Comments (4)
The first type of errors is related to an expected template argument list:
/usr/local/cub-2.1.0/cub/block/specializations/../../block/../block/specializations/../../warp/specializations/../../thread/thread_store.cuh:337:56: error:
a template argument list is expected after a name prefixed by the template keyword [-Wmissing-template-arg-list-after-template-kw]
337 | IterateThreadStore<0, VOLATILE_MULTIPLE>::template Dereference(
| ^
1 error generated when compiling for host.
The error occurs with LLVM >= 19
and all CUB versions. LLVM <= 18
doesn't throw such an error.
Fixed by #1535.
from hipify.
The second type of errors is related to the requested alignment, which must be 8192 bytes or smaller:
C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5.0/include\cuda/std\detail/libcxx/include\__utility\..\__type_traits/aligned_storage.h(134,1): error G9DC7A175: requested alignment must be 8192 bytes or smaller
134 | _CREATE_ALIGNED_STORAGE_SPECIALIZATION(0x4000);
| ^ ~~~~~~
C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5.0/include\cuda/std\detail/libcxx/include\__utility\..\__type_traits/aligned_storage.h:112:12: note: expanded from macro '_CREATE_ALIGNED_STORAGE_SPECIALIZATION'
112 | struct _ALIGNAS(n) type\
| ^ ~
C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5.0/include\cuda\std\detail\libcxx/include/__config:436:23: note: expanded from macro '_ALIGNAS'
436 | # define _ALIGNAS(x) alignas(x)
| ^ ~
1 error generated when compiling for host.
The error occurs with CUB > 1.9.8
and CUB shipped internally with CUDA.
Fixed by #1537.
from hipify.
The third type of errors is related to the explicit qualification required to use a member from qa dependent base class:
/usr/local/cuda-11.5.2/include/cub/block/specializations/../../block/../block/radix_rank_sort_operations.cuh:120:20: error: explicit qualification required to use member 'ProcessFloatMinusZero' from dependent base class
120 | return BFE(ProcessFloatMinusZero(key), bit_start, num_bits);
| ^
/usr/local/cuda-11.5.2/include/cub/block/specializations/../../block/block_radix_rank.cuh:409:50: note: in instantiation of member function 'cub::BFEDigitExtractor<double>::Digit' requested here
409 | unsigned int digit = digit_extractor.Digit(keys[ITEM]);
| ^
/usr/local/cuda-11.5.2/include/cub/block/specializations/../../block/block_radix_sort.cuh:261:72: note: in instantiation of function template specialization 'cub::BlockRadixRank<1024, 4, false>::RankKeys<unsigned long long, 4, cub::BFEDigitExtractor<double>>' requested here
261 | AscendingBlockRadixRank(temp_storage.asending_ranking_storage).RankKeys(
| ^
/usr/local/cuda-11.5.2/include/cub/block/specializations/../../block/block_radix_sort.cuh:343:13: note: in instantiation of member function 'cub::BlockRadixSort<double, 1024, 4>::RankKeys' requested here
343 | RankKeys(unsigned_keys, ranks, digit_extractor, is_descending);
| ^
/usr/local/cuda-11.5.2/include/cub/block/specializations/../../block/block_radix_sort.cuh:517:9: note: in instantiation of function template specialization 'cub::BlockRadixSort<double, 1024, 4>::SortBlocked<0, 1>' requested here
517 | SortBlocked(keys, values, begin_bit, end_bit, Int2Type<false>(), Int2Type<KEYS_ONLY>());
| ^
1 error generated when compiling for host.
The error occurs with CUB shipped internally with 11.4.0 <= CUDA < 11.6
.
from hipify.
Finally implemented
from hipify.
Related Issues (20)
- [HIPIFY] Makefile generation HOT 6
- [HIPIFY] Does HIPIFY support on WSL2? HOT 1
- [HIPIFY] hipify-clang terminates with constexpr function cannot overload function with same signature HOT 9
- [HIPIFY] Cuda graph HOT 2
- [HIPIFY][BLAS] cublasSetMathMode and CUBLAS_GEMM_DEFAULT_TENSOR_OP HOT 1
- [HIPIFY] Changing compiler and cuda environment related section to ROCm? HOT 3
- [HIPIFY][win] cannot find CUDA installation HOT 18
- [HIPIFY][tests][bug] `cusparse2rocsparse_10000.cu` failed with clang crash HOT 1
- [HIPIFY] How to hipify the programs based nvidia cutlass HOT 5
- [HIPIFY][build][LLVM] build fails, if multiple llvm/clang versions are installed HOT 4
- [HIPIFY] Linking fails when LLVM libraries were compiled as shared library. HOT 1
- [HIPIFY] hipconvertinplace-perl.sh does not seem to convert cuFuncSetAttribute and cuFuncSetCacheConfig HOT 2
- [HIPIFY] amd-staging branch build on Windows runs but doesn't replace anything in generated hip file HOT 9
- [HIPIFY][Issue]: "fatal error: '__clang_cuda_runtime_wrapper.h' file not found" while generating HOT 6
- [HIPIFY][Feature] Adding ability to hipify only header files in hipconvertinplace-perl.sh HOT 2
- [HIPIFY][Issue] ERROR when build HIPIFY using Rocm's LLVM HOT 2
- [HIPIFY][Feature] Support for `math_constants.h` HOT 1
- [HIPIFY][Issue] Error loading cub HOT 2
- [HIPIFY][build][Issue] std::__throw_bad_array_new_length build failure on Red Hat Enterprise Linux Server release 7.9 HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hipify.