brain-hackers_pepepper-mirror
/
linux-brain
mirror of https://github.com/brain-hackers/linux-brain.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/amdkfd: Extend CU mask to 8 SEs (v3) 

Following bitmap layout logic introduced by:
"drm/amdgpu: support get_cu_info for Arcturus".

v2: squash in fixup for gfx_v9_0.c (Alex)
v3: squash in debug print output fix

Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Jay Cornwall 2019-07-18 16:57:22 -05:00 committed by Alex Deucher
parent 857b82d0df
commit 5145d57ec5
5 changed files with 30 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
View File

@ -3341,6 +3341,10 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
mqd->compute_static_thread_mgmt_se1 = 0xffffffff;
mqd->compute_static_thread_mgmt_se2 = 0xffffffff;
mqd->compute_static_thread_mgmt_se3 = 0xffffffff;
mqd->compute_static_thread_mgmt_se4 = 0xffffffff;
mqd->compute_static_thread_mgmt_se5 = 0xffffffff;
mqd->compute_static_thread_mgmt_se6 = 0xffffffff;
mqd->compute_static_thread_mgmt_se7 = 0xffffffff;
mqd->compute_misc_reserved = 0x00000003;
mqd->dynamic_cu_mask_addr_lo =

10
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
View File

@ -98,8 +98,8 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
uint32_t *se_mask)
{
struct kfd_cu_info cu_info;
uint32_t cu_per_sh[4] = {0};
int i, se, cu = 0;
uint32_t cu_per_se[KFD_MAX_NUM_SE] = {0};
int i, se, sh, cu = 0;
amdgpu_amdkfd_get_cu_info(mm->dev->kgd, &cu_info);
@ -107,8 +107,8 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
cu_mask_count = cu_info.cu_active_number;
for (se = 0; se < cu_info.num_shader_engines; se++)
for (i = 0; i < 4; i++)
cu_per_sh[se] += hweight32(cu_info.cu_bitmap[se][i]);
for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++)
cu_per_se[se] += hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
/* Symmetrically map cu_mask to all SEs:
* cu_mask[0] bit0 -> se_mask[0] bit0;
@ -128,6 +128,6 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
se = 0;
cu++;
}
} while (cu >= cu_per_sh[se] && cu < 32);
} while (cu >= cu_per_se[se] && cu < 32);
}
}

2
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
View File

@ -26,6 +26,8 @@
#include "kfd_priv.h"
#define KFD_MAX_NUM_SE 8
/**
* struct mqd_manager
*

18
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
View File

@ -46,7 +46,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
struct queue_properties *q)
{
struct v9_mqd *m;
uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
uint32_t se_mask[KFD_MAX_NUM_SE] = {0};
if (q->cu_mask_count == 0)
return;
@ -59,12 +59,20 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
m->compute_static_thread_mgmt_se1 = se_mask[1];
m->compute_static_thread_mgmt_se2 = se_mask[2];
m->compute_static_thread_mgmt_se3 = se_mask[3];
m->compute_static_thread_mgmt_se4 = se_mask[4];
m->compute_static_thread_mgmt_se5 = se_mask[5];
m->compute_static_thread_mgmt_se6 = se_mask[6];
m->compute_static_thread_mgmt_se7 = se_mask[7];
pr_debug("update cu mask to %#x %#x %#x %#x\n",
pr_debug("update cu mask to %#x %#x %#x %#x %#x %#x %#x %#x\n",
m->compute_static_thread_mgmt_se0,
m->compute_static_thread_mgmt_se1,
m->compute_static_thread_mgmt_se2,
m->compute_static_thread_mgmt_se3);
m->compute_static_thread_mgmt_se3,
m->compute_static_thread_mgmt_se4,
m->compute_static_thread_mgmt_se5,
m->compute_static_thread_mgmt_se6,
m->compute_static_thread_mgmt_se7);
}
static void set_priority(struct v9_mqd *m, struct queue_properties *q)
@ -125,6 +133,10 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
m->compute_static_thread_mgmt_se1 = 0xFFFFFFFF;
m->compute_static_thread_mgmt_se2 = 0xFFFFFFFF;
m->compute_static_thread_mgmt_se3 = 0xFFFFFFFF;
m->compute_static_thread_mgmt_se4 = 0xFFFFFFFF;
m->compute_static_thread_mgmt_se5 = 0xFFFFFFFF;
m->compute_static_thread_mgmt_se6 = 0xFFFFFFFF;
m->compute_static_thread_mgmt_se7 = 0xFFFFFFFF;
m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;

8
drivers/gpu/drm/amd/include/v9_structs.h
View File

@ -196,10 +196,10 @@ struct v9_mqd {
uint32_t compute_wave_restore_addr_lo;
uint32_t compute_wave_restore_addr_hi;
uint32_t compute_wave_restore_control;
uint32_t reserved_39;
uint32_t reserved_40;
uint32_t reserved_41;
uint32_t reserved_42;
uint32_t compute_static_thread_mgmt_se4;
uint32_t compute_static_thread_mgmt_se5;
uint32_t compute_static_thread_mgmt_se6;
uint32_t compute_static_thread_mgmt_se7;
uint32_t reserved_43;
uint32_t reserved_44;
uint32_t reserved_45;