Alex Zinenko 11d12670da GPUToCUDA: attach CUBIN to the nested module rather than to the function ... Originally, we were attaching attributes containing CUBIN blobs to the kernel function called by `gpu.launch_func`. This kernel is now contained in a nested module that is used as a compilation unit. Attach compiled CUBIN blobs to the module rather than to the function since we were compiling the module. This also avoids duplication of the attribute on multiple kernels within the same module. PiperOrigin-RevId: 273497303		2019-10-08 05:11:26 -07:00
..
GPUCommon	Moving the GPUIndexIntrinsicOpLowering template to a common location	2019-10-04 06:20:05 -07:00
GPUToCUDA	GPUToCUDA: attach CUBIN to the nested module rather than to the function	2019-10-08 05:11:26 -07:00
GPUToNVVM	Support reduction of partial warps.	2019-10-07 03:31:00 -07:00
GPUToROCDL	Moving the GPUIndexIntrinsicOpLowering template to a common location	2019-10-04 06:20:05 -07:00
GPUToSPIRV	Use named modules for gpu.launch_func	2019-10-08 04:30:32 -07:00
LoopToStandard	NFC: rename Conversion/ControlFlowToCFG to Conversion/LoopToStandard	2019-10-03 01:35:03 -07:00
LoopsToGPU	NFC: Finish replacing FunctionPassBase/ModulePassBase with OpPassBase.	2019-09-13 13:34:27 -07:00
StandardToLLVM	Replace constexpr MemRefType::kDynamicStrideOrOffset by a MemRefType:;getDynamicStrideOrOffset() method - NFC	2019-10-04 08:58:09 -07:00
StandardToSPIRV	Fix a number of Clang-Tidy warnings.	2019-09-23 02:34:27 -07:00
VectorToLLVM	Fix a number of Clang-Tidy warnings.	2019-09-23 02:34:27 -07:00
CMakeLists.txt	NFC: rename Conversion/ControlFlowToCFG to Conversion/LoopToStandard	2019-10-03 01:35:03 -07:00