summaryrefslogtreecommitdiffstats
path: root/clang/test/CodeGenOpenCL
Commit message (Expand)AuthorAgeFilesLines
* Add more tests for OpenCL atomic builtin functionsYaxun Liu2017-09-132-1/+45
* [AMDGPU] Change addr space of clk_event_t, queue_t and reserve_id_t to globalYaxun Liu2017-09-131-8/+11
* [OpenCL] Add half load and store builtinsJan Vesely2017-09-071-0/+39
* [OpenCL] Do not use vararg in emitted functions for enqueue_kernelYaxun Liu2017-09-031-18/+72
* Adapt testcases to LLVM change r312144 in DIGlobalVariableExpressionAdrian Prantl2017-08-301-20/+20
* Parse and print DIExpressions inline to ease IR and MIR testingReid Kleckner2017-08-231-21/+18
* Attempt to fix failure in CodeGenOpenCL/atomic-ops.cl againYaxun Liu2017-08-151-20/+20
* Attempt to fix failure in CodeGenOpenCL/atomic-ops.clYaxun Liu2017-08-151-5/+5
* Remove -finclude-default-header in OpenCL atomic testsYaxun Liu2017-08-152-5/+43
* [OpenCL] Support variable memory scope in atomic builtinsYaxun Liu2017-08-152-1/+79
* [OpenCL] Allow targets to select address space per typeSven van Haastregt2017-08-151-2/+12
* AMDGPU: Use direct struct returns and argumentsMatt Arsenault2017-08-093-29/+553
* Add OpenCL 2.0 atomic builtin functions as Clang builtinYaxun Liu2017-08-042-0/+213
* [OpenCL] Add missing subgroup builtinsJoey Gouly2017-08-011-0/+5
* [OpenCL] Enable subgroup extension in testsJoey Gouly2017-07-311-1/+1
* [OpenCL] Add extension Sema check for subgroup builtinsJoey Gouly2017-07-312-0/+4
* [OpenCL] Fix access qualifiers metadata for kernel arguments with typedefAlexey Sotkin2017-07-261-0/+22
* [OpenCL] Added extended tests on metadata generation for half data type and a...Egor Churaev2017-07-181-9/+28
* [AMDGPU] Fix size and alignment of size_t and pointer typesYaxun Liu2017-07-053-28/+98
* [AMDGPU] Fix regressions on mesa/clover with libclc due to address spaceYaxun Liu2017-07-041-0/+2
* CodeGen: Fix invalid bitcast for coerced function argumentYaxun Liu2017-06-291-5/+47
* [OpenCL] Fix OpenCL and SPIR version metadata generation.Alexey Bader2017-06-201-8/+9
* [OpenCL] spir_kern by defaul: fix old test casesPekka Jaaskelainen2017-06-016-8/+8
* [OpenCL] Makes kernels use the SPIR_KERNEL CC by default.Pekka Jaaskelainen2017-06-011-0/+65
* Fix issue with test that caused bildbot failureJaved Absar2017-05-301-1/+1
* [OpenCL] Test on half immediate support.Egor Churaev2017-05-291-0/+17
* IRGen: Add optnone attribute on function during O0Mehdi Amini2017-05-291-25/+25
* Resubmit r303861.Konstantin Zhuravlyov2017-05-261-0/+7
* Revert "[AMDGPU] add __builtin_amdgcn_s_getpc"Reid Kleckner2017-05-251-7/+0
* [AMDGPU] add __builtin_amdgcn_s_getpcTim Corringham2017-05-251-0/+7
* [AMDGPU] Do not require opencl triple environment for OpenCLYaxun Liu2017-05-237-1/+8
* CodeGen: Cast alloca to expected address spaceYaxun Liu2017-05-188-8/+68
* [OpenCL] Emit function-scope variable in constant address space as static var...Yaxun Liu2017-05-153-27/+31
* [OpenCL] Add intel_reqd_sub_group_size attribute supportXiuli Pan2017-05-041-0/+4
* Debug Info: Remove special-casing of indirect function argument handling.Adrian Prantl2017-04-181-2/+1
* CodeGen: Let byval parameter use alloca address spaceYaxun Liu2017-04-171-0/+18
* CodeGen: Let lifetime intrinsic use alloca address spaceYaxun Liu2017-04-171-0/+15
* [AMDGPU][GFX9] Set +fp32-denormals for >=gfx900 unless -cl-denorms-are-zero i...Konstantin Zhuravlyov2017-04-141-0/+13
* [OpenCL] Map default address space to alloca address spaceYaxun Liu2017-04-113-14/+31
* [AMDGPU] Temporarily change constant address space from 4 to 2 for the new ad...Yaxun Liu2017-04-062-1/+3
* [AMDGPU] Translate reqd_work_group_size into amdgpu_flat_work_group_sizeStanislav Mekhanoshin2017-04-061-0/+12
* [OpenCL] Enables passing sampler initializer to function argumentEgor Churaev2017-04-051-0/+4
* Preserve vec3 type.Jin-Gu Kang2017-04-041-0/+24
* [OpenCL] Do not generate "kernel_arg_type_qual" metadata for non-pointer argsEgor Churaev2017-03-311-6/+7
* [OpenCL] Extended mapping of parcing CodeGen argumentsEgor Churaev2017-03-271-4/+25
* [AMDGPU] Switch address space mapping by triple environment amdgizYaxun Liu2017-03-251-0/+9
* Fix array sizes where address space is not yet knownKonstantin Zhuravlyov2017-03-211-0/+12
* [OpenCL] Added implicit conversion rank for overloading functions with vector...Egor Churaev2017-03-211-0/+46
* AMDGPU: Make 0 the private nullptr valueMatt Arsenault2017-03-132-56/+144
* [AMDGPU] Add builtin functions readlane ds_permute mov_dppYaxun Liu2017-03-102-0/+36
OpenPOWER on IntegriCloud