- 24 3月, 2021 28 次提交
-
-
由 James Zhu 提交于
Aldebaran has a new mmBIF_MMSCH1_DOORBELL_RANGE setting. Signed-off-by: NJames Zhu <James.Zhu@amd.com> Reviewed-by: NLeo Liu <leo.liu@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
MEC2_JT is not supported Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Acked-by: NAlex Deucher <alexander.deucher@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Eric Huang 提交于
The macro is for memory mapped by GPU as uncached. Signed-off-by: NEric Huang <jinhuieric.huang@amd.com> Reviewed-by: NOak Zeng <Oak.Zeng@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Eric Huang 提交于
To support new cache coherence HW on A+A platform mainly in KFD. Signed-off-by: NEric Huang <jinhuieric.huang@amd.com> Reviewed-by: NOak Zeng <Oak.Zeng@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 James Zhu 提交于
Aldebaran is using jpeg2.6, and the main change is jpeg2.6 using AMDGPU_MMHUB_0, and jpeg2.5 using AMDGPU_MMHUB_1. Signed-off-by: NJames Zhu <James.Zhu@amd.com> Reviewed-by: NLeo Liu <leo.liu@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Yong Zhao 提交于
Aldebaran should be the same as Arcturus in the PTE SNOOPED bit handling. Signed-off-by: NYong Zhao <Yong.Zhao@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Oak Zeng 提交于
Client ID 26 is reserved. Add it to the table. Signed-off-by: NOak Zeng <Oak.Zeng@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 James Zhu 提交于
Aldebaran is using vcn2.6, and the main change is vcn2.6 using AMDGPU_MMHUB_0, and vcn2.5 using AMDGPU_MMHUB_1 Signed-off-by: NJames Zhu <James.Zhu@amd.com> Reviewed-by: NLeo Liu <leo.liu@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 James Zhu 提交于
including firmware support etc. Signed-off-by: NJames Zhu <James.Zhu@amd.com> Reviewed-by: NLeo Liu <leo.liu@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Rajneesh Bhardwaj 提交于
Currently host-gpu io link is always reported as PCIe however, on some A+A systems, there could be one xgmi link available. This change exposes xgmi link via sysfs when it is present. v2: fix includes (Alex) Reviewed-by: NOak Zeng <oak.zeng@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: NRajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Rajneesh Bhardwaj 提交于
Aldebaran uses registers defined in header gc_9_4_2 but much of the xgmi related functionality can be obtained by reusing the exisitng definition from gfxhub_v1_1_get_xgmi_info. While adding support for Aldebaran, also refactored code to better handle the new scenario. Signed-off-by: NRajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Rajneesh Bhardwaj 提交于
This applies to AMD Accelerated Processing Platforms that support host gpu interconnect throguh a special link (xgmi). Aldebaran systems will support this special feature for utilizing the benefits of host-gpu cache coherence. This change outlines the basic framework for mapping the GPU VRAM (HBM) to system address space making it accesible to the host but managed by the amdgpu driver since this region is marked as reserved memory in host address space by the underlying system firmware. v2: switch to smuio callback function to check the type of host-gpu interface (Hawking) v3: use hub callbacks rather than direct function calls (Alex) Reviewed-by: NOak Zeng <oak.zeng@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: NRajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Rajneesh Bhardwaj 提交于
Like its predecessors Aldebran also supports advanced high bandwidth GPU-GPU communication interface known as xgmi. This enables the basic xgmi support while refactoring the code slightly. Detection of xgmi link between host cpu and gpu will be introduced in a different patch. Reviewed-by: NOak Zeng <oak.zeng@amd.com> Reviewed-by: NChristian König <christian.koenig@amd.com> Reviewed-by: NAlex Deucher <alexander.deucher@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: NRajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
initialize smuio v13_0 callbacks for aldebaran Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NAlex Deucher <alexander.deucher@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
Aldebaran will use smuio v13_0 callbacks Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NAlex Deucher <alexander.deucher@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
is_host_gpu_xgmi_supported is used to query gpu and cpu/host link type. get_die_id is used to query die ids. Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NAlex Deucher <alexander.deucher@amd.com> Reviewed-by: NJohn Clements <john.clements@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
Add psp v13 ip block to soc ip init list for aldebaran Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
ALDEBARAN doesn't need these golden settings. Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
SRIOV pf/vf function identifier regsiter in aldebaran is the same as the one in arcturus Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
PMFW should be loaded before any operation that may toggling DF-Cstate. otherwsie, tOS has no choice but to locally toggle DF Cstate (i.e. disable DF-Cstate even it already enabled by VBIOS) Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
mmRCC_DEV0_EPF0_STRAP0 offset in aldebaran is changed from arcturus Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
Initialze psp ip function for aldebaran Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
Add callback functions for psp_v13 ring Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
Add callback function to support trusted os loading for psp v13 Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
Add callback function to support sys_drv firmware loading for psp v13 Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
Add callback function to support key database firmware loading for psp v13 Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Hawking Zhang 提交于
Initialize sos microcode for aldebaran Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Reviewed-by: NKevin Wang <kevin1.wang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Yong Zhao 提交于
This gives more information and improves productivity. Signed-off-by: NYong Zhao <Yong.Zhao@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 10 3月, 2021 12 次提交
-
-
由 Jay Cornwall 提交于
Similar to arcturus, but ARCH/ACC VGPRs may now be split unevenly. A new field in SQ_WAVE_GPR_ALLOC tracks the boundary between the two sets of VGPRs. Squash below patches: drm/amdkfd: Use preprocessor for IP-specific trap handler code drm/amdkfd: Fix VGPR restore race in gfx8/gfx9 trap handler drm/amdkfd: Remove duplicated code in gfx9 trap handler drm/amdkfd: Separate ARCH/ACC VGPR restore in trap handler drm/amdkfd: Reverse order of ARCH/ACC VGPR restore in trap handler Signed-off-by: NJay Cornwall <jay.cornwall@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Kevin Wang 提交于
add sdma firmware load support for soc model v2: drop some emulator leftovers (Alex) Signed-off-by: NKevin Wang <kevin1.wang@amd.com> Reviewed-by: NAlex Deucher <alexander.deucher@amd.com> Reviewed-by: NLe Ma <Le.Ma@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Yong Zhao 提交于
Add initial KFD support. Signed-off-by: NYong Zhao <Yong.Zhao@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
Set ip blocks and asic family id Signed-off-by: NLe Ma <le.ma@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <evan.quan@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
On aldebaran, mmBIF_SDMA4_DOORBELL_RANGE isn't right next to mmBIF_SDMA3_DOORBELL_RANGE. Signed-off-by: NLe Ma <le.ma@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <evan.quan@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
Add initial sdma support for aldebaran, and this asic has 5 sdma instances. v2: remove adundant condition check Signed-off-by: NLe Ma <le.ma@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <Evan.Quan@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
Add gfx initial support Signed-off-by: NLe Ma <le.ma@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <evan.quan@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
Set backdoor loading way in current phase v2: change case location to not break other asics Signed-off-by: NLe Ma <le.ma@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <evan.quan@amd.com> Reviewed-by: NAlex Deucher <alexander.deucher@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
Add gfx memory controller support Signed-off-by: NLe Ma <le.ma@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <evan.quan@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
v1: dupilcate mmhub_v1_7.c from mmhub_v1_0.c because mmhub register address for aldebaran is different from existing asics (Le) v2: switch to latest mmhub_v9_4_2 register headers (Hawking) v3: squash in init VM_L2_CNTL3 default value for mmhub v1_7 Signed-off-by: NLe Ma <le.ma@amd.com> Signed-off-by: NKevin Wang <kevin1.wang@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <evan.quan@amd.com> Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
Initialize aldebaran common ip block Signed-off-by: NLe Ma <le.ma@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <evan.quan@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Le Ma 提交于
Parses asic configurations stored in gpu_info firmware and make them available for driver to use. Signed-off-by: NLe Ma <le.ma@amd.com> Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com> Acked-by: NEvan Quan <evan.quan@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-