AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
12,664 Commits 3 Branches 0 Tags
8d5fa39c5bbda653673690b8185517750553ca3c
Commit Graph

11946 Commits

Author SHA1 Message Date
Saleel Kudchadker 8d5fa39c5b SWDEV-365820 - Refactor build path 
This is an initial change before we refactor the build/link paths for
kernel launches for HIP. This current change is needed as compiler was
setting some dump file which needed fs access which has slowdowns for
NFS mounted file systems

Change-Id: I828f9bb04d789b4f8c05c1ed08767f325efeb47c


[ROCm/clr commit: 3f2f7252aa]
 2024-01-04 14:20:59 -05:00
David Salinas ecc933301a Enable support for roc-obj tools on Windows 
SWDEV-301785 - roc-obj - support for Windows COFF

Change-Id: I20d53196e2d126391934351cb824b7bc926fb1ce


[ROCm/clr commit: 9fa8dcd1d1]
 2024-01-04 10:31:02 -05:00
Ioannis Assiouras 30471a9fd9 SWDEV-438299 - Simplified the code in ExtractFatBinaryUsingCOMGR 
Change-Id: Ic15f2b71ae87ab3ca36ed5af2c816d57d09b3e70


[ROCm/clr commit: 411bccff5b]
 2024-01-04 04:01:58 -05:00
Ioannis Assiouras 1c3e482bd4 SWDEV-438531 - Fixed hipGraphExecMemcpyNodeSetParams for H2H kind 
The function erroneously returns hipErrorInvalidValue when kind
is set to hipMemcpyHostToHost

Change-Id: I6810b9f04f3218e517fd2f96410d1375e6ac6ff0


[ROCm/clr commit: af86c1b8a2]
 2024-01-04 03:47:39 -05:00
Satyanvesh Dittakavi d1901f2017 SWDEV-434846 - Limit the gpu single allocation percentage for all MI300 versions 
Change-Id: I33dea3eaab249ce3f9a624d38267489f99cd530c


[ROCm/clr commit: 755eb2962c]
 2024-01-03 23:47:44 -05:00
German Andryeyev b8e7a858a5 SWDEV-311271 - Switch to sorted map for pool allocations 
Sorted map can work much faster for many allocations and a low reuse frequency

Change-Id: I6dba29ebc8bfacdf34307149b6a2b194890b2932


[ROCm/clr commit: a1fffac595]
 2024-01-03 17:36:05 -05:00
shadi f318f0f7e6 SWDEV-388256 - correct API name 
Signed-off-by: shadi <shadi.dashmiz@amd.com>
Change-Id: Icbf79613268fe0737a8033abfbcc9f33d785bc12


[ROCm/clr commit: a071c4d2fc]
 2024-01-03 15:06:41 -05:00
Saleel Kudchadker dfb1087c3e SWDEV-422207 - Tag captured kernel names for graphs 
Change-Id: I9540daa4abf9c340541a681037e2dca4eec821ed


[ROCm/clr commit: dfd4635f91]
 2024-01-03 11:50:05 -05:00
Konstantin Zhuravlyov 326372ce2d Don't pass -fsc-use-buffer-for-hsa-global option in OCLPerfUncoalescedRead test 
- This is an SC-only option

Change-Id: If9afe5f8e4ec6dbcf6ce1ca4406131ef92669f84


[ROCm/clr commit: 55e5b3d07a]
 2024-01-02 23:13:45 -05:00
Jatin Chaudhary 937678b4f6 SWDEV-436233 - fix the cumode in hiprtc 
cumode should be active when wgp mode is off

Change-Id: I12f2e55d942ddeb0fb4470de7abc3caff1f430f7


[ROCm/clr commit: 49369f0851]
 2024-01-02 17:43:32 -05:00
German 4750a76899 SWDEV-404889 - Enable debugger interface in PAL 
Add GPU_DEBUG_ENABLE to control ttpm behavior. If enabled,
then HW will collect more debug info at some perf cost

Change-Id: Icee0686b903a7b1bd483710b9d611877cd43c6aa


[ROCm/clr commit: 7d661bc7df]
 2024-01-02 11:51:42 -05:00
Satyanvesh Dittakavi f423584145 SWDEV-379212 - Handle template kernels with hiprtc lowered names 
Change-Id: Ib8e6493a1f342f92a35031d5ee39b2e22132b56a


[ROCm/clr commit: dc8f66b86f]
 2024-01-02 03:28:28 -05:00
Jaydeep Patel 5f13c16039 SWDEV-437440 - Specify which defination to use at compile time. 
Change-Id: Ibeee914f293d26fa68ab793cac8b662aa34e8df3


[ROCm/clr commit: c3fc607e7d]
 2023-12-21 19:59:39 -05:00
Konstantin Zhuravlyov 4abdfe5489 Removed some options 
-xnack, -force-wgp-mode, -force-wave-size-32, -round-trip-spirv,
-fe-gen-spirv, -lower-pipe-builtins=0|1, -lower-atomics=0|1,
-set-lds=<value>, -set-scalar-registers=<value>,
-set-vector-registers=<value>, -limit-scalar-registers=<value>,
-limit-vector-registers=<value>, -sc-xnack-iommu,
-faa-for-barrier/-fno-a-for-barrier, -sc-dev-format, -verify-lwspir,
-verify-hwspir, -ffma-enable/-fno-fma-enable,
-fmad-enable/-fno-mad-enable, -fdisable-avx/-fno-disable-avx,
-fforce-llvm/-fno-force-llvm, -print-compile-phases,
-kernel-cache-enforce-miss, -kernel-cache-wipe, -kernel-cache,
-sc[=<filename>]/--load-sc-dll[=<filename>],
-be[=<filename>]/--load-be-dll[=<filename>],
-cg[=<filename>]/--load-cg-dll[=<filename>],
-link[=<filename>]/--load-link-dll[=<filename>],
-opt[=<filename>]/--load-opt-dll[=<filename>],
-fe[=<filename>]/--load-fe-dll[=<filename>],
-cl[=<filename>]/--load-cl-dll[=<filename>], -just-kernel=<kernel-name>,
-use-debugil, -fmulti-level-call/-fno-multi-level-call,
-fdebug-call/-fno-debug-call, -fmacro-call/-fno-macro-call,
-fstack-uav/-fno-stack-uav, -fdef-res-id/-fno-def-res-id,
-wokth=int/--waves-opt-kernel-threshold,
-ilkth=int/--inline-kernel-size-threshold,
-ilsth=int/--inline-size-threshold, -ilcth=int/--inline-cost-threshold,
-scopt=int/--sc-opt-level, -flib-no-inline/-fno-lib-no-inline,
-fuser-no-inline/-fno-user-no-inline,
-scras=int/--sc-si-opt-reg-alloc-strategy, -fsc-post-ra-sched,
-fsc-live-sched/-fno-sc-live-sched, -fsc-use-buffer-for-hsa-global,
-fsc-schedule-no-reorder, -fsc-min-reg-schedule,
-fsc-bias-schedule-to-minimize-insts,
-fsc-bias-schedule-to-minimize-regs, -fsc-disable-merge-memory,
-fsc-disable-loop-unroll, -fsc-use-mubuf/-fno-sc-use-mubuf,
-fsc-selective-inline/-fno-sc-selective-inline,
-fsc-keep-calls/-fno-sc-keep-calls, -slc=0|1/--simplifylibcall,
-stack-alignment=<n>, -fdiv2fmul=0|1, -prt-opt-liveness=0|1,
-liveness=0|1, -SRAE-threshold=<value>, -memcombine-max-vec-gen=<value>,
-small-global-objects, -fast-fmaf, -fast-fma, -bfo=0|1, -ebb=0|1, -aa,
-mem2reg=0|1, -licm=0|1, -unroll-allow-partial,
-unroll-threshold=<positive integer>, -unroll-count=<positive integer>,
-apt/--ap-threshold=<positive integer>, -srt/--sr-threshold=<positive
integer>, -fdebug-linker/-fno-debug-linker, -fbin-gpu64/-fno-bin-gpu64,
-fbin-disasm/-fno-bin-disasm, -fbin-bif30, -fbin-hsail/-fno-bin-hsail,
-fbin-amdil/-fno-bin-amdil, -fbin-spir/-fno-bin-spir, -fonly-bin-source,
-fper-pointer-uav/-fno-per-pointer-uav

Change-Id: I1af5b0a11b55bf75b727057143159fbbf1bb8f0e


[ROCm/clr commit: 15b8cf911a]
 2023-12-21 10:18:37 -05:00
Anusha GodavarthySurya 67bb022698 SWDEV-422207 - Fix simple graph test when DEBUG_CLR_GRAPH_PACKET_CAPTURE flag is enabled 
- For new AccumulateCommand we enqueue nop barrier packet. So during stream sync we need system flush.

Change-Id: I0b97b626bcdae582ef95e7c95030d78df1fa5a54


[ROCm/clr commit: 748c6b3520]
 2023-12-20 22:50:36 -05:00
Anusha GodavarthySurya b10799a7e7 SWDEV-351966 - Rename hip::__hipExtModuleLaunchKernel to hip::hipExtModuleLaunchKernel 
Change-Id: Ie922760f37bf0c9abf2653d36e32705a12ab5a90


[ROCm/clr commit: 9b6cf0f74b]
 2023-12-20 22:50:01 -05:00
kjayapra-amd 30d6b89d6f SWDEV-413997 - Enable Virtual Mem support by default. 
Change-Id: Ia3db3919701708cf95574692e1d47375ca99d7fd


[ROCm/clr commit: e05923b139]
 2023-12-20 12:49:16 -05:00
Alex Xie 15756659d0 SWDEV-438177 - move ldconfig to amd opencl package instead of icd 
Change-Id: I2486f38d398a508ead7d24f03d4cf7816d5c157c


[ROCm/clr commit: 06ff62da61]
 2023-12-20 10:04:58 -05:00
Ioannis Assiouras 7c08efde2a SWDEV-438299 - Fixed out of bounds memory access in ExtractFatBinaryUsingCOMGR 
Change-Id: Ib1c6a38da0b81b78d250d7fb88d1194864a0251d


[ROCm/clr commit: 5158ec1c00]
 2023-12-20 04:17:40 -05:00
German Andryeyev 3a4261966c SWDEV-311271 - Release freed memory from MemPools 
Runtime has to release extra memory, held by the pools,
in synchronization points for event, stream or device.

Change-Id: Id533a5e1d137812aa72bdfe101b4b333c6a43d66


[ROCm/clr commit: 3fa4e31180]
 2023-12-19 13:47:04 -05:00
German e6578eda9c SWDEV-1 - Promote PAL verison to 843 
Change-Id: I2b8d2fd1df61b376598da53bef530243f8d6e757


[ROCm/clr commit: adf9406a16]
 2023-12-19 10:25:32 -05:00
Rahul Garg 0051334261 SWDEV-388256 - Add support of hipExtGetLastError 
Change-Id: Ie119d5ea611019996b8a80f7b820ca6a160496a6


[ROCm/clr commit: 92aa9d0fba]
 2023-12-18 22:03:22 -05:00
Ioannis Assiouras e51c2f6097 SWDEV-437817 - Fix hipMemCpy2D case that erroneously fails with invalid argument error 
When an offset is applied to the source or destination pointers plus the kind is set to
hipMemcpyDefault and the source or destination is allocated with hipMallocManaged
hipMemCpy2D erroneously fails with hipErrorInvalidValue.

Change-Id: I0db4c17514f743652d8f9a2691da6601a2abb2a1


[ROCm/clr commit: d3bfb55d7a]
 2023-12-18 07:31:56 -05:00
Anusha GodavarthySurya 5355857116 SWDEV-436405 - Move hipChooseDevice out of hip namespace 
Change-Id: I47a3cc5e5409f418b282d1a2e250128c769f4778


[ROCm/clr commit: 4a7291ded8]
 2023-12-18 04:37:39 -05:00
taosang2 75b68c4989 SWDEV-435296 - Fix sporatic segment fault 
Fix sporatic segment fault in texture test
via retaining image in texture object which
references the image.
The image will be released when the texture
object is destroyed.

Change-Id: Ic3fefa2d5dda6afebd1acd4d41ad310b138af6dd


[ROCm/clr commit: d6d235a111]
 2023-12-15 21:06:20 -05:00
Ioannis Assiouras d45267dd2a SWDEV-433745 - Added demangled symbol for hipExtModuleLaunchKernel 
Change-Id: Ib8051fcbdf0c8c99e97c845b777d6562220701a0


[ROCm/clr commit: fe739047e5]
 2023-12-15 16:59:40 -05:00
German Andryeyev 67597f4901 SWDEV-436869 - Destroy host memory 
Recent changes disabled system memory allocation
in the abstraciton layer. That requires memory
allocation/destruction in ROCR. Add destruction logic.

Change-Id: I68fe6b0a620ca743fe5850052ea0efa8bb7931c2


[ROCm/clr commit: a6d480e098]
 2023-12-15 16:39:41 -05:00
kjayapra-amd 6a36bf3b30 SWDEV-413997 - Alignment should be a multiple of device granularity. 
Change-Id: Ie9c636385bbe3139c2dc24c16f31c9d5e2d56b95


[ROCm/clr commit: f9fd5f4049]
 2023-12-15 13:27:23 -05:00
German cba839f38d SWDEV-436796 - Enable device memory for kernel arguments 
Extra CPU read back will be performed before every submission to make sure
previous writes over PCIE reached GPU. HDP flush is done by CP.

Change-Id: I402d28ca26c8cee4a3920feb3599af8c285d0889


[ROCm/clr commit: cfc07c88ee]
 2023-12-15 13:11:50 -05:00
German fa8e88b108 SWDEV-432575 - Disable direct map for persistent memory 
Persistent memory should use direct access for write map and
indirect for read map.

Change-Id: I9fc84836d60088b24012ed25f7ef8c16e33796a3


[ROCm/clr commit: c8b3253a24]
 2023-12-15 10:59:01 -05:00
Rahul Garg a7971d31f9 SWDEV-422771 - Update links of ROCm projects 
Change-Id: I211308814adce86549ce327ed0a823f799b3de03


[ROCm/clr commit: 35ce9f81d8]
 2023-12-15 08:09:21 -05:00
Anusha GodavarthySurya 01c89b94cd SWDEV-436405 - Add hipGetDevicePropertiesR0000 and hipChooseDeviceR0000 to hip dispatch table 
Change-Id: I5b373ac030502eb88477d20a1d216bc48369b51d


[ROCm/clr commit: 3e72b8d1e1]
 2023-12-15 06:26:52 -05:00
Jaydeep Patel 526e60cb70 SWDEV-411343 - Import VK buffer memory exported by name. 
Change-Id: Idc7c840fcd6bf758ecc29ffd6558d24e5bd0a25b


[ROCm/clr commit: 9551d48e7f]
 2023-12-14 22:16:11 -05:00
jiabaxie 32b402f11a SWDEV-435477 - correct MACH IDs and add strx1/halo and krackan support for hip 
Change-Id: I5b7ed449f4755d69f10677b90ab2b0ceae050b3d


[ROCm/clr commit: f80985f6a1]
 2023-12-14 13:07:03 -05:00
kjayapra-amd 9a53a2bec3 SWDEV-413997 - Fixing MGPU cases on PAL side by passing Global Context to virtual alloc. 
Change-Id: I6614058d1456d199d710b12acd95160a79aa48c8


[ROCm/clr commit: ec010e4d2d]
 2023-12-14 11:34:32 -05:00
German 7883f1e6f7 SWDEV-430809 - Replace hipErrorSharedObjectInitFailed vs hipErrorNoBinaryForGpu 
hipErrorSharedObjectInitFailed should be used for interop objects.

Change-Id: Id3bcffaac3b511021f2fd57e9b156a897b646db0


[ROCm/clr commit: 68d442f29a]
 2023-12-14 10:35:10 -05:00
sdashmiz 25a8281952 SWDEV-421021 - move new fn pointers to end of the file 
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I98d2379b3ef90282de64b22138b1dedcc3586a1b


[ROCm/clr commit: 3a6e1b8fc5]
 2023-12-14 09:15:07 -05:00
Sameer Sahasrabuddhe 4cf2b1cfd1 SWDEV-437090: move the __hip_assert macro to a common place 
It cannot be moved to amd_device_functions.h because that causes circular
dependences when trying to use the macro in other files. So we create a new
header and move all assert/abort macros to that common header.

As a side-effect, also fix the macro to correctly expand the entire condition
argument, and also consume the trailing semicolon.

Change-Id: I43688c8e61183503a3a1a039b91321a3779152af


[ROCm/clr commit: 7137a296dd]
 2023-12-14 09:03:14 -05:00
Anusha GodavarthySurya 3789c40cb5 SWDEV-422207 - Fix graph catch tests with graph optimizations(DEBUG_CLR_GRAPH_PACKET_CAPTURE enabled) 
Change-Id: I16297e0ddde286bf1798c90f2bf846e69819010d


[ROCm/clr commit: 2bb2446d8f]
 2023-12-14 01:27:08 -05:00
German Andryeyev 7130b87d5c SWDEV-436859 - Enable pitch for COPY_HOST_PTR 
Original logic didn't use pitch because, abstraction layer had
a sysmem copy without pitch. Since extra sysmem copy was
disabled, the code has to accept pitch values from the app.

Change-Id: Ia9fba7b33ddff4e9109b4e63d0d6afa52f501c8f


[ROCm/clr commit: fb3dfcf889]
 2023-12-13 16:50:16 -05:00
Mark Searles 8b94eaf0a6 SWDEV-435276 - Use -mllvm=<option> syntax rather than -mllvm <option> syntax 
Separating -mllvm from its option can cause, in rare circumstances,
the option to be dropped. Or the mllvm to be dropped. Either of which
can cause a compilation error. This issue was exposed investigating
SWDEV-435276

Change-Id: Ie665d49183b55a57c9b58619cad525e44f3be8a5


[ROCm/clr commit: 704d5df91b]
 2023-12-13 13:32:51 -05:00
sdashmiz 5e1985996c SWDEV-421021 - Add hipDrvmemsetnode for graph 
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I0240a162a16e61549d46b5d086c831404550e833


[ROCm/clr commit: b8e820f835]
 2023-12-13 09:30:36 -05:00
Jatin Chaudhary 7fb95958d9 SWDEV-434226 - populate correct output in mempool supported handle type query 
Change-Id: Iabbf9c0b54d9978671e3492f13660917499a03fa


[ROCm/clr commit: d5e596c975]
 2023-12-13 04:40:41 -05:00
Satyanvesh Dittakavi 542044aadc SWDEV-434846 - Correct the vgprs per simd for MI300 
Change-Id: Id4862da7611f64392bfc1538fb644801ec0a9e7f


[ROCm/clr commit: b2102fe939]
 2023-12-13 03:06:21 -05:00
Jatin Chaudhary 1114efcc0d SWDEV-431399 - use x86 intrinsics only x86 platforms 
This was highlighted by github issue:
https://github.com/ROCm-Developer-Tools/clr/issues/32
On RISC-V platforms this header might not be present.

Change-Id: I5f0959a7b281c760802e76541d50693d1a3902be


[ROCm/clr commit: 12461dbd6a]
 2023-12-12 19:10:50 -05:00
Jatin Chaudhary 761f932275 SWDEV-431315 - mark stack as non executable in hiprtc generated header 
Reference: https://wiki.gentoo.org/wiki/Hardened/GNU_stack_quickstart

Change-Id: I66860eb3787b8c835c52168dcf7a084982f0d7e6


[ROCm/clr commit: 14cbd8d24c]
 2023-12-12 18:56:51 -05:00
Jatin Chaudhary bb93a976d4 SWDEV-430619 - copy uuid via memcpy 
If uuid is copied via strncpy it will stop at first null character. We
  need to copy all 16 bytes which might have a null on windows.

Change-Id: I8667919cb251133eec3333a23768c356879727e8


[ROCm/clr commit: db909b2a1e]
 2023-12-12 04:09:05 -05:00
Alex Xie 5aaa498e45 SWDEV-434373 - Add icd config to opencl package 
Change-Id: Id2d143ae82b0fa4d5321912fca9daa1e958f1fb6


[ROCm/clr commit: 5a3c4ea49d]
 2023-12-11 11:17:37 -05:00
German fe71f14732 SWDEV-434241 - Replace size_t with uint64_t 
The kernel accepts uint64_t, but with 32bit OCL build size_t was 32 bit

Change-Id: I6fe37d2e5e69c7bd62d7b1bd4cace758758b3482


[ROCm/clr commit: b3171d08e6]
 2023-12-08 16:56:29 -05:00
Todd tiantuo Li c7abb07c97 SWDEV-422544 - Use hipDeviceAttributeUnifiedAddressing as APU flag 
Change-Id: If718a20f62f0ba8d83c01a0b2d16ff3f706f7bd4


[ROCm/clr commit: b825decd42]
 2023-12-08 11:40:34 -05:00