Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
SWIFTsim
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Deploy
Releases
Model registry
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
SWIFT
SWIFTsim
Commits
1b5cf348
Commit
1b5cf348
authored
8 years ago
by
James Willis
Browse files
Options
Downloads
Patches
Plain Diff
Fixed bugs in AVX-512 instructions.
Conflicts: src/vector.h
parent
a239328b
Branches
Branches containing commit
Tags
Tags containing commit
1 merge request
!396
Avx512 fixes
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
src/vector.h
+7
-4
7 additions, 4 deletions
src/vector.h
with
7 additions
and
4 deletions
src/vector.h
+
7
−
4
View file @
1b5cf348
...
...
@@ -116,10 +116,13 @@
for (int i = 0; i < VEC_SIZE; i++) b += a.f[i]; \
}
#endif
/* Calculates the number of set bits in the mask and adds the result to an int.
*/
#define VEC_FORM_PACKED_MASK(mask, v_mask, pack) \
pack += __builtin_popcount(mask);
/* Do nothing in the case of AVX-512 as there are already
* instructions for left-packing.*/
#define VEC_FORM_PACKED_MASK(mask, packed_mask) packed_mask = mask
/* Finds the horizontal maximum of vector b and returns a float. */
#define VEC_HMAX(a, b) b = _mm512_reduce_max_ps(a.v)
/* Performs a left-pack on a vector based upon a mask and returns the result. */
#define VEC_LEFT_PACK(a, mask, result) \
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment