Граф коммитов

83 Коммитов

Автор SHA1 Сообщение Дата
Chris Freehill 0878deda17 rocr: Dynamically allocate static global memory
To allow non-POD global variables to last until the last thread
has exited, use "new" to allocate the memory instead of static
allocation.

Change-Id: Ica571b61ff8068a52e472c49cb1c44917e60c8c8
2024-11-07 09:53:31 -05:00
Chris Freehill 9b13bcd0ac rocr: Ensure globals are initialized at first use
When ROCr is built as a static library, global variables
were often not initialized to valid values at their first
use. This change addresses that problem.

Change-Id: I550fa41feb3bc04b9cc686bcfb4acf2a7b651a88
2024-10-16 23:19:48 -04:00
David Belanger 4f453f3bd4 Fix image issue on GFX12
Fix encoding of pitch in SRD (1 bit missing).
Issue affects images with pitch > 8192.

Signed-off-by: David Belanger <david.belanger@amd.com>
Change-Id: Id0b431f51ab3984d1a47d3e8c13d35e28a6009cf
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-07-17 22:32:23 -05:00
Yifan Zhang 71494a920b Add support for GC 11.5.2
Change-Id: Iad8604881dc66108933ac2155fef3b74bca9ac3f
Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:50:03 -05:00
Yifan Zhang 1d1a32d725 GFX1150: remove dupilcated definition of GFX1150
This patch is to remove duplicated definition of GFX1150.

Change-Id: I4a8b8bce5c2721748c4d64e1da13b59feae2139a
Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:41:53 -05:00
David Yat Sin f1a13b6d87 Move addrlib into rocr namespace
This avoids conflicts in case application is loading another copy of
addrlib.

Change-Id: Ifb4a10270c867366d5eed0a8c015257b415189a5
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:41:53 -05:00
David Yat Sin e721eb509b Remove debug bits set in forbiddenBlock
Removing extra bits set in forbiddenBlock that seemed to be set for
debugging and are causing unexpected image formats to be used.

Change-Id: I29c9e319907027a2b0b6bf7c1c0c8558eb6a36f4
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:27:09 -05:00
David Yat Sin cf4b5e1598 Update Addrlib gfx10 files
Update changes to  gfx10 addrlib files from:
https://gitlab.freedesktop.org/mesa/mesa.git

mesa top commit:
4d298673da9b05d826b960eece2e715a6b187330

Change-Id: I6015c827d3e9b1fbde034686432670958f424a1d
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:27:09 -05:00
David Belanger f8a015f53e Implement AddrLib support for GFX12
Add new files image_manager_gfx12.{h,cpp}.

Implement BUF/IMG/SAMP desc changes for GFX12.

Implement compute surface info code using AddrLib3 API (new starting
from GFX12).

Implement algorithm for choosing "best" swizzle mode (starting
from AddrLib3/GFX12, AddrLib provides only list of suitable swizzle mode,
up to client, ROCr, to choose the best).   Algorithm implemented follows
behaviour in GFX11 and behaviour for GFX12 on other platforms.

Signed-off-by: David Belanger <david.belanger@amd.com>
Change-Id: Ib344c86228a98bbac5acdab421ee2ef9b1e84eef
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:27:09 -05:00
David Belanger 8165da63cc Added/Updated header files for AddrLib support (GFX12)
Updated struct definitions, field size changes and new fields in
registers.h.

Added resource_gfx12.h and updated fields in BUF/IMG/SAMP descriptor
structs based on documentation.

Signed-off-by: David Belanger <david.belanger@amd.com>
Change-Id: I08f05ba30f54c40e7b823a6a105829a1e8590b3d
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:27:09 -05:00
David Belanger bb02f4e9a7 GFX12: Update addrlib
Updated address lib to mesa amd-temp-gfx12 branch.
Commit: 6e5244bd3184f0720197270a10e031b5ecd5fe75

Signed-off-by: David Belanger <david.belanger@amd.com>
Change-Id: Icaead4f38c5f3019c375116070b1f97a927f09b0
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:27:09 -05:00
Sreekant Somasekharan 24463635f9 Initial GFX1201 changes.
Add target gfx1201 to several files.

Change-Id: I5cae7dba00ed58f8fbfa6e7147275bd7d5feaed0
Signed-off-by: Sreekant Somasekharan <sreekant.somasekharan@amd.com>
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:27:09 -05:00
David Belanger 2f14acd9c1 Initial GFX12 changes.
Add target gfx1200 to several files.
Add cases for GFX12 in a few switch statements.

Signed-off-by: David Belanger <david.belanger@amd.com>
Change-Id: Ib90032f5b9d5a3306060f13a43d970108a1399df
Signed-off-by: Chris Freehill <cfreehil@amd.com>
2024-06-25 12:27:09 -05:00
Shweta.Khatri bc9cac97fe Fixing compilation errors related to MUSL libc
Fix Musl libc NULL errors and unsupported pthread funcs for compatibility.
Also ensures cleanup and error handling irrespective of CPU affinity override.

Fix submitted by github dev - AngryLoki
https://github.com/ROCm/ROCR-Runtime/issues/181

Change-Id: Ia487315e504112be5d3370756f23f6e23b9ae4be
2024-04-17 07:14:15 -04:00
Shweta Khatri acf9e95027 Revert "Restore default code object version usage for ROCr and ROCr Test"
This reverts commit 6ef7fcedd1290b59190f81df1d25142ecb05d282.

Change-Id: Icc0300c25a89fcb99287d013863a00ace7e12129
2023-12-04 15:03:31 +00:00
Lang Yu 991bbdcf24 Revert "Revert "Add support for GC 11.5.0 and 11.5.1""
This reverts commit ebc51dd0eb.

gfx1150/1151 is merged into mainline now.

Change-Id: Id179949318a37888c74abb5a8610d95bc2f22906
2023-12-04 15:03:31 +00:00
Jonathan Kim 2f847cf05f Restore default code object version usage for ROCr and ROCr Test
Remove override that forces ROCr image blit source and ROCr test to use
code object version 4 now that mainline has been updated to version 5.

Change-Id: I94681e86835c0e382475306ead4cd4132a2ee78f
2023-12-04 15:01:44 +00:00
David Yat Sin 1a7de9588e Add LoongArch64 Support
Patch submitted by user Xinmudotmoe on github

Change-Id: I58fd035b4ec4856f20d63747ababd49fa9764348
2023-10-26 11:36:16 -04:00
David Yat Sin 3ee6c9b0e2 Fix clang compile warnings
Change-Id: Iea9afc3d998a6c5db28af6c7b54939960b11ae95
2023-09-07 12:00:02 -04:00
David Yat Sin ebc51dd0eb Revert "Add support for GC 11.5.0 and 11.5.1"
Reverting this as current mainline compiler branch does not support
gfx1150/gfx1151 yet. Will bring back later.

This reverts commit e877840197.

Change-Id: I31ff4fb2d5817538094a7ffaeba96dd6a7d660c7
2023-07-26 15:03:54 +00:00
Lang Yu e877840197 Add support for GC 11.5.0 and 11.5.1
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Change-Id: I3c4116e78a5c1ddac2389f5fece57485bdb17f68
2023-07-22 16:06:22 +08:00
David Yat Sin 41f6d0426d Adding gfx941 and gfx942
Adding support for gfx941 and gfx942 ISAs.
gfx940 ISA will use sc0:1 sc1:1 on load/store operations
gfx942 ISA will use default load/store operations

Change-Id: If1efbef86f59e2cf2d48fe359cd4166405a0a579
2023-05-23 11:13:16 -04:00
Mike Li bd98a1e5bf Added gfx940 ISA
Signed-off-by: Mike Li <Tianxinmike.Li@amd.com>
Change-Id: Icb1830fe186abc69fe7ee709b7f12b882cab9e87
2023-04-27 16:08:58 -04:00
Konstantin Zhuravlyov f115a3505c Compile image blit kernels with code object v4
Change-Id: I4b1923fe8f22dda1277409794d0856419228eceb
2023-02-02 17:33:15 -05:00
David Yat Sin a4f898ad15 Add env variable to print image SRD contents
Add environment variable HSA_IMAGE_PRINT_SRD to print contents of SRD
registers for image functions

Change-Id: Ifb47a73dcfad8745ee7445e20de96e1021b80bd6
2023-01-13 11:01:04 -05:00
Shweta Khatri e72329ab76 Fixed GFX11 Texture, Buffer and Sampler Resource Descriptor definitions
Change-Id: I101806f9f91ec2ad78339dabc98375bd09946dd0
2023-01-05 15:40:47 -05:00
David Yat Sin b9d1ad8604 Revert "Correct limit query return type to match spec ABI."
This reverts commit 7826d4ca2d.

Changing the parameter sizes breaks backward ABI.

Change-Id: Iff14b7c11294f0931f36fcfd42fff11a492d4205
2022-11-14 19:13:58 -05:00
David Belanger a0d3db6e8d Initial changes for gfx1101, based on gfx1100/gfx1102 implementation.
Change-Id: I949c1027ccabf38b4f924590e42e7327dc550f73
Signed-off-by: David Belanger <david.belanger@amd.com>
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
2022-10-13 09:28:39 -04:00
David Yat Sin 9cb10a3dd8 Fix compile warnings and remove unused variables
Change-Id: I7acaee5e9cf218b358ffaf0e3af6067faf6f3d2a
2022-10-06 10:11:17 -04:00
Sean Keely 7826d4ca2d Correct limit query return type to match spec ABI.
Change-Id: I2eeed1f4b79d10c7d9ab0fd36c0146063053c76a
2022-10-04 01:48:26 +00:00
Lang Yu d0e7c617df Query agent family id from roct
Add agent info query HSA_AMD_AGENT_INFO_ASIC_FAMILY_ID.
Then we can remove the codes to parse family id.

Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Change-Id: I3ac4746d3015e89b32322ebc0f8a3084f98677a4
2022-08-25 10:15:43 -04:00
David Yat Sin 117495fe88 Fix image LUT for gfx11
For gfx11 the image type table has some different values compared to
previous asic families (e.g TYPE_SRGB). Creating a new LUT class to
use these new values.

Change-Id: Ifdfc6cd29bfd5f4ec2643c848fcb9986eb874f9e
2022-08-04 11:23:28 -04:00
Yifan Zhang daa01b8d57 Add gfx1103 support
This patch adds gfx1103 support

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Change-Id: I7f1d580059fcd501bce2c8fea894637960c29bc1
2022-08-04 11:23:28 -04:00
David Yat Sin 574bea4a4c Use FAMILY_GFX1103 for gfx1103
Also adding elf entry

Change-Id: Id47ec379f2880961022b4607eb7f106b7e9d7048
2022-08-04 11:23:28 -04:00
David Yat Sin f971834d7a Update entries for gfx11
Update image table enums and format tables for gfx11.
Remove some entries that are not needed.

Change-Id: I060c1e285925a6d428ef1c5498f5dd89f5d79d97
2022-08-04 11:23:28 -04:00
David Yat Sin 319e71e79f Use FAMILY_GFX1100 for GFX11 devices
Change-Id: Ib182b647a91987040d655dbc05cbe5f867d4f61a
2022-08-04 11:23:28 -04:00
David Yat Sin a742b7e830 Update addrLib to support gfx11
This library was taken from public MESA library:
https://gitlab.freedesktop.org/mesa/mesa/-/tree/main/src/amd/addrlib

with top commit:
2866ae32da0348caf71ad2d11c353321df626ff4

Removing macros.h as it is no longer used by addrlib

Change-Id: I0fdabfe48b74c259b4d29d81beae89604bbc141a
2022-08-04 11:23:28 -04:00
David Yat Sin 90322899fe Update scratch register definitions for GFX11
Update scratch register definitions for GFX11 asics.

Change-Id: I6195e04b0a099fe84d1015c2f34ca3756a8175ef
2022-08-04 11:23:28 -04:00
David Yat Sin 907e05c1b3 Add new ImageManager for GFX11
Adding new ImageManager class for GFX11 GPUs

ImageManagerGfx11 functions copied from ImageManagerNv.
Register descriptions in resource_gfx11.h updated for gfx11.

Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Change-Id: I48b39f6a633aef14aa829f7240a43fe0feb1c290
2022-08-03 10:57:09 -04:00
David Yat Sin cc3bd31591 Add gfx1102 support
Change-Id: I39cbda81a7a999aa2ecfad7a3e720000f7ca3408
Signed-off-by: David Yat Sin <David.YatSin@amd.com>
2022-08-03 10:56:54 -04:00
Graham Sider 446c5e9672 Add gfx1100 support
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: Ic5d5559e43df5c73409ba900a42c6901aabae661
2022-08-03 10:56:49 -04:00
Sean Keely 752cfd5ffd Adjust include paths for new header locations.
Thunk and rocm_smi_lib paths have been updated.

Change-Id: If2948172f8064dd992cbccbc2a80f9161ad4d457
2022-05-09 14:44:32 -04:00
Sean Keely 7f370dd84c Drop build dependency on DeviceLibs.
DeviceLibs is still needed but is found and included by clang now.

Change-Id: I03ff7dc91c028d2ee6747aa1779d223a9ba13915
2022-05-06 01:01:05 -04:00
Yifan Zhang 54c8b7900d add gfx1036 support
Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Change-Id: Ifc1b3cf2e46cf753f57470ebc6b034c1a349d3d2
2022-04-29 17:52:22 -04:00
Sean Keely 7e73760cd0 Revert "add gfx1036 support"
Compiler is not promoted to mainline yet.

This reverts commit 2f97f17df9.

Change-Id: I7256aeb3698ee3ae640a9f457a929abe24d5ef17
2022-03-18 02:35:01 -05:00
Yifan Zhang 2f97f17df9 add gfx1036 support
Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Change-Id: I075779b1369fde759c29572fa2027a3748d6ed4c
2022-03-05 13:16:19 +08:00
Chen Gong dec63b4f15 Correct the gfx version of gfx90c to 90c
Corrections have been made in libhsakmt, and corresponding changes are required here as well.

Signed-off-by: Chen Gong <curry.gong@amd.com>
Change-Id: Ib697ce25278c2c5ac6ef0206930ec285f46c60d1
2022-01-25 19:05:46 +08:00
Sean Keely 322588a60e Add missing return in ScopeGuard::operator=.
This omission did not cause problems earlier due to having not been
instanced.

Change-Id: I7a54f82e06c299902f3bf6b4d3737cc5e30961ad
2021-11-15 18:50:46 -06:00
Sean Keely 2e9a9f7c7a Correct Clang version detection and support for multiple prefix paths.
Bumps cmake minimum version to 3.7 for version comparison operator.

Previously the Clang cmake project version strings were used.  These
are not defined if the clang cmake project has not been loaded.
We should use CMAKE_CXX_COMPILER_VERSION to check the version when
only the compiler binary is redirected and the project files are
not available.

Also adjust device libs lookup logic to handle multiple paths in
CMAKE_PREFIX_PATH.

Change-Id: I67b6958d8241685cd6c3a0af68507c9fdc6331ef
2021-09-20 19:23:04 -05:00
Oak Zeng 80206af91e Add gfx1013 support
Change-Id: I7122caea3ef2254b50bde25ec545116685452116
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
2021-09-15 01:10:20 -04:00