Add support for i64 (#563)

* Add the i64 dtype.

* Adapt the cuda kernels.
This commit is contained in:
Laurent Mazare
2023-08-23 10:42:19 +01:00
committed by GitHub
parent 3743bed2d7
commit 9a5c7db91a
16 changed files with 313 additions and 36 deletions

View File

@ -142,6 +142,8 @@ __device__ __forceinline__ double absg(double a) { return fabs(a); }
__device__ __forceinline__ float copysigng(float a, float b) { return copysignf(a, b); }
__device__ __forceinline__ double copysigng(double a, double b) { return copysign(a, b); }
__device__ __forceinline__ int64_t ming(int64_t a, int64_t b) { return min(a, b); }
__device__ __forceinline__ int64_t maxg(int64_t a, int64_t b) { return max(a, b); }
__device__ __forceinline__ uint32_t ming(uint32_t a, uint32_t b) { return min(a, b); }
__device__ __forceinline__ uint32_t maxg(uint32_t a, uint32_t b) { return max(a, b); }
__device__ __forceinline__ uint8_t ming(uint8_t a, uint8_t b) { return min(a, b); }