diff options
| author | rander <rander.wang@intel.com> | 2017-06-23 11:02:27 +0800 |
|---|---|---|
| committer | Yang Rong <rong.r.yang@intel.com> | 2017-07-04 09:55:52 +0800 |
| commit | 6fde3e082897975bacde1134c4a8096420fa5ab9 (patch) | |
| tree | ab2937c4a7581acbbf5c01a25e9b3da92d475ba0 | |
| parent | f0c3b352c3da283aaf4199136894b1da352832f7 (diff) | |
| download | beignet-6fde3e082897975bacde1134c4a8096420fa5ab9.tar.gz | |
Runtime: refine max group size for SKL & KBL
Now change max group size to 256. it is a reasonable
size for Gen9. According to performance test, 256 make
good progress in openCV and no regression. So change it
Signed-off-by: rander.wang <rander.wang@intel.com>
Reviewed-by: Yang Rong <rong.r.yang@intel.com>
| -rw-r--r-- | src/cl_device_id.c | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/src/cl_device_id.c b/src/cl_device_id.c index b9a60bb1..1960463e 100644 --- a/src/cl_device_id.c +++ b/src/cl_device_id.c @@ -149,7 +149,7 @@ static struct _cl_device_id intel_skl_gt1_device = { .max_thread_per_unit = 7, .sub_slice_count = 2, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; @@ -159,7 +159,7 @@ static struct _cl_device_id intel_skl_gt2_device = { .max_thread_per_unit = 7, .sub_slice_count = 3, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; @@ -169,7 +169,7 @@ static struct _cl_device_id intel_skl_gt3_device = { .max_thread_per_unit = 7, .sub_slice_count = 6, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; @@ -179,7 +179,7 @@ static struct _cl_device_id intel_skl_gt4_device = { .max_thread_per_unit = 7, .sub_slice_count = 9, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; @@ -209,7 +209,7 @@ static struct _cl_device_id intel_kbl_gt1_device = { .max_thread_per_unit = 7, .sub_slice_count = 2, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; @@ -219,7 +219,7 @@ static struct _cl_device_id intel_kbl_gt15_device = { .max_thread_per_unit = 7, .sub_slice_count = 3, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; @@ -229,7 +229,7 @@ static struct _cl_device_id intel_kbl_gt2_device = { .max_thread_per_unit = 7, .sub_slice_count = 3, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; @@ -239,7 +239,7 @@ static struct _cl_device_id intel_kbl_gt3_device = { .max_thread_per_unit = 7, .sub_slice_count = 6, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; @@ -249,7 +249,7 @@ static struct _cl_device_id intel_kbl_gt4_device = { .max_thread_per_unit = 7, .sub_slice_count = 9, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 256, .max_clock_frequency = 1000, #include "cl_gen9_device.h" }; |