You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: crates/cust/CHANGELOG.md
+4-3Lines changed: 4 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -74,9 +74,9 @@ Instead you can now use `DeviceSlice::index` which behaves the same.
74
74
- Added `ModuleJitOption`, `JitFallback`, `JitTarget`, and `OptLevel` for specifying options when loading a module. Note that
75
75
`ModuleJitOption::MaxRegisters` does not seem to work currently, but NVIDIA is looking into it.
76
76
You can achieve the same goal by compiling the ptx to cubin using nvcc then loading that: `nvcc --cubin foo.ptx -maxrregcount=REGS`
77
-
- Added `Module::from_fatbin` and `Module::from_fatbin_unchecked`.
78
-
- Added `Module::from_cubin` and `Module::from_cubin_unchecked`.
79
-
- Added `Module::from_ptr` and `Module::from_ptx_cstr`.
77
+
- Added `Module::from_fatbin`.
78
+
- Added `Module::from_cubin`.
79
+
- Added `Module::from_ptx` and `Module::from_ptx_cstr`.
80
80
-`Stream`, `Module`, `Linker`, `Function`, `Event`, `UnifiedBox`, `ArrayObject`, `LockedBuffer`, `LockedBox`, `DeviceSlice`, `DeviceBuffer`, and `DeviceBox` all now impl `Send` and `Sync`, this makes
81
81
it much easier to write multigpu code. The CUDA API is fully thread-safe except for graph objects.
82
82
@@ -98,6 +98,7 @@ it much easier to write multigpu code. The CUDA API is fully thread-safe except
98
98
-`DeviceSlice::as_ptr` and `DeviceSlice::as_ptr_mut` now both return a `DevicePointer<T>`.
99
99
-`DeviceSlice` is now `Clone` and `Copy`.
100
100
-`DevicePointer::as_raw` now returns a `CUdeviceptr`, not a `*const T` (use `DevicePointer::as_ptr`).
101
+
- Fixed typo in `CudaError`, `InvalidSouce` is now `InvalidSource`, no more invalid sauce 🍅🥣
0 commit comments