summaryrefslogtreecommitdiffstats
path: root/test/CodeGenCUDA
Commit message (Expand)AuthorAgeFilesLines
* [CUDA][HIP] Allow function-scope static const variableYaxun Liu2018-07-281-0/+6
* [HIP] Support -fcuda-flush-denormals-to-zero for amdgcnYaxun Liu2018-07-211-0/+15
* [HIP] Register/unregister device fat binary only onceYaxun Liu2018-07-201-4/+19
* [FileCheck] Add -allow-deprecated-dag-overlap to failing clang testsJoel E. Denny2018-07-112-10/+10
* [CUDA] Use atexit() to call module destructor.Artem Belevich2018-06-271-2/+2
* [CUDA][HIP] Allow CUDA __global__ functions to have amdgpu kernel attributesYaxun Liu2018-06-121-0/+37
* [CUDA][HIP] Set kernel calling convention before arrange functionYaxun Liu2018-06-121-0/+39
* [CUDA] Fix emission of constant strings in sectionsJonas Hahnfeld2018-06-081-3/+3
* [CUDA][HIP] Do not emit type info when compiling for deviceYaxun Liu2018-06-051-2/+9
* [HIP] Support offloading by linker scriptYaxun Liu2018-05-181-17/+23
* Fix failure in lit test kernel-call.cu due to name manglingYaxun Liu2018-04-251-2/+2
* Fix lit test kernel-call.cu failure on ps4 due to dso_localYaxun Liu2018-04-251-2/+2
* Fix failure in lit test kernel-call.cuYaxun Liu2018-04-251-1/+1
* [HIP] Add hip input kind and codegen for kernel launchingYaxun Liu2018-04-253-45/+74
* [CUDA] Set LLVM calling convention for CUDA kernelYaxun Liu2018-04-201-0/+41
* [CUDA] Register relocatable GPU binariesJonas Hahnfeld2018-04-201-45/+66
* Remove -cc1 option "-backend-option".Eli Friedman2018-04-121-1/+1
* Fix typos in clangAlexander Kornienko2018-04-062-2/+2
* Revert "Set calling convention for CUDA kernel"Artem Belevich2018-04-031-29/+0
* [CUDA] Let device-side shared variables be initialized with undefYaxun Liu2018-04-022-36/+93
* Set calling convention for CUDA kernelYaxun Liu2018-03-291-0/+29
* Disable emitting static extern C aliases for amdgcn target for CUDAYaxun Liu2018-03-291-0/+3
* Really fix test on windows.Rafael Espindola2018-02-231-3/+3
* Fix one last test on a windows host.Rafael Espindola2018-02-231-1/+1
* [CUDA] CUDA has no device-side library builtins.Artem Belevich2018-01-231-0/+22
* CodeGenModule: Always output wchar_size, check LLVM assumptions.Matthias Braun2017-05-201-2/+2
* Use FPContractModeKind universallyAdam Nemet2017-03-291-2/+2
* [CodeGen] [CUDA] Add the ability set default attrs on functions in linked mod...Justin Lebar2017-01-251-0/+62
* [CUDA] Improve target attribute checking for function templates.Artem Belevich2016-12-071-3/+3
* [CUDA] Rename cuda_builtin_vars.h to __clang_cuda_builtin_vars.h.Justin Lebar2016-10-081-1/+1
* [CUDA] Add missing ':' to noexcept.cu test.Justin Lebar2016-10-051-1/+1
* [CUDA] Mark device functions as nounwind.Justin Lebar2016-10-043-5/+44
* [CUDA] Disallow overloading destructors.Justin Lebar2016-10-031-8/+0
* [CUDA] Raise an error if a wrong-side call is codegen'ed.Justin Lebar2016-08-151-32/+0
* [CUDA] Place GPU binary into .nv_fatbin section and align it by 8.Artem Belevich2016-08-121-2/+4
* [CUDA] Align kernel launch args correctly when the LLVM type's alignment is d...Justin Lebar2016-07-271-0/+36
* NVPTX: Use the nvvm builtins to read SRegs rather than the legacy ptx onesJustin Bogner2016-07-071-12/+12
* [CUDA] Give templated device functions internal linkage, templated kernels ex...Justin Lebar2016-06-301-2/+2
* [CUDA] Add implicit conversion of __launch_bounds__ arguments to rvalue.Artem Belevich2016-06-061-0/+5
* [CUDA] Conservatively mark inline asm as convergent.Justin Lebar2016-05-311-0/+6
* Avoid depending on test inputes that aren't in InputsReid Kleckner2016-05-202-133/+157
* [CUDA] Do not allow non-empty destructors for global device-side variables.Artem Belevich2016-05-191-3/+79
* [CUDA] Split device-var-init.cu tests into separate Sema and CodeGen parts.Artem Belevich2016-05-191-199/+33
* [CUDA] Enable fusing FP ops (-ffp-contract=fast) for CUDA by default.Artem Belevich2016-05-191-0/+32
* [CUDA] Fix flush-denormals.cu test so that it checks what it intends to CHECK.Justin Lebar2016-05-101-3/+5
* [CUDA] Restrict init of local __shared__ variables to empty constructors only.Artem Belevich2016-05-092-33/+10
* [CUDA] Only __shared__ variables can be static local on device side.Artem Belevich2016-05-092-8/+8
* [CUDA] Make sure device-side __global__ functions are always visible.Artem Belevich2016-05-021-2/+11
* [CUDA] Add -fcuda-flush-denormals-to-zero.Justin Lebar2016-04-051-0/+23
* [CUDA] Add -disable-llvm-passes to CodeGenCUDA/link-device-bitcode.cu. NFCJustin Lebar2016-03-301-4/+4
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-21 19:16:30 +0000