summaryrefslogtreecommitdiff
path: root/test/CodeGenOpenCL
AgeCommit message (Expand)Author
2017-04-18Debug Info: Remove special-casing of indirect function argument handling.Adrian Prantl
2017-04-17CodeGen: Let byval parameter use alloca address spaceYaxun Liu
2017-04-17CodeGen: Let lifetime intrinsic use alloca address spaceYaxun Liu
2017-04-14[AMDGPU][GFX9] Set +fp32-denormals for >=gfx900 unless -cl-denorms-are-zero i...Konstantin Zhuravlyov
2017-04-11[OpenCL] Map default address space to alloca address spaceYaxun Liu
2017-04-06[AMDGPU] Temporarily change constant address space from 4 to 2 for the new ad...Yaxun Liu
2017-04-06[AMDGPU] Translate reqd_work_group_size into amdgpu_flat_work_group_sizeStanislav Mekhanoshin
2017-04-05[OpenCL] Enables passing sampler initializer to function argumentEgor Churaev
2017-04-04Preserve vec3 type.Jin-Gu Kang
2017-03-31[OpenCL] Do not generate "kernel_arg_type_qual" metadata for non-pointer argsEgor Churaev
2017-03-27[OpenCL] Extended mapping of parcing CodeGen argumentsEgor Churaev
2017-03-25[AMDGPU] Switch address space mapping by triple environment amdgizYaxun Liu
2017-03-21Fix array sizes where address space is not yet knownKonstantin Zhuravlyov
2017-03-21[OpenCL] Added implicit conversion rank for overloading functions with vector...Egor Churaev
2017-03-13AMDGPU: Make 0 the private nullptr valueMatt Arsenault
2017-03-10[AMDGPU] Add builtin functions readlane ds_permute mov_dppYaxun Liu
2017-03-09[DebugInfo] Append extended dereferencing mechanism to variables' DIExpressio...Konstantin Zhuravlyov
2017-03-08[DebugInfo] Add address space when creating DIDerivedTypesKonstantin Zhuravlyov
2017-02-25AMDGPU: export s_sendmsg{halt} instrinsicsJan Vesely
2017-02-25AMDGPU: export l1 cache invalidation intrinsicsJan Vesely
2017-02-25AMDGPU: export s_waitcnt builtinJan Vesely
2017-02-22AMDGPU: Add fmed3 half builtinMatt Arsenault
2017-02-22[OpenCL] r600 needs OpenCL kernel calling conventionJan Vesely
2017-02-16[OpenCL] Correct ndrange_t implementationAnastasia Stulova
2017-02-07AMDGPU: Add a test checking alignments of emitted globals/allocasMatt Arsenault
2017-01-31AMDGPU: Add builtin for fmed3 intrinsicMatt Arsenault
2017-01-27[OpenCL] Add missing address spaces in IR generation of blocksAnastasia Stulova
2017-01-23AMDGPU: Update for changed subtarget feature nameMatt Arsenault
2017-01-20AMDGPU: Add builtin for getreg intrinsicMatt Arsenault
2016-12-23[OpenCL] Align fake address space map with the SPIR target maps.Egor Churaev
2016-12-23Fix problems in "[OpenCL] Enabling the usage of CLK_NULL_QUEUE as compare ope...Egor Churaev
2016-12-23Cleanup the handling of noinline function attributes, -fno-inline,Chandler Carruth
2016-12-22Add the alloc_size attribute to clang, attempt 2.George Burgess IV
2016-12-20Revert "[OpenCL] Enabling the usage of CLK_NULL_QUEUE as compare operand."Daniel Jasper
2016-12-20[OpenCL] Enabling the usage of CLK_NULL_QUEUE as compare operand.Egor Churaev
2016-12-20Revert r290149: Add the alloc_size attribute to clang.Chandler Carruth
2016-12-20Add the alloc_size attribute to clang.George Burgess IV
2016-12-18Recommit r289979 [OpenCL] Allow disabling types and declarations associated w...Yaxun Liu
2016-12-16Revert r289979 due to regressionsYaxun Liu
2016-12-16[OpenCL] Allow disabling types and declarations associated with extensionsYaxun Liu
2016-12-15Re-commit r289252 and r289285, and fix PR31374Yaxun Liu
2016-12-14Revert 289252 (and follow-up 289285), it caused PR31374Nico Weber
2016-12-13Fixing build failure by adding triple option to new test condition.Neil Hickey
2016-12-13Improve handling of floating point literals in OpenCL to only use double prec...Neil Hickey
2016-12-13[OpenCL] Enable unroll hint for OpenCL 1.x.Egor Churaev
2016-12-09Add support for non-zero null pointer for C and OpenCLYaxun Liu
2016-12-07[OpenCL] Added a LIT test for ensuring address space mangling is done the sam...Alexey Bader
2016-12-07[OpenCL] Fix SPIR version generation.Alexey Bader
2016-11-29[OpenCL] Prevent generation of globals in non-constant AS for OpenCL.Anastasia Stulova
2016-11-18[AMDGPU] Change frexp.exp builtin to return i16 for f16 inputKonstantin Zhuravlyov
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-02 18:54:35 +0000