Skip to content

[doc][ext] Update HIP/L0 support in p2p doc #15847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 31, 2024

Conversation

JackAKirk
Copy link
Contributor

The extension document was out of date since it stated that P2P access only worked on CUDA. This updates it to clarify that P2P access is also supported on hip and l0 backends.

@JackAKirk JackAKirk requested a review from a team as a code owner October 24, 2024 11:32
@JackAKirk
Copy link
Contributor Author

However note that it seems that Level Zero support may require greater clarification/testing: #15841

@kaanolgu
Copy link

However note that it seems that Level Zero support may require greater clarification/testing: #15841

Previously I tested with oneapi standalone dpcppp compiler downloaded from website but now I cloned one of the latest commits from the repository that I know worked in my other system with Nvidia GPUs and tested on that commit in my Intel GPU VM system now it prints out :

$ export DPCPP_HOME=~/sycl_workspace
$ export PATH=$DPCPP_HOME/llvm/build/bin:$PATH;export 
$ LD_LIBRARY_PATH=$DPCPP_HOME/llvm/build/lib:$LD_LIBRARY_PATH

$ clang --version
clang version 20.0.0git (https://github.com/intel/llvm fda7dc722161a649879a8e682704d06356a38d25)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /home/sdp/sycl_workspace/llvm/build/bin
Build config: +assertions

$ sycl-ls
ZE_LOADER_DEBUG_TRACE:Using Loader Library Path: 
ZE_LOADER_DEBUG_TRACE:Tracing Layer Library Path: libze_tracing_layer.so.1
SYCL Exception encountered: Native API failed. Native API returns: 2147483646 (UR_RESULT_ERROR_UNKNOWN)

On the other hand, the installation test $ python $DPCPP_HOME/llvm/buildbot/check.py returns:

FAIL: Clang :: Driver/sycl-device-lib-amdgcn.cpp (11484 of 83579)
******************** TEST 'Clang :: Driver/sycl-device-lib-amdgcn.cpp' FAILED ********************
Exit Code: 1

Command Output (stderr):
--
RUN: at line 9: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl -fno-sycl-device-lib=all --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-NO-DEVLIB /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl -fno-sycl-device-lib=all --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-NO-DEVLIB /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
RUN: at line 23: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl -fsycl-device-lib=all --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl -fsycl-device-lib=all --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
RUN: at line 29: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fsycl -fsycl-device-lib=libc,libm-fp32,libm-fp64,libimf-fp32,libimf-fp64,libimf-bf16,libm-bfloat16  -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl -fsycl-device-lib=libc,libm-fp32,libm-fp64,libimf-fp32,libimf-fp64,libimf-bf16,libm-bfloat16 -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
RUN: at line 36: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fno-sycl-device-lib=libc,libm-fp32,libm-fp64,libimf-fp32,libimf-fp64,libimf-bf16,libm-bfloat16  -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefixes=CHK-UNUSED-WARN,CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fno-sycl-device-lib=libc,libm-fp32,libm-fp64,libimf-fp32,libimf-fp64,libimf-bf16,libm-bfloat16 -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefixes=CHK-UNUSED-WARN,CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
RUN: at line 47: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -### -nogpulib --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fsycl -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ONLY-NEEDED /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -### -nogpulib --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906 /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ONLY-NEEDED /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-amdgcn.cpp

--

********************
FAIL: Clang :: Driver/sycl-device-lib-nvptx.cpp (11488 of 83579)
******************** TEST 'Clang :: Driver/sycl-device-lib-nvptx.cpp' FAILED ********************
Exit Code: 1

Command Output (stderr):
--
RUN: at line 9: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl -fno-sycl-device-lib=all --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-NO-DEVLIB /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl -fno-sycl-device-lib=all --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-NO-DEVLIB /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
RUN: at line 23: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl -fsycl-device-lib=all --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl -fsycl-device-lib=all --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
RUN: at line 29: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fsycl -fsycl-device-lib=libc,libm-fp32,libm-fp64,libimf-fp32,libimf-fp64,libimf-bf16,libm-bfloat16  -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl -fsycl-device-lib=libc,libm-fp32,libm-fp64,libimf-fp32,libimf-fp64,libimf-bf16,libm-bfloat16 -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
RUN: at line 36: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL  -fno-sycl-device-lib=libc,libm-fp32,libm-fp64,libimf-fp32,libimf-fp64,libimf-bf16,libm-bfloat16  -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefixes=CHK-UNUSED-WARN,CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -ccc-print-phases -std=c++11 -fsycl --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fno-sycl-device-lib=libc,libm-fp32,libm-fp64,libimf-fp32,libimf-fp64,libimf-bf16,libm-bfloat16 -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefixes=CHK-UNUSED-WARN,CHK-ALL /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
RUN: at line 47: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -### --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp 2>&1  | /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ONLY-NEEDED /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -### --sysroot=/home/sdp/sycl_workspace/llvm/clang/test/Driver/Inputs/SYCL -fsycl -fsycl-targets=nvptx64-nvidia-cuda /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp
+ /home/sdp/sycl_workspace/llvm/build/bin/FileCheck -check-prefix=CHK-ONLY-NEEDED /home/sdp/sycl_workspace/llvm/clang/test/Driver/sycl-device-lib-nvptx.cpp

--

********************
FAIL: SYCL :: basic_tests/device-selectors-exception.cpp (82522 of 83579)
******************** TEST 'SYCL :: basic_tests/device-selectors-exception.cpp' FAILED ********************
Exit Code: -6

Command Output (stdout):
--
# RUN: at line 1
/home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++  -fsycl -fsycl-targets=spir64-unknown-unknown /home/sdp/sycl_workspace/llvm/sycl/test/basic_tests/device-selectors-exception.cpp -o /home/sdp/sycl_workspace/llvm/build/tools/sycl/test/basic_tests/Output/device-selectors-exception.cpp.tmp.out
# executed command: /home/sdp/sycl_workspace/llvm/build/bin/clang --driver-mode=g++ -fsycl -fsycl-targets=spir64-unknown-unknown /home/sdp/sycl_workspace/llvm/sycl/test/basic_tests/device-selectors-exception.cpp -o /home/sdp/sycl_workspace/llvm/build/tools/sycl/test/basic_tests/Output/device-selectors-exception.cpp.tmp.out
# RUN: at line 2
env SYCL_DEVICE_FILTER="" /home/sdp/sycl_workspace/llvm/build/tools/sycl/test/basic_tests/Output/device-selectors-exception.cpp.tmp.out
# executed command: env SYCL_DEVICE_FILTER= /home/sdp/sycl_workspace/llvm/build/tools/sycl/test/basic_tests/Output/device-selectors-exception.cpp.tmp.out
# .---command stderr------------
# | ZE_LOADER_DEBUG_TRACE:Using Loader Library Path: 
# | ZE_LOADER_DEBUG_TRACE:Tracing Layer Library Path: libze_tracing_layer.so.1
# | device-selectors-exception.cpp.tmp.out: /home/sdp/sycl_workspace/llvm/sycl/test/basic_tests/device-selectors-exception.cpp:30: int main(): Assertion `std::string(E.what()).find("info::device_type::gpu") != std::string::npos && "Incorrect device type in exception message for GPU device."' failed.
# `-----------------------------
# error: command failed with exit status: -6

--

********************
FAIL: SYCL :: tools/sycl-ls.test (82580 of 83579)
******************** TEST 'SYCL :: tools/sycl-ls.test' FAILED ********************
Exit Code: 1

Command Output (stdout):
--
# RUN: at line 3
sycl-ls --verbose > vanilla_verbose.out
# executed command: sycl-ls --verbose
# .---command stderr------------
# | ZE_LOADER_DEBUG_TRACE:Using Loader Library Path: 
# | ZE_LOADER_DEBUG_TRACE:Tracing Layer Library Path: libze_tracing_layer.so.1
# | SYCL Exception encountered: Native API failed. Native API returns: 2147483646 (UR_RESULT_ERROR_UNKNOWN)
# | 
# `-----------------------------
# RUN: at line 4
sycl-ls > vanilla.out
# executed command: sycl-ls
# .---command stderr------------
# | ZE_LOADER_DEBUG_TRACE:Using Loader Library Path: 
# | ZE_LOADER_DEBUG_TRACE:Tracing Layer Library Path: libze_tracing_layer.so.1
# | SYCL Exception encountered: Native API failed. Native API returns: 2147483646 (UR_RESULT_ERROR_UNKNOWN)
# | 
# `-----------------------------
# RUN: at line 6
env ONEAPI_DEVICE_SELECTOR="opencl:*" sycl-ls > ods_opencl.out
# executed command: env 'ONEAPI_DEVICE_SELECTOR=opencl:*' sycl-ls
# .---command stderr------------
# | INFO: Output filtered by ONEAPI_DEVICE_SELECTOR environment variable, which is set to opencl:*.
# | To see device ids, use the --ignore-device-selectors CLI option.
# | 
# `-----------------------------
# RUN: at line 7
env SYCL_DEVICE_ALLOWLIST="BackendName:opencl" sycl-ls > sda_opencl.out
# executed command: env SYCL_DEVICE_ALLOWLIST=BackendName:opencl sycl-ls
# .---command stderr------------
# | INFO: Output filtered by SYCL_DEVICE_ALLOWLIST environment variable, which is set to BackendName:opencl.
# | To see device ids, use the --ignore-device-selectors CLI option.
# | 
# | ZE_LOADER_DEBUG_TRACE:Using Loader Library Path: 
# | ZE_LOADER_DEBUG_TRACE:Tracing Layer Library Path: libze_tracing_layer.so.1
# | SYCL Exception encountered: Native API failed. Native API returns: 2147483646 (UR_RESULT_ERROR_UNKNOWN)
# | 
# `-----------------------------
# RUN: at line 8
diff ods_opencl.out sda_opencl.out
# executed command: diff ods_opencl.out sda_opencl.out
# .---command stdout------------
# | *** /home/sdp/sycl_workspace/llvm/build/tools/sycl/test/tools/ods_opencl.out
# | --- /home/sdp/sycl_workspace/llvm/build/tools/sycl/test/tools/sda_opencl.out
# | ***************
# | *** 1,16 ****
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | - [opencl:gpu] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
# | --- 0 ----
# `-----------------------------
# error: command failed with exit status: 1

--

********************
********************
Failed Tests (4):
  Clang :: Driver/sycl-device-lib-amdgcn.cpp
  Clang :: Driver/sycl-device-lib-nvptx.cpp
  SYCL :: basic_tests/device-selectors-exception.cpp
  SYCL :: tools/sycl-ls.test


Testing Time: 175.26s

Total Discovered Tests: 102474
  Skipped          :   358 (0.35%)
  Unsupported      : 32370 (31.59%)
  Passed           : 69644 (67.96%)
  Expectedly Failed:    98 (0.10%)
  Failed           :     4 (0.00%)

With Intel OneAPI loaded via source /opt/intel/oneapi/setvars.sh I have these devices listed : (although I generated a VM with 8 GPUs on Tiber Devcloud I would assume that 16 each is including sub-devices ? )

$ icpx --version
Intel(R) oneAPI DPC++/C++ Compiler 2024.2.1 (2024.2.1.20240711)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /opt/intel/oneapi/compiler/2024.2/bin/compiler
Configuration file: /opt/intel/oneapi/compiler/2024.2/bin/compiler/../icpx.cfg

These are devices

$ sycl-ls
[opencl:cpu][opencl:0] Intel(R) OpenCL, Intel(R) Xeon(R) Platinum 8468V OpenCL 3.0 (Build 0) [2024.18.7.0.11_160000]
[opencl:cpu][opencl:1] Intel(R) OpenCL, Intel(R) Xeon(R) Platinum 8468V OpenCL 3.0 (Build 0) [2024.18.6.0.02_160000]
[opencl:gpu][opencl:2] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:3] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:4] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:5] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:6] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:7] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:8] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:9] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:10] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:11] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:12] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:13] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:14] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:15] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:16] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[opencl:gpu][opencl:17] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1550 OpenCL 3.0 NEO  [23.35.27191.42]
[level_zero:gpu][level_zero:0] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:1] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:2] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:3] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:4] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:5] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:6] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:7] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:8] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:9] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:10] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:11] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:12] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:13] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:14] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]
[level_zero:gpu][level_zero:15] Intel(R) Level-Zero, Intel(R) Data Center GPU Max 1550 1.3 [1.3.27191]

I am still experiencing the error message in #15841 and sometimes instead of exception error message it prints out the message "P2P access is not supported by devices, exiting."

  if (!Devs[0].ext_oneapi_can_access_peer(
          Devs[1], sycl::ext::oneapi::peer_access::access_supported)) {
    std::cout << "P2P access is not supported by devices, exiting."
              << std::endl;
    return 0;
  }

@JackAKirk
Copy link
Contributor Author

I think that this probably explains the recent p2p issues: ee97531
Seems that L0 UR p2p impl didn't conform to the spec and returned a bool, and then the above was an attempt to fix things.

I'll try to fix this.

@pbalcer
Copy link
Contributor

pbalcer commented Oct 25, 2024

I think that this probably explains the recent p2p issues: ee97531 Seems that L0 UR p2p impl didn't conform to the spec and returned a bool, and then the above was an attempt to fix things.

I'll try to fix this.

Related: oneapi-src/unified-runtime#2079
I thought this was a cosmetic issue for the most part.

@JackAKirk
Copy link
Contributor Author

I think that this probably explains the recent p2p issues: ee97531 Seems that L0 UR p2p impl didn't conform to the spec and returned a bool, and then the above was an attempt to fix things.

I'll try to fix this.

This is fixed by oneapi-src/unified-runtime#2246 and #15873

@JackAKirk JackAKirk changed the title [ext] Update HIP/L0 support in p2p doc [doc][ext] Update HIP/L0 support in p2p doc Oct 31, 2024
@JackAKirk
Copy link
Contributor Author

I think that this probably explains the recent p2p issues: ee97531 Seems that L0 UR p2p impl didn't conform to the spec and returned a bool, and then the above was an attempt to fix things.
I'll try to fix this.

This is fixed by oneapi-src/unified-runtime#2246 and #15873

These PRs are merged. This means that Level zero support should be fixed and the update to the docs in this PR is correct.
@intel/llvm-gatekeepers this can now be merged.

Thanks

@martygrant martygrant merged commit 4950917 into intel:sycl Oct 31, 2024
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants