f7c3760996
SWDEV-389199 - Add GL Memory object to memory map so that it is acknowledged by getMemoryObject.
...
Change-Id: Ia58bc30ba8be016c1f004f6af01dd767f45f7905
[ROCm/clr commit: 97dc73f581
2023-05-18 01:10:33 -04:00
9eda493469
SWDEV-399734, SWDEV-399733 - update maxGridDim for y and z
...
Change-Id: Id5b1dd2491798dd20a0672362f445ab4de164f6d
[ROCm/clr commit: fb82b292c2
2023-05-17 19:03:04 -04:00
915677e9a0
SWDEV-396533 - correct _shfl function to match cuda
...
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I311419fd25c055339f25fe0c7a132ec9ee225600
[ROCm/clr commit: 23e99dbb07
2023-05-17 14:19:46 -04:00
f7a7997c66
SWDEV-346940 - Remove default AMDGPU_TARGETS
...
hipcc and clang++ both have logic to detect the installed hardware
and to automatically select the appropriate AMDGPU target when it is
left unspecified. When the AMDGPU_TARGETS property is initialized with
a set of default values, it results in the addition of an explicit set
of --offload-arch flags being passed. These explicit architecture flags
disable the architecture autodetection in the compiler.
The resulting behaviour from setting fixed defaults makes it unpleasant
to compile with CMake because they increase the build times for projects
unless they are overriden (as most users do not need to build for all
five default architectures). The fixed defaults are also troublesome for
users with hardware not included in the default set (e.g., gfx1011,
gfx1031, gfx1100).
A possible alternative might be to detect the architecture within
hip-config.cmake rather than running the detection logic on each
compiler invocation. However, this approach is simpler.
Change-Id: I9495d766b7eed03852eb4dc72b0aabe4100bc32c
Signed-off-by: Cordell Bloor <Cordell.Bloor@amd.com >
[ROCm/clr commit: e1bed6f354
2023-05-16 16:35:09 -06:00
82e044cb6a
SWDEV-399851 - Add template overload for ToString in HIPRTC
...
HIPRTC_INIT_API can have nullptr in the arguments and ClPrint
can crash while printing
Change-Id: Iecade5c3867196509c8cc0647b9aa24be0960a02
[ROCm/clr commit: c98fad1edc
2023-05-16 14:21:19 +00:00
9e5b96d567
SWDEV-384013 - Print link options being passed to compiler with AMD_LOG_LEVEL
...
Change-Id: I556ed434587cff07a634796da51dcbb9ae78ef21
[ROCm/clr commit: 8753db5446
2023-05-15 15:52:04 -04:00
8d0b25334b
SWDEV-395773 - Fix unordered compare functions in fp16 header
...
Change-Id: I9158420e37cd3151159182223c6645ed84c4fddd
[ROCm/clr commit: 15bafc9a93
2023-05-11 10:42:13 -04:00
69d6e8873d
SWDEV-367537 - Add __hip_bfloat16 and vector definitions to match __nv_bfloat16
...
Change-Id: I1c0f9f5f278c2c3b4e175d9f08831ba458ed856e
[ROCm/clr commit: 6c793ea206
2023-05-11 04:45:13 -04:00
cb3642e26e
SWDEV-398047 - Disable arena for XNACK.
...
Change-Id: If6c98490bd5b8146a357f45ed132f687def0877f
[ROCm/clr commit: ffa1deef27
2023-05-10 23:28:05 -04:00
130f9c5117
SWDEV-399203 - Use clang pragma only with clang
...
Change-Id: I21d84ccde07e243b6bc06f1980c24b399e74d1c3
[ROCm/clr commit: a7041d15a7
2023-05-10 04:19:51 -04:00
c22413efba
SWDEV-380857 - Fix bug when reading bitcode file into vector<char> buffer
...
The previous implementation using std::copy() resulted in
differences between the in-memory and on-disk representations.
With the updated implementation, we get the same contents.
Change-Id: Iadfae3cd7f7ba99538da2ac4f11f30f5a78260d8
[ROCm/clr commit: b17056cb93
2023-05-08 16:25:01 -04:00
8d97827417
SWDEV-353281 - VM support in mempool for graphs
...
The change enables VM support in graphs on Windows. That allows
to avoid caching of all allocations at the cost of map/unmap
overhead during memory create/destroy.
Change-Id: I792be00fba099e5e5d3cd44a963e1dfd6976a86d
[ROCm/clr commit: 04b696abee
2023-05-05 15:31:26 -04:00
23584feba4
SWDEV-393910 - Port gfx94x changes to mainline.
...
Change-Id: Ibf727223bbe5230b132b47c39e0fc1d87cbd3b9c
[ROCm/clr commit: f14e8a2dba
2023-05-05 15:16:23 -04:00
2e9767d073
SWDEV-394488 - cudaStreamGetCaptureInfo_v2 is undefined in CUDA 12.0
...
hipStreamPerThrdCompilerOptn.cc test fails to build with cudaStreamGetCaptureInfo_v2
in CUDA 12.0.
fix was to change runtime API cudaStreamGetCaptureInfo_v2
to Driver cuStreamGetCaptureInfo_v2
Change-Id: I44a0110770d3246f5345092acae301c9a2f6d520
[ROCm/clr commit: 0aa70ee0e1
2023-05-05 10:10:07 -04:00
d43e7a2db1
SWDEV-396277 - Offset and bit size correction, Considaration of SA ID for Navi.
...
Correct sm id formula for GFX10 and GFX11.
Change-Id: I2883c139b8e684e0334ccc81f703a09e3ddec588
[ROCm/clr commit: a167abefe5
2023-05-05 01:04:42 -04:00
7adb0089c6
SWDEV-397356: Move HIP_API_PRINT after HIP_INIT so that the begin function call gets printed
...
Change-Id: I99b655596741c19bc483647794ae8b4f6e6f2843
[ROCm/clr commit: d88f0358b0
2023-05-04 18:46:21 -04:00
145506e067
SWDEV-398511 - Removed hiprtc_internal.hpp
...
Change-Id: Ic0751dfeb4936b3e233b44e34d16e0a1605874d7
[ROCm/clr commit: 29e0d2f335
2023-05-04 16:50:18 +01:00
91f676904b
SWDEV-393199 - Added new include file for opengl interop mappings for nvidia
...
Change-Id: I2e955a9dd06539939188a5f2e1dde4f173af1202
[ROCm/clr commit: 633e720da4
2023-05-03 19:43:24 -04:00
69406243e2
SWDEV-378006 - Adding a new guarantee macro to support printing args.
...
Change-Id: I2083ddaf8058759bdace7d3bb1e8e3670cbeddd2
[ROCm/clr commit: 7f41a96ffb
2023-05-03 12:43:16 -04:00
ebc60d68a8
SWDEV-396574 – Refactor texture channel type checking
...
Create __hip_is_tex_surf_channel_type to replace
__hip_is_tex_channel_type
__hip_is_itex_channel_type
__hip_is_surf_channel_type .
Change-Id: I1692b92d417bad742d562679f218ebf8ca532e31
[ROCm/clr commit: 381e6520d0
2023-05-02 10:01:13 -04:00
505bce23be
SWDEV-369567 - dimension check update
...
Change-Id: I31deb5070d4852db7dd6d37f9a514965f387698e
[ROCm/clr commit: 31b362bf6e
2023-05-02 08:04:04 -04:00
646af29dc5
SWDEV-1 - Fix incorrect SGPR usage in VGPR calculation. Pointed out by #58 issue on hipamd public repo
...
Change-Id: I8c27c0da254521714c92369990aa10f6fc09c246
[ROCm/clr commit: 54f73e430b
2023-05-02 03:53:18 -04:00
fa88970f6a
SWDEV-395559 - Move unsigned short up.
...
Change-Id: I3373a7bc22e632dc10b94b93ff023444d456b2b7
[ROCm/clr commit: cbd91bdc19
2023-05-02 00:43:36 -04:00
3a37f33e4e
SWDEV-396574 – Refactor device mapping functions
...
Refactor mapFrom(), mapTo(), mapElem(),
__hip_is_surf_channel_type() and
__hip_is_itex_channel_type()
Change-Id: I1692b92d407bad742d562678f218ebf8ca532e91
[ROCm/clr commit: 2f2d02649f
2023-05-01 13:57:10 -04:00
ebcab6e910
SWDEV-360031 - Correct APIs behaviour
...
- correct error for hipStreamWaitEvent when event recorded before
capture
- correct hipEventSync when event is synced during capture
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I7ecbed5621eaf323846d4ccb20ec112aaa8a5757
[ROCm/clr commit: 544318fffe
2023-05-01 13:38:59 -04:00
858a32a24a
SWDEV-374386 - hipGraphAddMemcpyNode negative cases
...
validate 3d memcpy params -
pitch, extend - height/width/depth, src/dst offsets and total size
Change-Id: I629fc242264ebbc3e9dbfd9233da8d3a127500b4
[ROCm/clr commit: 22eae6ac9e
2023-04-28 12:11:24 -04:00
01c24e04f3
SWDEV-1 - Search for doxygen config in old and new locations
...
Change-Id: Iebe7295c7200cc164cb32047df96aa70dec75bf4
[ROCm/clr commit: ccad05fe01
2023-04-27 04:57:12 -04:00
b2525dfb82
SWDEV-381627 - Move cl_vk_amd.hpp into rocclr
...
Rename VK interop to ExternalMemory object, since it should handle
DX interops also
Change-Id: I536ec46d3e53ece35234a2e29030393ad411b96d
[ROCm/clr commit: 3e5803c4c0
2023-04-26 15:25:01 -04:00
a00b618051
SWDEV-395413 - Fix fp16 header errors with -Werror in hiprtc
...
Change-Id: I7875b91758e826b439c67ac9f211a20f9b6133f0
[ROCm/clr commit: a67f354cec
2023-04-26 13:05:20 -04:00
898340aaa9
SWDEV-392367 - Fixes hipMemGetAddressRange returning device buffer size as 0
...
Change-Id: I6b5640b544390b2dfc53fad271acc7f30240e274
[ROCm/clr commit: 7aba1cf4cd
2023-04-25 13:46:52 -04:00
6b364523bd
SWDEV-389647 - SWDEV-388950 - Check device id same while set params.
...
GraphMemcpyNodeSetParamsFrom/ToSymbol APIs neew to check device id for
original src/dst is same as what is passed in while set.
Change-Id: If0b610808223dce9115562bb5e9b31c8eaa2df22
[ROCm/clr commit: b6aa27d4a3
2023-04-25 13:24:26 -04:00
44c74a77d2
SWDEV-390626 - Fix wrong mapping functions
...
Remove wrong functions
__hipMapFromNativeFloat4()
__hipMapToNativeFloat4()
Replace them with mapFrom() and mapTo()
Change-Id: I1692b92d397bfd732d562778f918ebf8ca532e93
[ROCm/clr commit: 650b6767c4
2023-04-25 13:19:00 -04:00
ca2d9bfbff
SWDEV-353281 - Don't add the same stream into the list
...
Change-Id: I7f41de68b669dc759bdb11657dd897ad57e368fc
[ROCm/clr commit: 31697779bb
2023-04-25 10:21:55 -04:00
0ddd82a5f7
SWDEV-367145 - adding support for timeline semaphore
...
Change-Id: I654359b48abe8bbaac2def5118d3ad0bb05d9492
[ROCm/clr commit: afa15ddb89
2023-04-25 10:02:43 -04:00
8e2c75defb
SWDEV-387508 - do not treat uuid as string
...
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I4de88330650eba4e4259686cdb5fb089b17aa8e4
[ROCm/clr commit: 261ce9837c
2023-04-25 09:52:12 -04:00
b373c0d221
SWDEV-390597 - Return No Device error for hipSetDevice and hipSetDeviceFlags.
...
Change-Id: I457b1197a8f1b71a8bbbdf09f193f643c61700b6
[ROCm/clr commit: 3dfe48b582
2023-04-24 03:50:33 -04:00
e404ad7bd8
SWDEV-389648 - Find node and then erase.
...
Change-Id: Iecf78fe6b0645e58b4de6658b59ad1285946b698
[ROCm/clr commit: 3c5888922e
2023-04-19 01:05:58 -04:00
3bab75e327
SWDEV-389477 - Check D2D is intra device.
...
Change-Id: Ibef2a6de82a18357ef35bcd70298478de6b0e380
[ROCm/clr commit: 415fb15c76
2023-04-19 01:01:12 -04:00
2536d245f6
SWDEV-388943,SWDEV-388954 - Corrected validations for memcpy kind.
...
Change-Id: I8338111ac46e4eba279d53969d12df3a23552049
[ROCm/clr commit: 2576153acd
2023-04-19 01:00:50 -04:00
e257db8ba7
SWDEV-388958 - SWDEV-388929 - Kind can be hipMemcpyDefault for H2D and D2D and srcMemory can be allocated using hipHostMalloc for H2D.
...
Change-Id: I187ff850ebb890b357ee03500105b71468508ea2
[ROCm/clr commit: 7215451db9
2023-04-19 01:00:28 -04:00
97726d4215
SWDEV-391731 - Check thread local list too.
...
With global flag, In addition to global vector, we need to check
thread local vector too. If both of them are empty then only
return false.
Change-Id: I3a24d16a35c702b34b9a8867dc410ebd80108f25
[ROCm/clr commit: 09a081235c
2023-04-19 01:00:09 -04:00
06bc6d9980
SWDEV-391178 - Extern monitor to avoid copy in multithreading.
...
Defining monitor in header cause copy and hence it's moved to cpp.
Change-Id: Ib07bbde2808d9cb2af9349076f777e8a5b28d210
[ROCm/clr commit: e8eb1772f2
2023-04-19 00:58:49 -04:00
82219d2fb1
SWDEV-366992 - adding handle type for vk interop
...
Change-Id: I79ee0d89b948c21b96709e9e607abe7901621a97
[ROCm/clr commit: 78de2ae692
2023-04-18 16:59:25 -04:00
a6f2ecd703
SWDEV-231145 - Add a validation for uniform launch
...
Change-Id: I68d61690c50060d9dcca117b248dddf69204a23f
[ROCm/clr commit: e82eecf33e
2023-04-18 12:56:09 -04:00
237480711a
SWDEV-382359 - Workaround a non-uniform launch in MIOpen
...
Change-Id: I0abff25fb20143225739e771c4d3bae5c2a054b9
[ROCm/clr commit: 73698479a9
2023-04-18 11:36:10 -04:00
53dcdf2b46
SWDEV-393060 - Address directed tests build failures with CLR
...
Change-Id: I76b93ee073d21ec5fae0db5a129ada89f750855d
[ROCm/clr commit: a3104c60e1
2023-04-14 03:53:51 -04:00
369f587081
SWDEV-393406 - hip catch/directed tests on nvidia
...
fix the duplicate symbolic link issue
Change-Id: I472dfba80263d0f1d275d8e149007322c8af3f7c
[ROCm/clr commit: e5a300f892
2023-04-10 19:54:23 +00:00
4eaa9fa01a
SWDEV-361630 - clr to be able to build hip directed tests
...
Change-Id: I85b45c52573683a963ac2b4ee0ec7c79653ecc4d
[ROCm/clr commit: 5e9545fdfd
2023-04-07 14:21:34 -04:00
c1be6ffca3
SWDEV-351540 - ASAN packaging for hip
...
Package ASAN libraries and license file
Suffix "asan" added to package name
Change-Id: Ia02bb55be0bd415dbd372b39ce884c38d8c3dcbf
[ROCm/clr commit: 267b342523
2023-04-07 11:54:48 +00:00
769f1e166e
SWDEV-390626 - Support surface Apis
...
Change-Id: I1691b82d597bfd722d562778f919ebf8ca530e90
[ROCm/clr commit: 53742adc08
2023-04-05 16:38:04 +00:00
Jaydeep Patel
pghafari
sdashmiz
Cordell Bloor
Satyanvesh Dittakavi
Jatin Chaudhary
Jacob Lambert
German
kjayapra-amd
Ajay
Ioannis Assiouras
taosang2
Maneesh Gupta
Sourabh Betigeri
Ranjith Ramakrishnan