diff options
| author | Yang Rong <rong.r.yang@intel.com> | 2014-06-09 23:29:48 +0800 |
|---|---|---|
| committer | Zhigang Gong <zhigang.gong@intel.com> | 2014-06-09 16:34:35 +0800 |
| commit | 0ff930bdb06a41e8cd5397e5fba8fb9234007eaa (patch) | |
| tree | 61b5b8f9a30ec72a162d979c8d79222d7764be41 | |
| parent | 162dcc186c7c444f75be1b9f693012ec2f13c100 (diff) | |
HSW: Set correct max work group size for GT2 and GT3.
v2: Return an error when can't fit work group to a single half slice.
Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
| -rw-r--r-- | src/cl_command_queue_gen7.c | 7 | ||||
| -rw-r--r-- | src/cl_device_id.c | 4 |
2 files changed, 9 insertions, 2 deletions
diff --git a/src/cl_command_queue_gen7.c b/src/cl_command_queue_gen7.c index d875021c..c9818e68 100644 --- a/src/cl_command_queue_gen7.c +++ b/src/cl_command_queue_gen7.c @@ -30,6 +30,7 @@ #include <stdio.h> #include <string.h> +#define MAX_GROUP_SIZE_IN_HALFSLICE 512 static INLINE size_t cl_kernel_compute_batch_sz(cl_kernel k) { return 256+32; } /* "Varing" payload is the part of the curbe that changes accross threads in the @@ -278,6 +279,12 @@ cl_command_queue_ND_range_gen7(cl_command_queue queue, kernel.thread_n = thread_n = (local_sz + simd_sz - 1) / simd_sz; kernel.curbe_sz = cst_sz; + /* Barrier and SLM must fit into a single half slice */ + if(kernel.use_slm > 0 && simd_sz == 8 && local_sz > MAX_GROUP_SIZE_IN_HALFSLICE){ + fprintf(stderr, "Beignet: Work group CAN NOT large than %d when using barrier or local momery.\n", MAX_GROUP_SIZE_IN_HALFSLICE); + return CL_OUT_OF_RESOURCES; + } + if (scratch_sz > ker->program->ctx->device->scratch_mem_size) { fprintf(stderr, "Beignet: Out of scratch memory %d.\n", scratch_sz); return CL_OUT_OF_RESOURCES; diff --git a/src/cl_device_id.c b/src/cl_device_id.c index d2b3bed2..c4353078 100644 --- a/src/cl_device_id.c +++ b/src/cl_device_id.c @@ -86,7 +86,7 @@ static struct _cl_device_id intel_hsw_gt2_device = { .max_compute_unit = 140, .max_thread_per_unit = 7, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 1024, .max_clock_frequency = 1000, .wg_sz = 1024, #include "cl_gen75_device.h" @@ -97,7 +97,7 @@ static struct _cl_device_id intel_hsw_gt3_device = { .max_compute_unit = 280, .max_thread_per_unit = 7, .max_work_item_sizes = {512, 512, 512}, - .max_work_group_size = 512, + .max_work_group_size = 1024, .max_clock_frequency = 1000, .wg_sz = 2048, #include "cl_gen75_device.h" |