Searched refs:gpuAtomicAdd (Results 1 – 4 of 4) sorted by relevance
| /external/pytorch/aten/src/ATen/cuda/ |
| D | Atomic.cuh | 174 inline __device__ void gpuAtomicAdd(uint8_t *address, uint8_t val) { in gpuAtomicAdd() function
182 inline __device__ void gpuAtomicAdd(int8_t *address, int8_t val) { in gpuAtomicAdd() function
190 inline __device__ void gpuAtomicAdd(int16_t *address, int16_t val) { in gpuAtomicAdd() function
198 inline __device__ int32_t gpuAtomicAdd(int32_t *address, int32_t val) { in gpuAtomicAdd() function
202 inline __device__ void gpuAtomicAdd(int64_t *address, int64_t val) { in gpuAtomicAdd() function
211 inline __device__ at::Half gpuAtomicAdd(at::Half *address, at::Half val) { in gpuAtomicAdd() function
222 inline __device__ at::BFloat16 gpuAtomicAdd(at::BFloat16 *address, at::BFloat16 val) { in gpuAtomicAdd() function
268 inline __device__ double gpuAtomicAdd(double *address, double val) { in gpuAtomicAdd() function
272 inline __device__ float gpuAtomicAdd(float *address, float val) { in gpuAtomicAdd() function
277 inline __device__ void gpuAtomicAdd(c10::complex<T> *address, c10::complex<T> val) { in gpuAtomicAdd() function
[all …]
|
| /external/pytorch/aten/src/ATen/native/cuda/ |
| D | NLLLoss2d.cu | 122 gpuAtomicAdd(total_weight, static_cast<scalar_t>(acc_weight_)); in C10_LAUNCH_BOUNDS_1()
123 gpuAtomicAdd(output, static_cast<scalar_t>(input_sum_)); in C10_LAUNCH_BOUNDS_1()
|
| /external/pytorch/aten/src/ATen/test/ |
| D | cuda_atomic_ops_test.cu | 18 gpuAtomicAdd(&sum[idx], a[idx]); in addition_test_kernel()
|
| /external/pytorch/docs/cpp/source/notes/ |
| D | tensor_basics.rst | 82 gpuAtomicAdd(trace, foo[i][i]);
|