Commit Graph

87 Commits

Author SHA1 Message Date
Fangrui Song 0c2f6e36f9 [Driver] llvm::None => std::nullopt. NFC 2022-12-03 19:43:25 +00:00
Matt Arsenault e748db0f7f Support: Convert Program APIs to std::optional 2022-12-01 17:00:44 -05:00
Matt Arsenault 840a793375 clang/AMDGPU: Use Support's wrapper around getenv
This does some extra stuff for Windows, so might as well
use it just in case.
2022-11-14 11:07:31 -08:00
Yaxun (Sam) Liu 082593ff7a [HIP] Detect HIP for Debian/Fedora
HIP is installed at /usr or /usr/local on Debin/Fedora,
and the version file is at {root}/share/hip/version.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D135796
2022-10-12 22:59:16 -04:00
Fangrui Song 1491282165 [clang] Change cc1 -fvisibility's canonical spelling to -fvisibility= 2022-09-02 11:49:38 -07:00
Kazu Hirata a33ef8f2b7 Use llvm::all_equal (NFC) 2022-08-27 09:53:10 -07:00
Kazu Hirata ca4af13e48 [clang] Don't use Optional::getValue (NFC) 2022-06-20 22:59:26 -07:00
Kazu Hirata f5ef2c5838 [clang] Convert for_each to range-based for loops (NFC) 2022-06-10 22:39:45 -07:00
Ron Lieberman f1e7ecaa18 Revert "[AMDPU][Sanitizer] Refactor sanitizer options handling for AMDGPU Toolchain"
This reverts commit cc2139524f.

failed a few buildbots
2022-04-02 13:25:50 +00:00
Ron Lieberman cc2139524f [AMDPU][Sanitizer] Refactor sanitizer options handling for AMDGPU Toolchain
authored by amit.pandey@amd.com  ampandey-AMD

Differential Revision: https://reviews.llvm.org/D122781
2022-04-02 11:01:09 +00:00
Fangrui Song c37accf0a2 [Option] Avoid using the default argument for the 3-argument hasFlag. NFC
The default argument true is error-prone: I think many would think the
default is false.
2022-03-26 00:57:06 -07:00
Yaxun (Sam) Liu 6730b44480 [HIP] Fix HIP include path
The clang compiler prepends the HIP header include paths to the search
list using -internal-isystem when building for the HIP language. This
prevents warnings related to things like reserved identifiers when
including the HIP headers even when ROCm is installed in a non-system
directory, such as /opt/rocm.

However, when HIP is installed in /usr, then the prepended include
path would be /usr/include. That is a problem, because the C standard
library headers are stored in /usr/include and the C++ standard
library headers must come before the C library headers in the search
path list (because the C++ standard library headers use #include_next
to include the C standard library headers).

While the HIP wrapper headers _do_ need to be earlier in the search
than the C++ headers, those headers get their own subdirectory and
their own explicit -internal-isystem argument. This include path is for
<hip/hip_runtime_api.h> and <hip/hip_runtime.h>, which do not require a
particular search ordering with respect to the C or C++ headers. Thus,
HIP include path is added after other system include paths.

With contribution from Cordell Bloor.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D120132
2022-03-09 20:57:27 -05:00
Yaxun (Sam) Liu 092f15ac40 [HIP] File device library ABI version file name
It should be oclc_abi_version* instead of abi_version*.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D120557
2022-02-28 16:24:50 -05:00
Yaxun (Sam) Liu d4e4ef2e81 [HIP] Support code object v5
New device library supporting v4 and v5 has abi_version_400.bc and abi
version_500.bc.

For v5, abi_version_500.bc is linked.

For v2-4, abi_version_400.bc is linked.

For old device library, for v2-4, none of the above is linked. For v5,
error is emitted about unsupported ABI version.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D118949

Fixes: SWDEV-321313
2022-02-04 09:55:08 -05:00
Henry Linjamäki 4e94cba5b4 [HIPSPV][2/4] Add HIPSPV tool chain
This patch adds a new tool chain, HIPSPVToolChain, for emitting HIP
device code as SPIR-V binary. The SPIR-V binary is emitted by using an
external tool, SPIRV-LLVM-Translator, temporarily. We intend to switch
the translator to the llc tool when the SPIR-V backend lands on LLVM
and proves to work well on HIP implementations which consume SPIR-V.

Before the SPIR-V emission the tool chain loads an optional external
pass plugin, either automatically from a HIP installation or from a
path pointed by --hipspv-pass-plugin, and runs passes that are meant
to expand/lower HIP features that do not have direct counterpart in
SPIR-V (e.g. dynamic shared memory).

Code emission for SPIR-V will be enabled and HIPSPVToolChain tests
will be added in the follow up patch part 3.

Other changes: New option ‘-nohipwrapperinc’ is added to exclude HIP
include wrappers. The reason for the addition is that they cause
compile errors when compiling HIP sources for the host side for HIPCL
and HIPLZ implementations. New option is added to avoid this issue.

Reviewed By: tra

Differential Revision: https://reviews.llvm.org/D110618
2021-12-14 10:22:38 -08:00
Kazu Hirata 16ceb44e62 [clang] Use llvm::{count,count_if,find_if,all_of,none_of} (NFC) 2021-10-25 09:14:45 -07:00
Kazu Hirata d8e4170b0a Ensure newlines at the end of files (NFC) 2021-10-23 08:45:29 -07:00
Kazu Hirata b8debabb77 [clang] Remove redundant calls to c_str() (NFC)
Identified with readability-redundant-string-cstr.
2021-08-31 08:53:51 -07:00
Pushpinder Singh 9830f902e4 [AMDGPU][OpenMP] Support linking of math libraries
Math libraries are linked only when -lm is specified. This is because
host system could be missing rocm-device-libs.

Reviewed By: JonChesterfield, yaxunl

Differential Revision: https://reviews.llvm.org/D105981
2021-07-30 13:53:44 +00:00
Jan Svoboda 60426f33b1 [clang][driver] NFC: Move InputInfo.h from lib to include
Moving `InputInfo.h` from `lib/Driver/` into `include/Driver` to be able to expose it in an API consumed from outside of `clangDriver`.

Reviewed By: dexonsmith

Differential Revision: https://reviews.llvm.org/D106787
2021-07-27 09:17:39 +02:00
David Blaikie 1def2579e1 PR51018: Remove explicit conversions from SmallString to StringRef to future-proof against C++23
C++23 will make these conversions ambiguous - so fix them to make the
codebase forward-compatible with C++23 (& a follow-up change I've made
will make this ambiguous/invalid even in <C++23 so we don't regress
this & it generally improves the code anyway)
2021-07-08 13:37:57 -07:00
Aaron En Ye Shi f2cc0427b1 [HIP] Fix --hip-version flag with 0 as component
Allow the usage of minor version 0, for hip versions
such as 4.0. Change the default values when performing
version checks.

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D104062
2021-06-11 16:25:03 +00:00
Yaxun (Sam) Liu b5dea8701b [HIP] Fix spack HIP device lib detection
spack HIP device library is installed at amdgcn directory under llvm/clang
directory.

This patch fixes detection of HIP device library for spack.

Reviewed by: Artem Belevich, Harmen Stoppels

Differential Revision: https://reviews.llvm.org/D103281
2021-06-04 09:12:41 -04:00
Yaxun (Sam) Liu 6d2c095020 [HIP] Check compatibility of -fgpu-sanitize with offload arch
-fgpu-sanitize is incompatible with offload arch containing xnack-.

This patch checks that.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D102975
2021-05-27 12:06:42 -04:00
Yaxun (Sam) Liu 18cb17ce4c [HIP] Fix spack detection
Missing or duplicate spack package should not cause error, since
users may only installed llvm/clang package, or users may installed
duplicate HIP package but will use environment variable or compiler
option to choose HIP path.

The message about missing or duplicate spack package is informational,
therefore should be emitted only when -v is specified.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D102556
2021-05-17 13:24:05 -04:00
Pushpinder Singh 59ad4e0f01 Reapply "[AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed"
This reverts commit 93604305bb.
2021-04-27 10:47:05 +00:00
Pushpinder Singh 93604305bb Revert "Reapply "[AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed""
This reverts commit 15be0c41d2.
2021-04-27 02:23:44 +00:00
Jon Chesterfield 15be0c41d2 Reapply "[AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed"
This reverts commit 24c1ed3b34.
2021-04-23 01:07:16 +01:00
Jon Chesterfield 2cdb9873b2 [clang][nfc] Split getOrCheckAMDGPUCodeObjectVersion
[clang][nfc] Split getOrCheckAMDGPUCodeObjectVersion

Separates detection of deprecated or invalid code object version from
returning the version. Written to avoid any behaviour change.

Precursor to a revision of D98746.

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D101077
2021-04-23 00:24:42 +01:00
Jon Chesterfield 24c1ed3b34 Revert "[AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed"
This reverts commit 722d4d8e75.

Unclear where hsa.h should be included from, see report in D99949
2021-04-22 19:39:37 +01:00
Pushpinder Singh 722d4d8e75 [AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed
This patch adds new clang tool named amdgpu-arch which uses
HSA to detect installed AMDGPU and report back latter's march.
This tool is built only if system has HSA installed.

The value printed by amdgpu-arch is used to fill -march when
latter is not explicitly provided in -Xopenmp-target.

Reviewed By: JonChesterfield, gregrodgers

Differential Revision: https://reviews.llvm.org/D99949
2021-04-22 05:20:28 +00:00
Pushpinder Singh 0ad50bf27f Revert "[AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed"
This reverts commit 3194761d27.
2021-04-21 08:05:38 +00:00
Pushpinder Singh 3194761d27 [AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed
This patch adds new clang tool named amdgpu-arch which uses
HSA to detect installed AMDGPU and report back latter's march.
This tool is built only if system has HSA installed.

The value printed by amdgpu-arch is used to fill -march when
latter is not explicitly provided in -Xopenmp-target.

Reviewed By: JonChesterfield, gregrodgers

Differential Revision: https://reviews.llvm.org/D99949
2021-04-21 05:05:49 +00:00
Pushpinder Singh efc013ec4d Revert "[AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed"
This reverts commit 7029cffc4e.
2021-04-16 09:16:58 +00:00
Pushpinder Singh 7029cffc4e [AMDGPU][OpenMP] Add amdgpu-arch tool to list AMD GPUs installed
This patch adds new clang tool named amdgpu-arch which uses
HSA to detect installed AMDGPU and report back latter's march.
This tool is built only if system has HSA installed.

The value printed by amdgpu-arch is used to fill -march when
latter is not explicitly provided in -Xopenmp-target.

Reviewed By: JonChesterfield, gregrodgers

Differential Revision: https://reviews.llvm.org/D99949
2021-04-16 05:26:20 +00:00
Yaxun (Sam) Liu 907af84396 [CUDA][HIP] rename -fcuda-flush-denormals-to-zero
Rename it to -fgpu-flush-denormals-to-zero.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D99688
2021-04-05 00:13:51 -04:00
Yaxun (Sam) Liu 282bf9eaf7 [HIP] Fix ROCm detection
ROCm has changed installation path to /opt/rocm-{release}. Add detection
for that. Also support ROCM_PATH environment variable.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D98867
2021-03-22 16:10:02 -04:00
Yaxun (Sam) Liu 34d1a5c7b1 [HIP] Support Spack packages
Spack is a package management tool extensively used by HPC community.
As ROCm packages are built by Spack by HPC community, we need to teach
clang driver to detect ROCm installation built by Spack.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D97340
2021-03-06 08:41:37 -05:00
Yaxun (Sam) Liu 51ade31e67 [HIP] Support device sanitizer
Add option -fgpu-sanitize to enable sanitizer for AMDGPU target.

Since it is experimental, it is off by default.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D96835
2021-02-18 23:30:25 -05:00
Michael Liao 2a29ce3034 [hip] Fix HIP version parsing.
- Need trimming before parsing major or minor version numbers. This's required
  due to the different line ending on Windows.
- In addition, the integer conversion may fail due to invalid char. Return that
  parsing function return `true` when the parsing fails.

Differential Revision: https://reviews.llvm.org/D93587
2021-01-06 17:00:14 -05:00
Yaxun (Sam) Liu 0b81d9a992 [AMDGPU] add -mcode-object-version=n
Add option -mcode-object-version=n to control code object version for
AMDGPU.

Differential Revision: https://reviews.llvm.org/D91310
2020-12-07 18:08:37 -05:00
Yaxun (Sam) Liu 0519e1ddb3 [HIP] Fix bug in driver about wavefront size
The static variable causes it only initialized once and take
the same value for different GPU archs, whereas they
may be different for different GPU archs, e.g. when
there are both gfx900 and gfx1010.

Removing static fixes that.

Differential Revision: https://reviews.llvm.org/D92628
2020-12-04 08:36:52 -05:00
Konstantin Zhuravlyov 67f189e93c Make sure both cc1 and cc1as process -m[no-]code-object-v3
Differential Revision: https://reviews.llvm.org/D89478
2020-10-15 14:03:26 -04:00
Konstantin Zhuravlyov 3fdf3b1539 AMDGPU: Update AMDHSA code object version handling
Differential Revision: https://reviews.llvm.org/D89076
2020-10-14 13:04:27 -04:00
Konstantin Zhuravlyov e2eaa91451 AMDGPU: Remove -mamdgpu-debugger-abi option
It has been unsupported for few years now.

Differential Revision: https://reviews.llvm.org/D89125
2020-10-13 12:20:28 -04:00
Serge Pavlov 70bf35070a [Driver] Add output file to properties of Command
Object of class `Command` contains various properties of a command to
execute, but output file was missed from them. This change adds this
property. It is required for reporting consumed time and memory implemented
in D78903 and may be used in other cases too.

Differential Revision: https://reviews.llvm.org/D78902
2020-10-08 18:23:39 +07:00
Yaxun (Sam) Liu 2cd75f738e Diagnose invalid target ID for AMDGPU toolchain for assembler
AMDGPU toolchain currently only diagnose invalid target ID for OpenCL
source compilation. Invalid target ID is not diagnosed for assembler.

This patch fixes that.

Differential Revision: https://reviews.llvm.org/D88377
2020-10-02 19:38:02 -04:00
Yaxun (Sam) Liu 36501b180a Emit predefined macro for wavefront size for amdgcn
Also fix the issue of multiple -m[no-]wavefrontsize64
options to make the last one wins.

Differential Revision: https://reviews.llvm.org/D88370
2020-10-02 10:17:21 -04:00
Yaxun (Sam) Liu 10eb3bf2d4 Skip -fPIE for AMDGPU and HIP toolchain
AMDGPU toolchain does not support -fPIE, therefore skip it if specified by driver.

Differential Revision: https://reviews.llvm.org/D88425
2020-09-28 22:03:18 -04:00
Yaxun (Sam) Liu ccb4124a41 Fix -gz=zlib options for linker
gcc translates -gz=zlib to --compress-debug-options=zlib for both assembler and linker
but clang only does this for assembler.

The linker needs --compress-debug-options=zlib option to compress the debug sections
in the generated executable or shared library.

Due to this bug, -gz=zlib has no effect on the generated executable or shared library.

This patch fixes that.

Differential Revision: https://reviews.llvm.org/D87321
2020-09-11 17:12:58 -04:00