use two-ended allocation depending on the buffer size to +* improve fragmentation quality. +* 512kb was measured as the most optimal number. +*/ +if (rbo->tbo.mem.size >512 *1024 )for (i =0 ; i < c; i++) { + rbo->placements[i] |=TTM_PL_FLAG_TOPDOWN ; + } } int radeon_bo_create(struct radeon_device *rdev,
Signature · 1 line
1.8.3.1
Quoted 29 lines · Lauri Kasanen
This decreases eviction by up to 20%, by improving the fragmentation quality. No harm in normal cases that fit VRAM fully (PTS gaming suite).
In some cases, even the VRAM-fitting cases improved slightly (openarena, urban terror).
512kb was measured as the most optimal threshold for 3d workloads common to radeon. Other drivers may need different thresholds according to their workloads.
Signed-off-by Lauri Kasanen <[email protected]>--- drivers/gpu/drm/radeon/radeon_object.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)drivers/gpu/drm/radeon/radeon_object.c +1
-1@@ -104,7 +104,7 @@ bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo)void radeon_ttm_placement_from_domain (struct radeon_bo *rbo,u32 domain) { -u32 c =0 ; +u32 c =0 , i; rbo->placement.fpfn =0 ; rbo->placement.lpfn =0 ;@@ -131,6 +131,15 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain) rbo->placements[c++] =TTM_PL_MASK_CACHING |TTM_PL_FLAG_SYSTEM ; rbo->placement.num_placement = c;
drivers/gpu/drm/radeon/radeon_object.c void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain) · line 142
Quoted 10 lines
drivers/gpu/drm/radeon/radeon_object.c +9
-0rbo->placement.num_busy_placement = c; + +/* +* Use two-ended allocation depending on the buffer size to +* improve fragmentation quality. +* 512kb was measured as the most optimal number. +*/ +if (rbo->tbo.mem.size >512 *1024 )for (i =0 ; i < c; i++) { + rbo->placements[i] |=TTM_PL_FLAG_TOPDOWN ; + }
Can you clean up the formatting of this chunk of code? It's a bit weird to read.
Alex
Quoted 10 lines
drivers/gpu/drm/radeon/radeon_object.c +0
-1} int radeon_bo_create(struct radeon_device *rdev, --1.8.3.1
_______________________________________________
dri-devel mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/dri-devel
PATCH 1/1 drm/radeon: Use two-ended allocation by size, v2
This decreases eviction by up to 20%, by improving the fragmentation quality. No harm in normal cases that fit VRAM fully (PTS gaming suite).
In some cases, even the VRAM-fitting cases improved slightly (openarena, urban terror).
512kb was measured as the most optimal threshold for 3d workloads common to radeon. Other drivers may need different thresholds according to their workloads.
v2: Nicer formatting
--- drivers/gpu/drm/radeon/radeon_object.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)
drivers/gpu/drm/radeon/radeon_object.c +12 -1
@@ -104,7 +104,7 @@ bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo)void radeon_ttm_placement_from_domain (struct radeon_bo *rbo,u32 domain) { -u32 c =0 ; +u32 c =0 , i; rbo->placement.fpfn =0 ; rbo->placement.lpfn =0 ;
@@ -131,6 +131,17 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain) rbo->placements[c++] =TTM_PL_MASK_CACHING |TTM_PL_FLAG_SYSTEM ; rbo->placement.num_placement = c; rbo->placement.num_busy_placement = c; + +/* +* Use two-ended allocation depending on the buffer size to +* improve fragmentation quality. +* 512kb was measured as the most optimal number. +*/ +if (rbo->tbo.mem.size >512 *1024 ) { +for (i =0 ; i < c; i++) { + rbo->placements[i] |=TTM_PL_FLAG_TOPDOWN ; + } + } } int radeon_bo_create(struct radeon_device *rdev,
Signature · 1 line
1.8.3.1
Re: [PATCH] drm/radeon: Use two-ended allocation by size, v2
Am 02.04.2014 19:33, schrieb Lauri Kasanen:
Quoted 10 lines
This decreases eviction by up to 20%, by improving the fragmentation quality. No harm in normal cases that fit VRAM fully (PTS gaming suite).
In some cases, even the VRAM-fitting cases improved slightly (openarena, urban terror).
512kb was measured as the most optimal threshold for 3d workloads common to radeon. Other drivers may need different thresholds according to their workloads.
v2: Nicer formatting
Signed-off-by Lauri Kasanen <[email protected]>
Quoted 35 lines
--- drivers/gpu/drm/radeon/radeon_object.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)drivers/gpu/drm/radeon/radeon_object.c +12
-1@@ -104,7 +104,7 @@ bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo)void radeon_ttm_placement_from_domain (struct radeon_bo *rbo,u32 domain) { -u32 c =0 ; +u32 c =0 , i; rbo->placement.fpfn =0 ; rbo->placement.lpfn =0 ;@@ -131,6 +131,17 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain) rbo->placements[c++] =TTM_PL_MASK_CACHING |TTM_PL_FLAG_SYSTEM ; rbo->placement.num_placement = c; rbo->placement.num_busy_placement = c; + +/* +* Use two-ended allocation depending on the buffer size to +* improve fragmentation quality. +* 512kb was measured as the most optimal number. +*/ +if (rbo->tbo.mem.size >512 *1024 ) { +for (i =0 ; i < c; i++) { + rbo->placements[i] |=TTM_PL_FLAG_TOPDOWN ; + } + } } int radeon_bo_create(struct radeon_device *rdev,