Commit 2b2339ee authored by Felix Kuehling's avatar Felix Kuehling Committed by Alex Deucher

drm/amdgpu: Albebaran: MTYPE_NC for coarse-grain remote memory

MTYPE UC was used for a specific use case that ended up not being
implemented. Use NC for better performance for coarse-grained memory where
cache coherence during shader execution is not required.
Signed-off-by: default avatarFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: default avatarOak Zeng <Oak.Zeng@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 0c6f7777
......@@ -453,7 +453,8 @@ static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
if (adev->gmc.xgmi.connected_to_cpu)
snoop = true;
} else {
mapping_flags |= AMDGPU_VM_MTYPE_UC;
mapping_flags |= coherent ?
AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
if (amdgpu_xgmi_same_hive(adev, bo_adev))
snoop = true;
}
......
......@@ -1040,7 +1040,8 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange)
if (adev->gmc.xgmi.connected_to_cpu)
snoop = true;
} else {
mapping_flags |= AMDGPU_VM_MTYPE_UC;
mapping_flags |= coherent ?
AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
if (amdgpu_xgmi_same_hive(adev, bo_adev))
snoop = true;
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment