[clang] 6a9cf21 - [CUDA, MemCpyOpt] Add a flag to force-enable memcpyopt and use it for CUDA.

Author: Artem Belevich Date: 2021-08-06T11:13:52-07:00 New Revision: 6a9cf21f5a2dcd02f90075d6d3576a87f1abd8a9 URL: https://github.com/llvm/llvm-project/commit/6a9cf21f5a2dcd02f90075d6d3576a87f1abd8a9 DIFF:

[clang] d774b4a - [NVPTX, CUDA] Add .and.popc variant of the b1 MMA instruction.

Author: Artem Belevich Date: 2021-07-15T12:02:09-07:00 New Revision: d774b4aa5eac785ffe40009091667521e183df40 URL: https://github.com/llvm/llvm-project/commit/d774b4aa5eac785ffe40009091667521e183df40 DIFF:

[clang] 25629bb - Fix cuda-bad-arch.cu test.

Author: Artem Belevich Date: 2021-07-13T11:57:25-07:00 New Revision: 25629bb45f0a4b8c8e99dbde4f4a7e3d980b9fd7 URL: https://github.com/llvm/llvm-project/commit/25629bb45f0a4b8c8e99dbde4f4a7e3d980b9fd7 DIFF:

[clang] 01d3a3d - [CUDA] Only allow NVIDIA offload-arch during CUDA compilation.

Author: Artem Belevich Date: 2021-07-13T11:09:14-07:00 New Revision: 01d3a3dcabaf862581b1d1aee604fcee6a18b240 URL: https://github.com/llvm/llvm-project/commit/01d3a3dcabaf862581b1d1aee604fcee6a18b240 DIFF:

[clang] cab5f89 - [Clang] allow overriding -fbasic-block-sections

Author: Artem Belevich Date: 2021-06-30T14:32:08-07:00 New Revision: cab5f89cfd9efa9166e1362972e460323b8254ef URL: https://github.com/llvm/llvm-project/commit/cab5f89cfd9efa9166e1362972e460323b8254ef DIFF:

[clang] 9a75c06 - [CUDA] Work around compatibility issue with libstdc++ 11.1.0

Author: Artem Belevich Date: 2021-05-24T11:07:09-07:00 New Revision: 9a75c06cd9d94d3fd13c47a01044da97b98cf26b URL: https://github.com/llvm/llvm-project/commit/9a75c06cd9d94d3fd13c47a01044da97b98cf26b DIFF:

[clang] f226e28 - [Clang][NVPTX] Add NVPTX intrinsics and builtins for CUDA PTX redux.sync instructions

Author: Steffen Larsen Date: 2021-05-17T09:46:59-07:00 New Revision: f226e28a880f8e40b1bfd4c77b9768a667372d22 URL: https://github.com/llvm/llvm-project/commit/f226e28a880f8e40b1bfd4c77b9768a667372d22 DIFF:

[clang] 02c2468 - [Clang][NVPTX] Add NVPTX intrinsics and builtins for CUDA PTX cp.async instructions

Author: Stuart Adams Date: 2021-05-17T09:46:59-07:00 New Revision: 02c2468864bbb37f7b279aff84961815c1500b6c URL: https://github.com/llvm/llvm-project/commit/02c2468864bbb37f7b279aff84961815c1500b6c DIFF: https://github.com/llvm/llvm-project/commit/02c2468864bbb37f7b279aff84961815c1500b6c.diff

[clang] eaa9ef0 - [CUDA, FDO] Filter out profiling options from GPU-side compilations.

Author: Artem Belevich Date: 2021-04-16T11:35:28-07:00 New Revision: eaa9ef075d9b4d49ce9dae723516e7e6e8b0c4b6 URL: https://github.com/llvm/llvm-project/commit/eaa9ef075d9b4d49ce9dae723516e7e6e8b0c4b6 DIFF:

[clang] 38cf112 - Allow applying attributes to subset of allowed subjects.

Author: Artem Belevich Date: 2021-04-12T09:33:33-07:00 New Revision: 38cf112a6bc8502ff8cce6ef524cf04c07f90f96 URL: https://github.com/llvm/llvm-project/commit/38cf112a6bc8502ff8cce6ef524cf04c07f90f96 DIFF:

[clang] 32e0645 - [CUDA] Remove `noreturn` attribute from __assertfail().

Author: Artem Belevich Date: 2021-03-01T13:59:22-08:00 New Revision: 32e0645276230bb5b736e378860df3b92b1f4ba8 URL: https://github.com/llvm/llvm-project/commit/32e0645276230bb5b736e378860df3b92b1f4ba8 DIFF:

[clang] 2aa01cc - [CUDA, NVPTX] Allow targeting sm_86 GPUs.

Author: Artem Belevich Date: 2021-02-09T11:01:10-08:00 New Revision: 2aa01ccec30109fbcc65934c5d7c8907793e0660 URL: https://github.com/llvm/llvm-project/commit/2aa01ccec30109fbcc65934c5d7c8907793e0660 DIFF:

[clang] 127091b - [CUDA] Normalize handling of defauled dtor.

Author: Artem Belevich Date: 2021-01-21T10:48:07-08:00 New Revision: 127091bfd5edf10495fee4724fd21c666e5d79c1 URL: https://github.com/llvm/llvm-project/commit/127091bfd5edf10495fee4724fd21c666e5d79c1 DIFF:

[clang] 0936655 - [CUDA] Do not diagnose host/device variable access in dependent types.

Author: Artem Belevich Date: 2020-12-14T11:53:18-08:00 New Revision: 0936655bac78f6e9cb84dc3feb30c32012100839 URL: https://github.com/llvm/llvm-project/commit/0936655bac78f6e9cb84dc3feb30c32012100839 DIFF:

[clang] 016e4eb - [DWARF] Allow toolchain to adjust specified DWARF version.

Author: Artem Belevich Date: 2020-12-09T16:34:34-08:00 New Revision: 016e4ebfde28d6bb1ab6399fc8abd8cfc6a1d9fd URL: https://github.com/llvm/llvm-project/commit/016e4ebfde28d6bb1ab6399fc8abd8cfc6a1d9fd DIFF:

[clang] 4326792 - [CUDA] Another attempt to fix early inclusion of from libstdc++

Author: Artem Belevich Date: 2020-12-04T12:03:35-08:00 New Revision: 43267929423bf768bbbcc65e47a07e37af7f4e22 URL: https://github.com/llvm/llvm-project/commit/43267929423bf768bbbcc65e47a07e37af7f4e22 DIFF:

[clang] 9a46505 - [CUDA] Unbreak CUDA compilation with -std=c++20

Author: Artem Belevich Date: 2020-11-19T10:35:47-08:00 New Revision: 9a465057a64dba8a8614424d26136f5c0452bcc3 URL: https://github.com/llvm/llvm-project/commit/9a465057a64dba8a8614424d26136f5c0452bcc3 DIFF:

[clang] cdbf6bf - [HIP] Use argv[0] as the default choice for the Executable name.

Author: Artem Belevich Date: 2020-11-03T10:31:39-08:00 New Revision: cdbf6bfdc7d15fc6a078c7773f142042a11d2c1b URL: https://github.com/llvm/llvm-project/commit/cdbf6bfdc7d15fc6a078c7773f142042a11d2c1b DIFF:

[clang] be86b67 - [CUDA] Allow local static variables with target attributes.

Author: Artem Belevich Date: 2020-11-03T10:30:38-08:00 New Revision: be86b6773b6ba4d101a848e109540548181d2ed5 URL: https://github.com/llvm/llvm-project/commit/be86b6773b6ba4d101a848e109540548181d2ed5 DIFF:

[clang] 0a3ebb4 - Revert "[CUDA] Allow local static variables with target attributes."

Author: Artem Belevich Date: 2020-11-02T15:09:07-08:00 New Revision: 0a3ebb4d8d988e063e395621d162fa224fa4fb08 URL: https://github.com/llvm/llvm-project/commit/0a3ebb4d8d988e063e395621d162fa224fa4fb08 DIFF:

[clang] f38a9e5 - [CUDA] Allow local static variables with target attributes.

Author: Artem Belevich Date: 2020-11-02T14:37:13-08:00 New Revision: f38a9e51178add132d2c8ae160787fb2175a48a4 URL: https://github.com/llvm/llvm-project/commit/f38a9e51178add132d2c8ae160787fb2175a48a4 DIFF:

[clang] e7fe125 - [CUDA] Extract CUDA version from cuda.h if version.txt is not found

Author: Artem Belevich Date: 2020-10-23T10:03:30-07:00 New Revision: e7fe125b776bf08d95e60ff3354a5c836218a0e6 URL: https://github.com/llvm/llvm-project/commit/e7fe125b776bf08d95e60ff3354a5c836218a0e6 DIFF:

[clang] 65d2064 - [CUDA] Improve clang's ability to detect recent CUDA versions.

Author: Artem Belevich Date: 2020-10-23T10:03:29-07:00 New Revision: 65d206484c54177641d4b11d42cab1f1acc8c0c7 URL: https://github.com/llvm/llvm-project/commit/65d206484c54177641d4b11d42cab1f1acc8c0c7 DIFF:

[clang] 30514f0 - [CUDA] Added conversion functions to builtin vars.

Author: Artem Belevich Date: 2020-09-24T14:33:04-07:00 New Revision: 30514f0afa3ee1e6da6bf9c41e83c28e884f0740 URL: https://github.com/llvm/llvm-project/commit/30514f0afa3ee1e6da6bf9c41e83c28e884f0740 DIFF:

[clang] ec5f793 - [OpenMP] split execution of a long test into smaller parts.

Author: Artem Belevich Date: 2020-08-11T11:52:40-07:00 New Revision: ec5f793996f4dc86d339db88c0836e0cf4e8abea URL: https://github.com/llvm/llvm-project/commit/ec5f793996f4dc86d339db88c0836e0cf4e8abea DIFF:

[clang] 9c8ae40 - [ARM] Speed up arm-cortex-cpus.c test

Author: Artem Belevich Date: 2020-08-10T14:27:19-07:00 New Revision: 9c8ae40860311e94de0a898101818f706228e958 URL: https://github.com/llvm/llvm-project/commit/9c8ae40860311e94de0a898101818f706228e958 DIFF:

[clang] 7d057ef - [CUDA] Work around a bug in rint/nearbyint caused by a broken implementation provided by CUDA.

Author: Artem Belevich Date: 2020-08-05T13:13:48-07:00 New Revision: 7d057efddc00ba7d03e6e684f23dd9b09fbd0527 URL: https://github.com/llvm/llvm-project/commit/7d057efddc00ba7d03e6e684f23dd9b09fbd0527 DIFF:

[clang] ac20150 - [CUDA] make the test more hermetic

Author: Artem Belevich Date: 2020-06-17T15:22:45-07:00 New Revision: ac20150e299a41ade860f432741c1b8557ac8058 URL: https://github.com/llvm/llvm-project/commit/ac20150e299a41ade860f432741c1b8557ac8058 DIFF:

[clang] d700237 - [CUDA,HIP] Use VFS for SDK detection.

Author: Artem Belevich Date: 2020-06-15T12:54:44-07:00 New Revision: d700237f1aa1bc05d584a0f50fdad89370e17987 URL: https://github.com/llvm/llvm-project/commit/d700237f1aa1bc05d584a0f50fdad89370e17987 DIFF:

[clang] ef649e8 - Revert "[CUDA][HIP] Workaround for resolving host device function against wrong-sided function"

Author: Artem Belevich Date: 2020-05-18T12:22:55-07:00 New Revision: ef649e8fd5d1748764a9afca3ce0b80113a6a239 URL: https://github.com/llvm/llvm-project/commit/ef649e8fd5d1748764a9afca3ce0b80113a6a239 DIFF:

[clang] 314f99e - [CUDA] Enable existing builtins for PTX7.0 as well.

Author: Artem Belevich Date: 2020-05-06T14:24:21-07:00 New Revision: 314f99e7d42ded663386190a54b5831dc4a6f3c1 URL: https://github.com/llvm/llvm-project/commit/314f99e7d42ded663386190a54b5831dc4a6f3c1 DIFF:

[clang] 844096b - [CUDA] Make NVVM builtins available with CUDA-11/PTX6.5

Author: Artem Belevich Date: 2020-05-05T15:43:32-07:00 New Revision: 844096b996a0b17d3f380af323614a5fe31b8a68 URL: https://github.com/llvm/llvm-project/commit/844096b996a0b17d3f380af323614a5fe31b8a68 DIFF:

[clang] bf6a26b - Revert D77954 -- it breaks Eigen & Tensorflow.

Author: Artem Belevich Date: 2020-05-05T14:07:31-07:00 New Revision: bf6a26b066382e0f41bf023c781d84061c542307 URL: https://github.com/llvm/llvm-project/commit/bf6a26b066382e0f41bf023c781d84061c542307 DIFF:

[clang] 8e20516 - [CUDA] Define __CUDACC__ before standard library headers

Author: Raul Tambre Date: 2020-04-17T12:56:13-07:00 New Revision: 8e20516540444618ad32dd11e835c05804053697 URL: https://github.com/llvm/llvm-project/commit/8e20516540444618ad32dd11e835c05804053697 DIFF: https://github.com/llvm/llvm-project/commit/8e20516540444618ad32dd11e835c05804053697.diff

[clang] 8c635ba - [CUDA] Fix missed CUDA version mappings.

Author: Artem Belevich Date: 2020-04-13T15:54:12-07:00 New Revision: 8c635ba4a84f8b5dbde1984fe2d7eeefaf827ffe URL: https://github.com/llvm/llvm-project/commit/8c635ba4a84f8b5dbde1984fe2d7eeefaf827ffe DIFF:

[clang] 6ed88af - [CUDA] Accept -x cu to indicate language is CUDA, transfer CUDA language flag to header-file arguments

Author: ADRA Date: 2020-04-09T13:08:41-07:00 New Revision: 6ed88afd780cc2cd04e50e25c5d3ffafc07b1c1b URL: https://github.com/llvm/llvm-project/commit/6ed88afd780cc2cd04e50e25c5d3ffafc07b1c1b DIFF: https://github.com/llvm/llvm-project/commit/6ed88afd780cc2cd04e50e25c5d3ffafc07b1c1b.diff LOG:

[clang] 33386b2 - [CUDA] Simplify GPU variant handling. NFC.

Author: Artem Belevich Date: 2020-04-08T11:19:43-07:00 New Revision: 33386b20aa82c73e28b871cfa35c89a3808c9f92 URL: https://github.com/llvm/llvm-project/commit/33386b20aa82c73e28b871cfa35c89a3808c9f92 DIFF:

[clang] a9627b7 - [CUDA] Add partial support for recent CUDA versions.

Author: Artem Belevich Date: 2020-04-08T11:19:44-07:00 New Revision: a9627b7ea7e2b47488188cb1d80a23b24a8066b2 URL: https://github.com/llvm/llvm-project/commit/a9627b7ea7e2b47488188cb1d80a23b24a8066b2 DIFF:

[clang] d2e498b - [CUDA] Improve testing of libdevice detection.

Author: Artem Belevich Date: 2020-04-08T11:19:45-07:00 New Revision: d2e498b1725dd7b792c061387ff76df71cd7728a URL: https://github.com/llvm/llvm-project/commit/d2e498b1725dd7b792c061387ff76df71cd7728a DIFF:

Re: [clang] 8527c1e - Added constraints on cl-options.cu test

\filecheck.exe" > > "-check-prefix=GS-default" > > "C:\src\llvm_package_64c23127\llvm-project\clang\test\Driver\ > cl-options.cu" > > # command stderr: > > > C:\src\llvm_package_64c23127\llvm-project\clang\test\Driver\c

[clang] fe8063e - Revert "[cuda][hip] Add CUDA builtin surface/texture reference support."

Author: Artem Belevich Date: 2020-03-27T10:01:38-07:00 New Revision: fe8063e1a0e983f1b4d38530f4fb157a26c0771c URL: https://github.com/llvm/llvm-project/commit/fe8063e1a0e983f1b4d38530f4fb157a26c0771c DIFF:

[clang] eb2ba2e - [CUDA] Warn about unsupported CUDA SDK version only if it's used.

Author: Artem Belevich Date: 2020-03-12T10:04:10-07:00 New Revision: eb2ba2ea953b5ea73cdbb598f77470bde1c6a011 URL: https://github.com/llvm/llvm-project/commit/eb2ba2ea953b5ea73cdbb598f77470bde1c6a011 DIFF:

[clang] 8527c1e - Added constraints on cl-options.cu test

Author: Artem Belevich Date: 2020-03-11T16:06:09-07:00 New Revision: 8527c1ed66c63db0590cd69320ba0bf8fad59b87 URL: https://github.com/llvm/llvm-project/commit/8527c1ed66c63db0590cd69320ba0bf8fad59b87 DIFF:

[clang] 0c06a38 - [CUDA,clang-cl] Filter out unsupported arguments for device-side compilation.

Author: Artem Belevich Date: 2020-03-11T13:42:16-07:00 New Revision: 0c06a389e5937895579effd5e608c79bc6332e53 URL: https://github.com/llvm/llvm-project/commit/0c06a389e5937895579effd5e608c79bc6332e53 DIFF:

[clang] 12fefee - [CUDA] Assume the latest known CUDA version if we've found an unknown one.

Author: Artem Belevich Date: 2020-01-28T10:11:42-08:00 New Revision: 12fefeef203ab4ef52d19bcdbd4180608a4deae1 URL: https://github.com/llvm/llvm-project/commit/12fefeef203ab4ef52d19bcdbd4180608a4deae1 DIFF:

[clang] cc14de8 - [CUDA] Fix order of memcpy arguments in __shfl_*(<64-bit type>).

Author: Artem Belevich Date: 2020-01-23T13:17:52-08:00 New Revision: cc14de88da27a8178976972bdc8211c31f7ca9ae URL: https://github.com/llvm/llvm-project/commit/cc14de88da27a8178976972bdc8211c31f7ca9ae DIFF:

Re: [clang] 23058f9 - [OPENMP]Do not use RTTI by default for NVPTX devices.

On Wed, Jan 15, 2020 at 3:09 PM Alexey Bataev wrote: > And I disabled it only for device side, which is NVPTX, no? Can host side > target class report that the target is NVPTX? If you look at the patch, it > disable RTTI only if current triple is NVPTX. Can it be true for the host? > You are

Re: [clang] 23058f9 - [OPENMP]Do not use RTTI by default for NVPTX devices.

On Wed, Jan 15, 2020 at 2:52 PM Alexey Bataev wrote: > 1. The problem is that it does not produce errors, > ATM, it does produce errors when it's disabled. > it leads to the emission of some declaration that cannot be resolved by > the linker. This what I was trying to avoid. > I'm OK with

Re: [clang] 23058f9 - [OPENMP]Do not use RTTI by default for NVPTX devices.

Thank you. In general, RTTI should probably be treated similar to how we deal with inline assembly and ignore errors if they are in the code that we're not going to codegen during this side of compilation. E.g. during host-side compilation we don't complain about GPU-side registers in inline

Re: [clang] 23058f9 - [OPENMP]Do not use RTTI by default for NVPTX devices.

Alexey, This breaks compilation of our cuda code which happens to transitively include protobuf headers. Can you, please, revert it for now until we figure out how RTTI should be handled? --Artem On Tue, Jan 14, 2020 at 3:15 PM Alexey Bataev via cfe-commits < cfe-commits@lists.llvm.org> wrote:

[clang] 7215b7e - [creduce] Fixed a typo in the error message we're looking for.

Author: Artem Belevich Date: 2019-11-07T17:16:51-08:00 New Revision: 7215b7ef530bff896a1da70c6b062e9259f5fde7 URL: https://github.com/llvm/llvm-project/commit/7215b7ef530bff896a1da70c6b062e9259f5fde7 DIFF:

r370792 - [CUDA] Use activemask.b32 instruction to implement __activemask w/ CUDA-9.2+

Author: tra Date: Tue Sep 3 10:31:58 2019 New Revision: 370792 URL: http://llvm.org/viewvc/llvm-project?rev=370792=rev Log: [CUDA] Use activemask.b32 instruction to implement __activemask w/ CUDA-9.2+ vote.ballot instruction is gone in recent CUDA versions and vote.sync.ballot can not be used

r369777 - Fixed a typo.

Author: tra Date: Fri Aug 23 09:24:17 2019 New Revision: 369777 URL: http://llvm.org/viewvc/llvm-project?rev=369777=rev Log: Fixed a typo. Modified: cfe/trunk/lib/Sema/SemaDecl.cpp Modified: cfe/trunk/lib/Sema/SemaDecl.cpp URL:

r359838 - [CUDA] Do not pass deprecated option fo fatbinary

Author: tra Date: Thu May 2 15:37:19 2019 New Revision: 359838 URL: http://llvm.org/viewvc/llvm-project?rev=359838=rev Log: [CUDA] Do not pass deprecated option fo fatbinary CUDA 10.1 tools deprecated some command line options. fatbinary no longer needs --cuda. Differential Revision:

r359248 - [CUDA] Implemented _[bi]mma* builtins.

Author: tra Date: Thu Apr 25 15:28:09 2019 New Revision: 359248 URL: http://llvm.org/viewvc/llvm-project?rev=359248=rev Log: [CUDA] Implemented _[bi]mma* builtins. These builtins provide access to the new integer and sub-integer variants of MMA (matrix multiply-accumulate) instructions provided

r353232 - Basic CUDA-10 support.

Author: tra Date: Tue Feb 5 14:38:58 2019 New Revision: 353232 URL: http://llvm.org/viewvc/llvm-project?rev=353232=rev Log: Basic CUDA-10 support. Differential Revision: https://reviews.llvm.org/D57771 Modified: cfe/trunk/include/clang/Basic/Cuda.h cfe/trunk/lib/Basic/Cuda.cpp

r352799 - [CUDA] add support for the new kernel launch API in CUDA-9.2+.

Author: tra Date: Thu Jan 31 13:34:03 2019 New Revision: 352799 URL: http://llvm.org/viewvc/llvm-project?rev=352799=rev Log: [CUDA] add support for the new kernel launch API in CUDA-9.2+. Instead of calling CUDA runtime to arrange function arguments, the new API constructs arguments in a local

r352798 - [CUDA] Propagate detected version of CUDA to cc1

Author: tra Date: Thu Jan 31 13:32:24 2019 New Revision: 352798 URL: http://llvm.org/viewvc/llvm-project?rev=352798=rev Log: [CUDA] Propagate detected version of CUDA to cc1 ..and use it to control that parts of CUDA compilation that depend on the specific version of CUDA SDK. This patch has a

r349981 - [CUDA] Treat extern global variable shadows same as regular extern vars.

Author: tra Date: Fri Dec 21 17:11:09 2018 New Revision: 349981 URL: http://llvm.org/viewvc/llvm-project?rev=349981=rev Log: [CUDA] Treat extern global variable shadows same as regular extern vars. This fixes compiler crash when we attempted to compile this code: extern __device__ int data;

r349087 - [CUDA] Make all host-side shadows of device-side variables undef.

Author: tra Date: Thu Dec 13 13:43:04 2018 New Revision: 349087 URL: http://llvm.org/viewvc/llvm-project?rev=349087=rev Log: [CUDA] Make all host-side shadows of device-side variables undef. The host-side code can't (and should not) access the values that may only exist on the device side. E.g.

r348662 - [CUDA] Added missing 'inline' for functions defined in a header.

Author: tra Date: Fri Dec 7 14:20:53 2018 New Revision: 348662 URL: http://llvm.org/viewvc/llvm-project?rev=348662=rev Log: [CUDA] Added missing 'inline' for functions defined in a header. Modified: cfe/trunk/lib/Headers/cuda_wrappers/new Modified: cfe/trunk/lib/Headers/cuda_wrappers/new

r343875 - [CUDA] Use all 64 bits of GUID in __nv_module_id

Author: tra Date: Fri Oct 5 11:39:58 2018 New Revision: 343875 URL: http://llvm.org/viewvc/llvm-project?rev=343875=rev Log: [CUDA] Use all 64 bits of GUID in __nv_module_id getGUID() returns an uint64_t and "%x" only prints 32 bits of it. Use PRIx64 format string to print all 64 bits.

r342924 - [CUDA] Added basic support for compiling with CUDA-10.0

Author: tra Date: Mon Sep 24 16:10:44 2018 New Revision: 342924 URL: http://llvm.org/viewvc/llvm-project?rev=342924=rev Log: [CUDA] Added basic support for compiling with CUDA-10.0 Modified: cfe/trunk/include/clang/Basic/Cuda.h cfe/trunk/lib/Basic/Cuda.cpp

r342752 - [CUDA] Fixed parsing of optional template-argument-list.

Author: tra Date: Fri Sep 21 10:46:28 2018 New Revision: 342752 URL: http://llvm.org/viewvc/llvm-project?rev=342752=rev Log: [CUDA] Fixed parsing of optional template-argument-list. We need to consider all tokens that start with '>' when we're checking for the end of an empty template argument

r342749 - [CUDA] Ignore uncallable functions when we check for usual deallocators.

Author: tra Date: Fri Sep 21 10:29:33 2018 New Revision: 342749 URL: http://llvm.org/viewvc/llvm-project?rev=342749=rev Log: [CUDA] Ignore uncallable functions when we check for usual deallocators. Previously clang considered function variants from both sides of compilation and that resulted in

[clang-tools-extra] r342514 - [clang-tidy] Replace redundant checks with an assert().

Author: tra Date: Tue Sep 18 14:51:02 2018 New Revision: 342514 URL: http://llvm.org/viewvc/llvm-project?rev=342514=rev Log: [clang-tidy] Replace redundant checks with an assert(). findStyleKind is only called if D is an explicit identifier with a name, so the checks for operators will never

r341118 - Revert the tests that should've been reverted in rL341115

Author: tra Date: Thu Aug 30 13:53:15 2018 New Revision: 341118 URL: http://llvm.org/viewvc/llvm-project?rev=341118=rev Log: Revert the tests that should've been reverted in rL341115 Removed: cfe/trunk/test/Preprocessor/aux-triple.c Modified:

r341115 - Reverted the "[CUDA/OpenMP] Define only some host macros during device compilation"

Author: tra Date: Thu Aug 30 13:43:39 2018 New Revision: 341115 URL: http://llvm.org/viewvc/llvm-project?rev=341115=rev Log: Reverted the "[CUDA/OpenMP] Define only some host macros during device compilation" The changes were breaking CUDA compilation. Reverted revisions: r340681 D50845

r337587 - [CUDA] Provide integer SIMD functions for CUDA-9.2

Author: tra Date: Fri Jul 20 10:44:34 2018 New Revision: 337587 URL: http://llvm.org/viewvc/llvm-project?rev=337587=rev Log: [CUDA] Provide integer SIMD functions for CUDA-9.2 CUDA-9.2 made all integer SIMD functions into compiler builtins, so clang no longer has access to the implementation of

r335880 - [CUDA] Place all CUDA sections in __NV_CUDA segment on Mac.

Author: tra Date: Thu Jun 28 10:15:52 2018 New Revision: 335880 URL: http://llvm.org/viewvc/llvm-project?rev=335880=rev Log: [CUDA] Place all CUDA sections in __NV_CUDA segment on Mac. That's where CUDA binaries appear to put them. Differential Revision: https://reviews.llvm.org/D48615

Re: r335740 - [analyzer] Allow registering custom statically-linked analyzer checkers

FYI, This commit breaks clang tests. It appears that StaticAnalysisTests misses dependency on clangFrontend. --Artem [60/134] Linking CXX executable tools/clang/unittests/StaticAnalyzer/StaticAnalysisTests FAILED: tools/clang/unittests/StaticAnalyzer/StaticAnalysisTests : &&

r335763 - [CUDA] Use atexit() to call module destructor.

Author: tra Date: Wed Jun 27 11:32:51 2018 New Revision: 335763 URL: http://llvm.org/viewvc/llvm-project?rev=335763=rev Log: [CUDA] Use atexit() to call module destructor. This matches the way NVCC does it. Doing module cleanup at global destructor phase used to work, but is, apparently, too

r335168 - [CUDA] Removed unused __nvvm_* builtins with non-generic pointers.

Author: tra Date: Wed Jun 20 13:34:04 2018 New Revision: 335168 URL: http://llvm.org/viewvc/llvm-project?rev=335168=rev Log: [CUDA] Removed unused __nvvm_* builtins with non-generic pointers. They were hot even hooked into CGBuiltin's machinery. Even if they were, CUDA does not support

r334143 - [CUDA] Check initializers of instantiated template variables.

Author: tra Date: Wed Jun 6 15:37:25 2018 New Revision: 334143 URL: http://llvm.org/viewvc/llvm-project?rev=334143=rev Log: [CUDA] Check initializers of instantiated template variables. We were already performing checks on non-template variables, but the checks on templated ones were missing.

r334108 - [CUDA] Replace 'nv_weak' attributes in CUDA headers with 'weak'.

Author: tra Date: Wed Jun 6 10:52:55 2018 New Revision: 334108 URL: http://llvm.org/viewvc/llvm-project?rev=334108=rev Log: [CUDA] Replace 'nv_weak' attributes in CUDA headers with 'weak'. Differential Revision: https://reviews.llvm.org/D47804 Modified:

r333098 - [CUDA] Fixed the list of GPUs supported by CUDA-9.

Author: tra Date: Wed May 23 09:45:23 2018 New Revision: 333098 URL: http://llvm.org/viewvc/llvm-project?rev=333098=rev Log: [CUDA] Fixed the list of GPUs supported by CUDA-9. Differential Revision: https://reviews.llvm.org/D47268 Modified: cfe/trunk/lib/Driver/ToolChains/Cuda.cpp

r331938 - [CUDA] Added -f[no-]cuda-short-ptr option

Author: tra Date: Wed May 9 16:10:09 2018 New Revision: 331938 URL: http://llvm.org/viewvc/llvm-project?rev=331938=rev Log: [CUDA] Added -f[no-]cuda-short-ptr option The option enables use of 32-bit pointers for accessing const/local/shared memory. The feature is disabled by default.

r330753 - [CUDA] Enable CUDA compilation with CUDA-9.2

Author: tra Date: Tue Apr 24 11:23:19 2018 New Revision: 330753 URL: http://llvm.org/viewvc/llvm-project?rev=330753=rev Log: [CUDA] Enable CUDA compilation with CUDA-9.2 Differential Revision: https://reviews.llvm.org/D45827 Modified: cfe/trunk/include/clang/Basic/Cuda.h

r330296 - [NVPTX, CUDA] Added support for m8n32k16 and m32n8k16 variants of wmma instructions.

Author: tra Date: Wed Apr 18 14:51:48 2018 New Revision: 330296 URL: http://llvm.org/viewvc/llvm-project?rev=330296=rev Log: [NVPTX, CUDA] Added support for m8n32k16 and m32n8k16 variants of wmma instructions. The new instructions were added added for sm_70+ GPUs in CUDA-9.1. Differential

r330280 - [CUDA] added missing __ldg(const signed char *)

Author: tra Date: Wed Apr 18 11:33:43 2018 New Revision: 330280 URL: http://llvm.org/viewvc/llvm-project?rev=330280=rev Log: [CUDA] added missing __ldg(const signed char *) Differential Revision: https://reviews.llvm.org/D45780 Modified: cfe/trunk/lib/Headers/__clang_cuda_intrinsics.h

r329830 - [NVPTX] Removed 'satom' feature which is no longer used.

Author: tra Date: Wed Apr 11 10:51:33 2018 New Revision: 329830 URL: http://llvm.org/viewvc/llvm-project?rev=329830=rev Log: [NVPTX] Removed 'satom' feature which is no longer used. Differential Revision: https://reviews.llvm.org/D45061 Modified: cfe/trunk/lib/Basic/Targets/NVPTX.cpp

r329829 - [NVPTX, CUDA] Improved feature constraints on NVPTX target builtins.

Author: tra Date: Wed Apr 11 10:51:19 2018 New Revision: 329829 URL: http://llvm.org/viewvc/llvm-project?rev=329829=rev Log: [NVPTX, CUDA] Improved feature constraints on NVPTX target builtins. When NVPTX TARGET_BUILTIN specifies sm_XX or ptxYY as required feature, consider those features

r329737 - [CUDA] Added --[no-]cuda-include-ptx=sm_XX|all option.

Author: tra Date: Tue Apr 10 11:38:22 2018 New Revision: 329737 URL: http://llvm.org/viewvc/llvm-project?rev=329737=rev Log: [CUDA] Added --[no-]cuda-include-ptx=sm_XX|all option. Currently we always include PTX into the fatbin along with the GPU code.It about doubles the size of the GPU binary

r329229 - Revert "[CUDA] Check initializers of instantiated template variables."

Author: tra Date: Wed Apr 4 13:48:42 2018 New Revision: 329229 URL: http://llvm.org/viewvc/llvm-project?rev=329229=rev Log: Revert "[CUDA] Check initializers of instantiated template variables." This (temporarily) reverts commit r329127 due to the problems it exposed in TensorFlow. Modified:

r329127 - [CUDA] Check initializers of instantiated template variables.

Author: tra Date: Tue Apr 3 15:41:06 2018 New Revision: 329127 URL: http://llvm.org/viewvc/llvm-project?rev=329127=rev Log: [CUDA] Check initializers of instantiated template variables. We were already performing checks on non-template variables, but the checks on templated ones were missing.

r329099 - Revert "Set calling convention for CUDA kernel"

Author: tra Date: Tue Apr 3 11:29:31 2018 New Revision: 329099 URL: http://llvm.org/viewvc/llvm-project?rev=329099=rev Log: Revert "Set calling convention for CUDA kernel" This reverts r328795 which introduced an issue with referencing __global__ function templates. More details in the original

r328362 - [CUDA] Fixed false error reporting in case of calling H->G->HD->D.

Author: tra Date: Fri Mar 23 12:49:03 2018 New Revision: 328362 URL: http://llvm.org/viewvc/llvm-project?rev=328362=rev Log: [CUDA] Fixed false error reporting in case of calling H->G->HD->D. Launching a kernel from the host code does not generate code for the kernel itself. This fixes an issue

r328213 - [CUDA] add REQUIRES fields for CUDA variants of LTO tests.

Author: tra Date: Thu Mar 22 09:47:41 2018 New Revision: 328213 URL: http://llvm.org/viewvc/llvm-project?rev=328213=rev Log: [CUDA] add REQUIRES fields for CUDA variants of LTO tests. Also relax checking for nvptx triple. This should avoid test failure if the test is executed on 32-bit platform.

Re: [PATCH] D44691: [CUDA] Disable LTO for device-side compilations.

On Thu, Mar 22, 2018 at 12:02 AM Yvan Roux wrote: > This patch broke ARM/AArch64 bots, see: > > http://lab.llvm.org:8011/builders/clang-cmake-armv8-full/builds/841/steps/ninja%20check%201/logs/FAIL%3A%20Clang%3A%3Athinlto.cu > > ​Sorry about that. I'll fix it ASAP. ​ --

r328161 - [CUDA] Disable LTO for device-side compilations.

Author: tra Date: Wed Mar 21 15:22:59 2018 New Revision: 328161 URL: http://llvm.org/viewvc/llvm-project?rev=328161=rev Log: [CUDA] Disable LTO for device-side compilations. This fixes host-side LTO during CUDA compilation. Before, LTO pipeline construction was clashing with CUDA pipeline

r328158 - [NVPTX] Make tensor shape part of WMMA intrinsic's name.

Author: tra Date: Wed Mar 21 14:55:02 2018 New Revision: 328158 URL: http://llvm.org/viewvc/llvm-project?rev=328158=rev Log: [NVPTX] Make tensor shape part of WMMA intrinsic's name. This is needed for the upcoming implementation of the new 8x32x16 and 32x8x16 variants of WMMA instructions

Re: r328006 - [NVPTX] Make tensor load/store intrinsics overloaded.

t; ArrayRef, ArrayRef, const > llvm::Twine &): Assertion `(i >= FTy->getNumParams()|| > FTy->getParamType(i) == Args[i]->getType()) && "Calling a function with > a bad signature!"' failed. > > Cheers, > Rafael > > > Artem Belevich via cfe-c

r328006 - [NVPTX] Make tensor load/store intrinsics overloaded.

Author: tra Date: Tue Mar 20 10:18:59 2018 New Revision: 328006 URL: http://llvm.org/viewvc/llvm-project?rev=328006=rev Log: [NVPTX] Make tensor load/store intrinsics overloaded. This way we can support address-space specific variants without explicitly encoding the space in the name of the

r325814 - [CUDA] Added missing functions.

Author: tra Date: Thu Feb 22 10:40:52 2018 New Revision: 325814 URL: http://llvm.org/viewvc/llvm-project?rev=325814=rev Log: [CUDA] Added missing functions. Initial commit missed sincos(float), llabs() and few atomics that we used to pull in from device_functions.hpp, which we no longer include.

r325626 - [CUDA] Added missing __threadfence_system() function for CUDA9.

Author: tra Date: Tue Feb 20 13:25:30 2018 New Revision: 325626 URL: http://llvm.org/viewvc/llvm-project?rev=325626=rev Log: [CUDA] Added missing __threadfence_system() function for CUDA9. Modified: cfe/trunk/lib/Headers/__clang_cuda_device_functions.h Modified:

r323713 - [CUDA] Added partial support for CUDA-9.1

Author: tra Date: Mon Jan 29 16:00:12 2018 New Revision: 323713 URL: http://llvm.org/viewvc/llvm-project?rev=323713=rev Log: [CUDA] Added partial support for CUDA-9.1 Clang can use CUDA-9.1 now, though new APIs (are not implemented yet. The major change is that headers in CUDA-9.1 went through

r323345 - [CUDA] Disable PGO and coverage instrumentation in NVPTX.

Author: tra Date: Wed Jan 24 09:41:02 2018 New Revision: 323345 URL: http://llvm.org/viewvc/llvm-project?rev=323345=rev Log: [CUDA] Disable PGO and coverage instrumentation in NVPTX. NVPTX does not have runtime support necessary for profiling to work and even call arc collection is prohibitively

r323239 - [CUDA] CUDA has no device-side library builtins.

Author: tra Date: Tue Jan 23 11:08:18 2018 New Revision: 323239 URL: http://llvm.org/viewvc/llvm-project?rev=323239=rev Log: [CUDA] CUDA has no device-side library builtins. We should (almost) never consider a device-side declaration to match a library builtin functio. Otherwise clang may

r322742 - [DeclPrinter] Fix two cases that crash clang -ast-print.

Author: tra Date: Wed Jan 17 11:29:39 2018 New Revision: 322742 URL: http://llvm.org/viewvc/llvm-project?rev=322742=rev Log: [DeclPrinter] Fix two cases that crash clang -ast-print. Both are related to handling anonymous structures. * clang didn't handle () around an anonymous struct variable. *

r321326 - [CUDA] More fixes for __shfl_* intrinsics.

Author: tra Date: Thu Dec 21 15:52:09 2017 New Revision: 321326 URL: http://llvm.org/viewvc/llvm-project?rev=321326=rev Log: [CUDA] More fixes for __shfl_* intrinsics. * __shfl_{up,down}* uses unsigned int for the third parameter. * added [unsigned] long overloads for non-sync shuffles.

<    1   2   3   4   5   6   7   8   9   >