Thanks for using Compiler Explorer
Sponsors
Jakt
C++
Ada
Analysis
Android Java
Android Kotlin
Assembly
C
C3
Carbon
C++ (Circle)
CIRCT
Clean
CMake
CMakeScript
COBOL
C++ for OpenCL
MLIR
Cppx
Cppx-Blue
Cppx-Gold
Cpp2-cppfront
Crystal
C#
CUDA C++
D
Dart
Elixir
Erlang
Fortran
F#
GLSL
Go
Haskell
HLSL
Hook
Hylo
IL
ispc
Java
Julia
Kotlin
LLVM IR
LLVM MIR
Modula-2
Nim
Objective-C
Objective-C++
OCaml
Odin
OpenCL C
Pascal
Pony
Python
Racket
Ruby
Rust
Snowball
Scala
Slang
Solidity
Spice
SPIR-V
Swift
LLVM TableGen
Toit
TypeScript Native
V
Vala
Visual Basic
Vyper
WASM
Zig
Javascript
GIMPLE
Ygen
cuda source #1
Output
Compile to binary object
Link to binary
Execute the code
Intel asm syntax
Demangle identifiers
Verbose demangling
Filters
Unused labels
Library functions
Directives
Comments
Horizontal whitespace
Debug intrinsics
Compiler
10.0.0 sm_75 CUDA-10.2
10.0.1 sm_75 CUDA-10.2
11.0.0 sm_75 CUDA-10.2
16.0.0 sm_90 CUDA-11.8
17.0.1(libc++) sm_90 CUDA-12.1
18.1.0(libc++) sm_90 CUDA-12.3.1
19.1.0 sm_90 CUDA-12.5.1
NVCC 10.0.130
NVCC 10.1.105
NVCC 10.1.168
NVCC 10.1.243
NVCC 10.2.89
NVCC 11.0.2
NVCC 11.0.3
NVCC 11.1.0
NVCC 11.1.1
NVCC 11.2.0
NVCC 11.2.1
NVCC 11.2.2
NVCC 11.3.0
NVCC 11.3.1
NVCC 11.4.0
NVCC 11.4.1
NVCC 11.4.2
NVCC 11.4.3
NVCC 11.4.4
NVCC 11.5.0
NVCC 11.5.1
NVCC 11.5.2
NVCC 11.6.0
NVCC 11.6.1
NVCC 11.6.2
NVCC 11.7.0
NVCC 11.7.1
NVCC 11.8.0
NVCC 12.0.0
NVCC 12.0.1
NVCC 12.1.0
NVCC 12.2.1
NVCC 12.3.1
NVCC 12.4.1
NVCC 12.5.1
NVCC 12.6.1
NVCC 12.6.2
NVCC 9.1.85
NVCC 9.2.88
NVRTC 11.0.2
NVRTC 11.0.3
NVRTC 11.1.0
NVRTC 11.1.1
NVRTC 11.2.0
NVRTC 11.2.1
NVRTC 11.2.2
NVRTC 11.3.0
NVRTC 11.3.1
NVRTC 11.4.0
NVRTC 11.4.1
NVRTC 11.5.0
NVRTC 11.5.1
NVRTC 11.5.2
NVRTC 11.6.0
NVRTC 11.6.1
NVRTC 11.6.2
NVRTC 11.7.0
NVRTC 11.7.1
NVRTC 11.8.0
NVRTC 12.0.0
NVRTC 12.0.1
NVRTC 12.1.0
clang 7.0.0 sm_70 CUDA-9.1
clang 8.0.0 sm_75 CUDA-10.0
clang 9.0.0 sm_75 CUDA-10.1
clang rocm-4.5.2
clang rocm-5.0.2
clang rocm-5.1.3
clang rocm-5.2.3
clang rocm-5.3.2
clang rocm-5.7.0
clang rocm-6.0.2
clang rocm-6.1.2
clang staging rocm-6.1.2
clang trunk rocm-6.1.2
trunk sm_90 CUDA-12.6.1
Options
Source code
#include <assert.h> #include <cstdint> #if __clang__ extern "C" { __device__ inline size_t __nv_cvta_generic_to_global_impl(const void *__ptr) { return (size_t)(void __attribute__((address_space(1))) *)__ptr; } __device__ inline size_t __nv_cvta_generic_to_shared_impl(const void *__ptr) { return (size_t)(void __attribute__((address_space(3))) *)__ptr; } __device__ inline size_t __nv_cvta_generic_to_constant_impl(const void *__ptr) { return (size_t)(void __attribute__((address_space(4))) *)__ptr; } __device__ inline size_t __nv_cvta_generic_to_local_impl(const void *__ptr) { return (size_t)(void __attribute__((address_space(5))) *)__ptr; } __device__ inline void *__nv_cvta_global_to_generic_impl(size_t __ptr) { return (void *)(void __attribute__((address_space(1))) *)__ptr; } __device__ inline void *__nv_cvta_shared_to_generic_impl(size_t __ptr) { return (void *)(void __attribute__((address_space(3))) *)__ptr; } __device__ inline void *__nv_cvta_constant_to_generic_impl(size_t __ptr) { return (void *)(void __attribute__((address_space(4))) *)__ptr; } __device__ inline void *__nv_cvta_local_to_generic_impl(size_t __ptr) { return (void *)(void __attribute__((address_space(5))) *)__ptr; } __device__ inline uint32_t __nvvm_get_smem_pointer(void *__ptr) { return __nv_cvta_generic_to_shared_impl(__ptr); } } // extern "C" #else extern "C" __device__ uint32_t __nvvm_get_smem_pointer(void *); #endif __device__ int g; __global__ void kernel(int inner_idx, int outer_idx) { __shared__ int s[1024]; auto TypeV = &s[0]; ((decltype(TypeV))__cvta_generic_to_shared(&s[inner_idx]))[outer_idx] = 7; }
Become a Patron
Sponsor on GitHub
Donate via PayPal
Source on GitHub
Mailing list
Installed libraries
Wiki
Report an issue
How it works
Contact the author
CE on Mastodon
CE on Bluesky
About the author
Statistics
Changelog
Version tree