wait() is redesigned with two pathes:
fast path: Use spinlock to wait for notify signal. If the
signal hasn't been received for some loops, go to slow path.
slow path: Use condition_variable's wait().
Improve monitor wrapper for better performance.
Fix some bugs left from name removing patch.
Change-Id: I893a8353121a25d11e37c8e631caf31cc1fc1f24
[ROCm/clr commit: f2ff56af9c]
wait() is redesigned with two pathes:
fast path: Use spinlock to wait for notify signal. If the
signal hasn't been received for some loops, go to slow path.
slow path: Use condition_variable's wait().
Improve monitor wrapper for better performance.
Fix some bugs left from name removing patch.
Change-Id: I893a8353121a25d11e37c8e631caf31cc1fc1f24
Since GFX950 can support page table fragment up to 18 without
performance loss. So set GFX950 default svm.alignment_order to 18.
Change-Id: Ibcdb7f041fb07a38e924c471beec261ea227ca1d
Signed-off-by: James Zhu <James.Zhu@amd.com>
Since GFX950 can support page table fragment up to 18 without
performance loss. So set GFX950 default svm.alignment_order to 18.
Change-Id: Ibcdb7f041fb07a38e924c471beec261ea227ca1d
Signed-off-by: James Zhu <James.Zhu@amd.com>
[ROCm/ROCR-Runtime commit: 9509af4b98]
This patch creates the blacklist for gfx950 by copying gfx942 but adding
KFDGWSTest.Semaphore as GWS support is completely removed from gfx950.
Change-Id: I5d7c17e57b8cfd9fae63780ecc9dd55662cfdade
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
This patch creates the blacklist for gfx950 by copying gfx942 but adding
KFDGWSTest.Semaphore as GWS support is completely removed from gfx950.
Change-Id: I5d7c17e57b8cfd9fae63780ecc9dd55662cfdade
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
[ROCm/ROCR-Runtime commit: 0b6e457201]
Make sure to use allocate the same amount of size for VGPR data in
gfx950 as it is done for gfx940.
Change-Id: I6a0820996389627ccbdfef856e5150c46fac92a1
Signed-off-by: Lancelot SIX <lancelot.six@amd.com>
Make sure to use allocate the same amount of size for VGPR data in
gfx950 as it is done for gfx940.
Change-Id: I6a0820996389627ccbdfef856e5150c46fac92a1
Signed-off-by: Lancelot SIX <lancelot.six@amd.com>
[ROCm/ROCR-Runtime commit: 76052ba028]
Added HSA_IMAGE_ENABLE_3D_SWIZZLE_DEBUG environment flag to
enable/disable this. Default value is false (view3dAs2dArray = 1)
Enabling this flag will enable support for swizzles that do 3D
interleaving. Note that all features of 3D images are supported
with 2D swizzles,it's just that the access patterns are different
and therefore cache hit-rates may be better or worse, depending
on how it's used. Volumetric algorithms do better with 3D and apps
that tend to access a single slice at a time do better with 2D.
Change-Id: Id8574a6710fe4333a1ee331e5ce9195a81434198
Added HSA_IMAGE_ENABLE_3D_SWIZZLE_DEBUG environment flag to
enable/disable this. Default value is false (view3dAs2dArray = 1)
Enabling this flag will enable support for swizzles that do 3D
interleaving. Note that all features of 3D images are supported
with 2D swizzles,it's just that the access patterns are different
and therefore cache hit-rates may be better or worse, depending
on how it's used. Volumetric algorithms do better with 3D and apps
that tend to access a single slice at a time do better with 2D.
Change-Id: Id8574a6710fe4333a1ee331e5ce9195a81434198
[ROCm/ROCR-Runtime commit: 6361466baa]
Replaces WaitAny with WaitMultiple to more closely align with the
underlying driver API for waiting on multiple events.
WaitMultiple adds a single parameter, wait_on_all, to the WaitAny
interface providing a single function for waiting on multiple
events when we only need AND and OR semantics for the signal
checking logic.
Change-Id: I68a4a45d48151d9d69aef02fd8f7263b9e6c0e75
Replaces WaitAny with WaitMultiple to more closely align with the
underlying driver API for waiting on multiple events.
WaitMultiple adds a single parameter, wait_on_all, to the WaitAny
interface providing a single function for waiting on multiple
events when we only need AND and OR semantics for the signal
checking logic.
Change-Id: I68a4a45d48151d9d69aef02fd8f7263b9e6c0e75
[ROCm/ROCR-Runtime commit: 8a38f121ea]
The CWSR area size needs to take into account the size of LDS each
active workgroup can have. The current implementation uses a constant
for that. This patch refactors this to use the HsaNodeProperties of the
device's the CWSR area is for to figure out the size of LDS.
Change-Id: Ib8585b2b7140ec5c99e7b7d62e67f785697c028a
Signed-off-by: Lancelot Six <Lancelot.Six@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
The CWSR area size needs to take into account the size of LDS each
active workgroup can have. The current implementation uses a constant
for that. This patch refactors this to use the HsaNodeProperties of the
device's the CWSR area is for to figure out the size of LDS.
Change-Id: Ib8585b2b7140ec5c99e7b7d62e67f785697c028a
Signed-off-by: Lancelot Six <Lancelot.Six@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
[ROCm/ROCR-Runtime commit: c51aa0d155]
<squashed with patch for gfx950 generic targets>
Signed-off-by: Chris Freehill <Chris.Freehill@amd.com>
Change-Id: Ifec6d93cf46c7fbf736c6572882299e279260af6
Tao Sang
Elwazir, Ammar
Yiannis Papadopoulos
Min Zhou
James Zhu
Amber Lin
Saleel Kudchadker
Indic, Vladimir
Lancelot Six
Trowbridge, Ian
Gerardo Hernandez
Anavena Venkatesh
Shweta Khatri
Tony Gutierrez
Ioannis Assiouras
Marko Arandjelovic
Jacob Lambert
Alex Sierra
David Yat Sin
Vladana Stojiljkovic