Filter1D example and memory aware replace #320
Conversation
Codecov Report
📣 This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more @@ Coverage Diff @@
## master #320 +/- ##
==========================================
+ Coverage 86.21% 86.61% +0.39%
==========================================
Files 73 75 +2
Lines 16625 16968 +343
==========================================
+ Hits 14333 14696 +363
+ Misses 2292 2272 -20
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
yamaguchi1024
force-pushed
the
filter1D
branch
from
71d206c
to
ceae539
Compare
yamaguchi1024
changed the title
| @@ -52,6 +60,17 @@ def mm256_broadcast_ss( | |||
| out[i] = val[0] | |||
|
|
|||
|
|
|||
| @instr("{dst_data} = _mm512_fmadd_ps({dst_data}, {lhs_data}, {rhs_data});") | |||
| def mm256_fmadd_ps_broadcast( | |||
| dst: [f32][8] @ AVX2, lhs: [f32][8] @ AVX2, rhs: [f32][1] @ DRAM | |||
There was a problem hiding this comment.
Why can't this just be rhs : f32 @ DRAM?
There was a problem hiding this comment.
I think we should extend the unification to be able to unify rhs : f32, rhs : f32[1], and rhs : [f32][1], but for now, having an argument as windows is more accommodating 😅
There was a problem hiding this comment.
I figured it was a limitation in unification... just wanted to make a note of it.
No description provided.