AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Felix Kuehling <Felix.Kuehling@amd.com>
To: amd-gfx@lists.freedesktop.org
Cc: joseph.greathouse@amd.com
Subject: [PATCH 2/2] drm/amdgpu: Albebaran: MTYPE_NC for coarse-grain remote memory
Date: Mon, 10 May 2021 19:35:28 -0400	[thread overview]
Message-ID: <20210510233528.1633-3-Felix.Kuehling@amd.com> (raw)
In-Reply-To: <20210510233528.1633-1-Felix.Kuehling@amd.com>

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: Felix Kuehling <Felix.Kuehling@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 ++-
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c             | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 941a204d28f5..93ee569f6a63 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -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;
 			}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index b11f2b364bbf..a1b1981084fa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1034,7 +1034,8 @@ 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;
 			}
-- 
2.31.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

  parent reply	other threads:[~2021-05-10 23:35 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-10 23:35 [PATCH 0/2] Use MTYPE_NC for coarse-grain remote memory Felix Kuehling
2021-05-10 23:35 ` [PATCH 1/2] drm/amdgpu: Arcturus: " Felix Kuehling
2021-05-10 23:35 ` Felix Kuehling [this message]
2021-05-11  1:48 ` [PATCH 0/2] Use " Zeng, Oak

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210510233528.1633-3-Felix.Kuehling@amd.com \
    --to=felix.kuehling@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=joseph.greathouse@amd.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox