The older compiler does not promote integral
arguments to double, instead it uses float.
This patch tries to support the old compiler
headers, and also the newer one.
Change-Id: I01e0b96a82ecddc6230cb5baf2573a318b25445b
[ROCm/clr commit: d432615faa]
Remove hip-hcc codes from hip code base
Simplify hip CMakeLists.txt to exclude hip-hcc
Simplify cmake cmd for hip-rocclr building
Some minor fixes
Change-Id: I1ae357ecfd638d6c25bca293c1724b026be21ecd
[ROCm/clr commit: 1cba7ec965]
HIP supports compiling kernels from LLVM IR into executable.
The device LLVM IR needs to be compiled into a fat binary
object. This device object is embedded into a host object using
llvm-mc directives. Then, any host linker may link the host and
device objects together into an executable. A README was added.
Change-Id: I8ebb6ae86b7ab4290f7cba2eea5584d73a7c453e
[ROCm/clr commit: f7b5fea916]
HIP supports compiling kernels from assembly into exec.
The device assembly needs to be compiled into a fat binary
object. This device object is embedded into a host object using
llvm-mc directives. Then, any host linker may link the host and
device objects together into an executable. A README is added.
Change-Id: I59d3a8b5363073810ffc3aa0d57f21b0df272369
[ROCm/clr commit: b8b90f344c]
When OCL ROCr backend performs CL_MEM_COPY_HOST_PTR it may attempt
to have access to amd::Memory object it's currently creating,
but it's not ready yet. The logic creates a temporary dummy object
to perform a copy transfer. The new change will make sure runtime
skips allocation of the same device::Memory object second time.
Change-Id: I14c6a00a3941fdcaa6aea299e9f096e4c3f5cadf
[ROCm/clr commit: 1fde842703]
The HIP-Clang math headers upstream have been updated
to perform type promotion on math function overloads.
If any argument has integral type, it will be cast to
double.
Change-Id: I38d9e6240c40c4092b946851469498b2ae6500ae
[ROCm/clr commit: 9c041b1984]
Make sure the logic updates the command status when it's done in
HW, but not on submission.
Add the last command tracking, otherwise queue sync logic in the HIP
upper layer may skip synchronization, assuming the queue is empty.
Change-Id: I2d046792553e74df090a10f7d7a78914610f6df2
[ROCm/clr commit: 5b31c69a95]
SWDEV-261229: Change atomicAdd float implementation to use clang builtin
along with deprecating atomicAddNoRet
Change-Id: I5e98034fec54ee1a2b85d5f56273e34945d49ea3
[ROCm/clr commit: 542d3219dc]
Add a flag to record gpu TS in a marker, also disable marker flush
if there was already a marker submitted before.
Change-Id: I9cdf8e49137690c0050fe9370764dd059855a2f8
[ROCm/clr commit: db7ed1a78c]
Use barrier packets for every profile marker that gets submitted
and use the completion signal to get GPU ts. This gives most accurate
dispatch time. Club cache flushes with profile marker if there is a
pending dispatch that needs cache flush. This optimization saves on
extra barrier and helps wall time
Change-Id: Ib62d6d7aabf4743827b561be6c9c5afa813203da
[ROCm/clr commit: 59c6cb0268]
- As `long`/`ulong` on Windows has different bit sizes from Linux
platforms, even compiled in 64-bit mode. Need to use portable data
type `int64_t`/`uint64_t` as possible or use `long long` ones to
match the prototype in LLVM IR.
Change-Id: I62fe16a2e53aa0f2f2b4069b8a1596b8db7050c9
[ROCm/clr commit: f3b63c004a]
1. Negative Test Cases
2. API functionality tests for hopcount and linktype using rocm-smi library.
3. API functionality test for hopcount when devices are reversed.
4. Disabling test case 7.
5. Implemented External Review Comments.
6. Created a new header file hipP2pLinkTypeAndHopFunc.h.
7. Removed test case 0x7 from directed test.
8. Put testMaskedDevice() under __linux__, placed TODO in line 404 (comments) and replaced '&=' with '='.
SWDEV-238517 for enhancing hip unit tests
Change-Id: I1ae256ecfd637d6c25bca293c1724b026be20eca
[ROCm/clr commit: 4b16d3896d]
- Test d2d transfer after doing copy from pinned host buffer
- Test d2d transfer after doing copy from unpinned host buffer
SWDEV-238517 for enhancing hip unit tests
Change-Id: Ib262185ce2692036e11c0f95ccb850eb3bce1c81
[ROCm/clr commit: 50524ae60c]
1. Negative Test Cases
2. API functionality test using multiple streams.
3. API functionality validation using multiple GPUs.
4. Setting hipTexRefSetFlags() with HIP_TRSF_READ_AS_INTEGER flag instead of 0 as suggested in SWDEV-256096.
5. Enabling test cases 0x03 (short) and 0x04 (char).
6. Implemented external code review comments.
SWDEV-238517 for enhancing hip unit tests
Change-Id: If42796047ec1cf2e3695dc2b7f40a2d9dd50f5bd
[ROCm/clr commit: 4f039d1bf5]
SWDEV-262064 - compilation fails when hipLaunchCooperativeKernel C++ routine is invoked
on nvcc path.
Change-Id: Icde35dd1a7008b406401bb3996c06d7acfb27d8d
[ROCm/clr commit: 80cb172fef]
[PAL to KFD/ROCr][ROCr_Runtime][Vega10] OCLSeparateCompile subtest of
oclcompiler from ocltst test package is encountering clLinkProgram()
failed (chksum 0x00000001) error
If runtime does not provide a file name as dump file to ELF library,
ELF library use a temp file in current folder.
The current folder can be not writable for several reasons:
1. The application current folder might be system folder, the user
does not have write permission.
2. The current folder is under a readonly file system. This happens for
embedded customers.
Tested in VEGA10. Issue was fixed.
Change-Id: Ic0e9f040b7c7583914301673cce237ab28b0c0cb
[ROCm/clr commit: 6327dbc4cc]
Aaron En Ye Shi
Alex Xie
Rahul Garg
Tao Sang
Saleel Kudchadker
German Andryeyev
Jatin Chaudhary
Sarbojit Sarkar
Chauncey Hui
Sudheer Kumar
sumanthtg
Jason Tang
Satyanvesh Dittakavi
agodavar
Sourabh Betigeri
Yaxun (Sam) Liu
Michael LIAO
Siu Chi Chan
Rupam Chetia
Tony