summaryrefslogtreecommitdiff
path: root/test/CodeGenCUDA
AgeCommit message (Expand)AuthorFilesLines
2016-06-06[CUDA] Add implicit conversion of __launch_bounds__ arguments to rvalue.Artem Belevich1-0/+5
2016-05-31[CUDA] Conservatively mark inline asm as convergent.Justin Lebar1-0/+6
2016-05-20Avoid depending on test inputes that aren't in InputsReid Kleckner2-133/+157
2016-05-19[CUDA] Do not allow non-empty destructors for global device-side variables.Artem Belevich1-3/+79
2016-05-19[CUDA] Split device-var-init.cu tests into separate Sema and CodeGen parts.Artem Belevich1-199/+33
2016-05-19[CUDA] Enable fusing FP ops (-ffp-contract=fast) for CUDA by default.Artem Belevich1-0/+32
2016-05-10[CUDA] Fix flush-denormals.cu test so that it checks what it intends to CHECK.Justin Lebar1-3/+5
2016-05-09[CUDA] Restrict init of local __shared__ variables to empty constructors only.Artem Belevich2-33/+10
2016-05-09[CUDA] Only __shared__ variables can be static local on device side.Artem Belevich2-8/+8
2016-05-02[CUDA] Make sure device-side __global__ functions are always visible.Artem Belevich1-2/+11
2016-04-05[CUDA] Add -fcuda-flush-denormals-to-zero.Justin Lebar1-0/+23
2016-03-30[CUDA] Add -disable-llvm-passes to CodeGenCUDA/link-device-bitcode.cu. NFCJustin Lebar1-4/+4
2016-03-29[CUDA] Remove three obsolete CUDA cc1 flags.Justin Lebar2-18/+4
2016-03-23[CUDA] Merge most of CodeGenCUDA/function-overload.cu into SemaCUDA/function-...Justin Lebar1-230/+4
2016-03-02Fixed test failure platforms with name mangling different from Linux.Artem Belevich1-3/+4
2016-03-02[CUDA] Do not generate unnecessary runtime init code.Artem Belevich1-0/+20
2016-03-02[CUDA] Emit host-side 'shadows' for device-side global variablesArtem Belevich2-7/+46
2016-02-24[CUDA] Mark all CUDA device-side function defs, decls, and calls as convergent.Justin Lebar2-1/+40
2016-02-12[CUDA] Tweak attribute-based overload resolution to match nvcc behavior.Artem Belevich1-17/+106
2016-02-11[CUDA] Don't crash when trying to printf a non-scalar object.Justin Lebar1-0/+17
2016-02-02[CUDA] Do not allow dynamic initialization of global device side variables.Artem Belevich1-0/+393
2016-01-28[CUDA] Generate CUDA's printf alloca in its function's entry block.Justin Lebar1-33/+23
2016-01-25[CUDA] Don't generate aliases for static extern "C" functions.Justin Lebar1-0/+17
2016-01-23[CUDA] Make printf work.Justin Lebar2-0/+55
2015-12-17[CUDA] Make vtable construction aware of host/device side of CUDA compilation.Artem Belevich1-0/+61
2015-10-27Allow linking multiple bitcode files.Artem Belevich2-2/+32
2015-09-23[CUDA] __global__ functions should always be visible externally.Artem Belevich1-6/+1
2015-09-22[CUDA] Allow function overloads in CUDA based on host/device attributes.Artem Belevich1-0/+214
2015-09-22[CUDA] Add implicit __attribute__((used)) to all __global__ functions.Artem Belevich1-0/+15
2015-09-10[CUDA] Postprocess bitcode linked in during device-side CUDA compilation.Artem Belevich2-0/+94
2015-09-10[CUDA] Allow trivial constructors as initializer for __shared__ variables.Artem Belevich1-0/+14
2015-08-22[CUDA] Change initializer for CUDA device code based on CUDA documentation.Jingyue Wu2-7/+7
2015-08-11Revert "[CUDA] Add implicit __attribute__((used)) to all __global__ functions."Daniel Jasper1-15/+0
2015-08-10[CUDA] Add implicit __attribute__((used)) to all __global__ functions.Artem Belevich1-0/+15
2015-05-11[cuda] Fixed test case failure on s390xArtem Belevich1-2/+2
2015-05-07Fixed test failure on machines with 32-bit size_t.Artem Belevich1-1/+1
2015-05-07[cuda] Include GPU binary into host object file and generate init/deinit code.Artem Belevich1-1/+40
2015-04-27[cuda] treat file scope __asm as __host__ and ignore it during device-side co...Artem Belevich1-0/+6
2015-04-21[cuda] Allow using integral non-type template parameters as launch_bounds att...Artem Belevich1-0/+51
2015-04-21[cuda] Added support for CUDA built-in variables.Artem Belevich1-0/+28
2015-04-21Revert r235398 "[cuda] Added support for CUDA built-in variables."Artem Belevich1-28/+0
2015-04-21[cuda] Added support for CUDA built-in variables.Artem Belevich1-0/+28
2015-03-25Fix addrspace when emitting constructors of static local variablesJingyue Wu1-0/+17
2015-03-13Test case updates for explicit type parameter to the gep operatorDavid Blaikie1-1/+1
2015-02-27Update Clang tests to handle explicitly typed load changes in LLVM.David Blaikie1-6/+6
2015-02-24CUDA: Add option to allow host device functions to call host functionsJacques Pienaar1-0/+32
2015-02-02When generating llvm.used, we may need an addrspacecast instead of a bitcast.Justin Holewinski1-0/+8
2014-12-15IR: Make metadata typeless in assembly, clang sideDuncan P. N. Exon Smith2-4/+4
2014-04-28Move all CUDA testing inputs to Inputs/ subdirectory inside the tests.Eli Bendersky7-6/+26
2014-04-15Add test case for r206302Eli Bendersky1-0/+30
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-04 11:55:12 +0000