diff options
| author | Felix Kuehling <Felix.Kuehling@amd.com> | 2018-03-15 17:27:46 -0400 |
|---|---|---|
| committer | Oded Gabbay <oded.gabbay@gmail.com> | 2018-03-15 17:27:46 -0400 |
| commit | c7bcbfa4f8d1e0e1078adfe959d4b65542bccf66 (patch) | |
| tree | bf626611a9648da7268e682253df552d6b1eea4b /drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c | |
| parent | 7c9b717196b1afd368436c258994ed6054717c7a (diff) | |
drm/amdkfd: Remove limit on number of GPUs
Currently the number of GPUs is limited by aperture placement options
available on GFX7 and GFX8 hardware. This limitation is not necessary.
Scratch and LDS represent per-work-item and per-work-group storage
respectively. Different work-items and work-groups use the same virtual
address to access their own data. Work running on different GPUs is by
definition in different work-groups (different dispatches, in fact).
That means the same virtual addresses can be used for these apertures
on different GPUs.
Add a new AMDKFD_IOC_GET_PROCESS_APERTURES_NEW ioctl that removes the
artificial limitation on the number of GPUs that can be supported. The
new ioctl allows user mode to query the number of GPUs to allocate
enough memory for all GPUs to be reported.
This deprecates AMDKFD_IOC_GET_PROCESS_APERTURES.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c | 22 |
1 files changed, 10 insertions, 12 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c index 7377513050e6..a06b0100af96 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c @@ -282,14 +282,14 @@ (((uint64_t)(base) & \ 0xFFFFFF0000000000UL) | 0xFFFFFFFFFFL) -#define MAKE_SCRATCH_APP_BASE(gpu_num) \ - (((uint64_t)(gpu_num) << 61) + 0x100000000L) +#define MAKE_SCRATCH_APP_BASE() \ + (((uint64_t)(0x1UL) << 61) + 0x100000000L) #define MAKE_SCRATCH_APP_LIMIT(base) \ (((uint64_t)base & 0xFFFFFFFF00000000UL) | 0xFFFFFFFF) -#define MAKE_LDS_APP_BASE(gpu_num) \ - (((uint64_t)(gpu_num) << 61) + 0x0) +#define MAKE_LDS_APP_BASE() \ + (((uint64_t)(0x1UL) << 61) + 0x0) #define MAKE_LDS_APP_LIMIT(base) \ (((uint64_t)(base) & 0xFFFFFFFF00000000UL) | 0xFFFFFFFF) @@ -314,7 +314,7 @@ int kfd_init_apertures(struct kfd_process *process) return -1; } /* - * For 64 bit process aperture will be statically reserved in + * For 64 bit process apertures will be statically reserved in * the x86_64 non canonical process address space * amdkfd doesn't currently support apertures for 32 bit process */ @@ -323,12 +323,11 @@ int kfd_init_apertures(struct kfd_process *process) pdd->gpuvm_base = pdd->gpuvm_limit = 0; pdd->scratch_base = pdd->scratch_limit = 0; } else { - /* - * node id couldn't be 0 - the three MSB bits of - * aperture shoudn't be 0 + /* Same LDS and scratch apertures can be used + * on all GPUs. This allows using more dGPUs + * than placement options for apertures. */ - pdd->lds_base = MAKE_LDS_APP_BASE(id + 1); - + pdd->lds_base = MAKE_LDS_APP_BASE(); pdd->lds_limit = MAKE_LDS_APP_LIMIT(pdd->lds_base); pdd->gpuvm_base = MAKE_GPUVM_APP_BASE(id + 1); @@ -336,8 +335,7 @@ int kfd_init_apertures(struct kfd_process *process) pdd->gpuvm_limit = MAKE_GPUVM_APP_LIMIT(pdd->gpuvm_base); - pdd->scratch_base = MAKE_SCRATCH_APP_BASE(id + 1); - + pdd->scratch_base = MAKE_SCRATCH_APP_BASE(); pdd->scratch_limit = MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base); } |