* correct typo (cherry picked from commit1507477306
) * fix another typo (cherry picked from commit269028360c
) Co-authored-by: Yang Li <yangli1990@live.com.au>
This commit is contained in:
@@ -94,7 +94,7 @@ attempts to use a float operation that is not supported, the runtime will report
|
|||||||
an unresolved symbol error.
|
an unresolved symbol error.
|
||||||
|
|
||||||
Float operations are performed via software libraries, specifically LLVM's float
|
Float operations are performed via software libraries, specifically LLVM's float
|
||||||
builtins. Due to be software emulated they consume more compute units than
|
builtins. Due to the software emulated they consume more compute units than
|
||||||
integer operations. In general, fixed point operations are recommended where
|
integer operations. In general, fixed point operations are recommended where
|
||||||
possible.
|
possible.
|
||||||
|
|
||||||
@@ -108,7 +108,7 @@ To run the test, sync the repo, and run:
|
|||||||
|
|
||||||
Recent results show the float operations take more instructions compared to
|
Recent results show the float operations take more instructions compared to
|
||||||
integers equivalents. Fixed point implementations may vary but will also be
|
integers equivalents. Fixed point implementations may vary but will also be
|
||||||
less then the float equivalents:
|
less than the float equivalents:
|
||||||
|
|
||||||
```
|
```
|
||||||
u64 f32
|
u64 f32
|
||||||
|
Reference in New Issue
Block a user