Skip to content

Commit 66198ab

Browse files
sayantnAmanieu
authored andcommitted
AVX512DQ Part 2: Broadcast, Extract, Insert
1 parent bbe9e51 commit 66198ab

File tree

2 files changed

+1981
-252
lines changed

2 files changed

+1981
-252
lines changed

crates/core_arch/avx512dq.md

Lines changed: 71 additions & 69 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
<summary>["AVX512DQ"]</summary><p>
22

3+
[Intel's List](https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#avx512techs=AVX512DQ)
4+
35
- And:
46
* [x] _mm_mask_and_pd
57
* [x] _mm_maskz_and_pd
@@ -69,39 +71,39 @@
6971

7072

7173
- Broadcast
72-
* [ ] _mm256_broadcast_f32x2
73-
* [ ] _mm256_mask_broadcast_f32x2
74-
* [ ] _mm256_maskz_broadcast_f32x2
75-
* [ ] _mm512_broadcast_f32x2
76-
* [ ] _mm512_mask_broadcast_f32x2
77-
* [ ] _mm512_maskz_broadcast_f32x2
78-
* [ ] _mm512_broadcast_f32x8
79-
* [ ] _mm512_mask_broadcast_f32x8
80-
* [ ] _mm512_maskz_broadcast_f32x8
81-
* [ ] _mm256_broadcast_f64x2
82-
* [ ] _mm256_mask_broadcast_f64x2
83-
* [ ] _mm256_maskz_broadcast_f64x2
84-
* [ ] _mm512_broadcast_f64x2
85-
* [ ] _mm512_mask_broadcast_f64x2
86-
* [ ] _mm512_maskz_broadcast_f64x2
87-
* [ ] _mm_broadcast_i32x2
88-
* [ ] _mm_mask_broadcast_i32x2
89-
* [ ] _mm_maskz_broadcast_i32x2
90-
* [ ] _mm256_broadcast_i32x2
91-
* [ ] _mm256_mask_broadcast_i32x2
92-
* [ ] _mm256_maskz_broadcast_i32x2
93-
* [ ] _mm512_broadcast_i32x2
94-
* [ ] _mm512_mask_broadcast_i32x2
95-
* [ ] _mm512_maskz_broadcast_i32x2
96-
* [ ] _mm512_broadcast_i32x8
97-
* [ ] _mm512_mask_broadcast_i32x8
98-
* [ ] _mm512_maskz_broadcast_i32x8
99-
* [ ] _mm256_broadcast_i64x2
100-
* [ ] _mm256_mask_broadcast_i64x2
101-
* [ ] _mm256_maskz_broadcast_i64x2
102-
* [ ] _mm512_broadcast_i64x2
103-
* [ ] _mm512_mask_broadcast_i64x2
104-
* [ ] _mm512_maskz_broadcast_i64x2
74+
* [x] _mm256_broadcast_f32x2
75+
* [x] _mm256_mask_broadcast_f32x2
76+
* [x] _mm256_maskz_broadcast_f32x2
77+
* [x] _mm512_broadcast_f32x2
78+
* [x] _mm512_mask_broadcast_f32x2
79+
* [x] _mm512_maskz_broadcast_f32x2
80+
* [x] _mm512_broadcast_f32x8
81+
* [x] _mm512_mask_broadcast_f32x8
82+
* [x] _mm512_maskz_broadcast_f32x8
83+
* [x] _mm256_broadcast_f64x2
84+
* [x] _mm256_mask_broadcast_f64x2
85+
* [x] _mm256_maskz_broadcast_f64x2
86+
* [x] _mm512_broadcast_f64x2
87+
* [x] _mm512_mask_broadcast_f64x2
88+
* [x] _mm512_maskz_broadcast_f64x2
89+
* [x] _mm_broadcast_i32x2
90+
* [x] _mm_mask_broadcast_i32x2
91+
* [x] _mm_maskz_broadcast_i32x2
92+
* [x] _mm256_broadcast_i32x2
93+
* [x] _mm256_mask_broadcast_i32x2
94+
* [x] _mm256_maskz_broadcast_i32x2
95+
* [x] _mm512_broadcast_i32x2
96+
* [x] _mm512_mask_broadcast_i32x2
97+
* [x] _mm512_maskz_broadcast_i32x2
98+
* [x] _mm512_broadcast_i32x8
99+
* [x] _mm512_mask_broadcast_i32x8
100+
* [x] _mm512_maskz_broadcast_i32x8
101+
* [x] _mm256_broadcast_i64x2
102+
* [x] _mm256_mask_broadcast_i64x2
103+
* [x] _mm256_maskz_broadcast_i64x2
104+
* [x] _mm512_broadcast_i64x2
105+
* [x] _mm512_mask_broadcast_i64x2
106+
* [x] _mm512_maskz_broadcast_i64x2
105107

106108

107109
- Convert:
@@ -252,45 +254,45 @@
252254

253255

254256
- Element Extract:
255-
* [ ] _mm512_extractf32x8_ps
256-
* [ ] _mm512_mask_extractf32x8_ps
257-
* [ ] _mm512_maskz_extractf32x8_ps
258-
* [ ] _mm256_extractf64x2_pd
259-
* [ ] _mm256_mask_extractf64x2_pd
260-
* [ ] _mm256_maskz_extractf64x2_pd
261-
* [ ] _mm512_extractf64x2_pd
262-
* [ ] _mm512_mask_extractf64x2_pd
263-
* [ ] _mm512_maskz_extractf64x2_pd
264-
* [ ] _mm512_extracti32x8_epi32
265-
* [ ] _mm512_mask_extracti32x8_epi32
266-
* [ ] _mm512_maskz_extracti32x8_epi32
267-
* [ ] _mm256_extracti64x2_epi64
268-
* [ ] _mm256_mask_extracti64x2_epi64
269-
* [ ] _mm256_maskz_extracti64x2_epi64
270-
* [ ] _mm512_extracti64x2_epi64
271-
* [ ] _mm512_mask_extracti64x2_epi64
272-
* [ ] _mm512_maskz_extracti64x2_epi64
257+
* [x] _mm512_extractf32x8_ps
258+
* [x] _mm512_mask_extractf32x8_ps
259+
* [x] _mm512_maskz_extractf32x8_ps
260+
* [x] _mm256_extractf64x2_pd
261+
* [x] _mm256_mask_extractf64x2_pd
262+
* [x] _mm256_maskz_extractf64x2_pd
263+
* [x] _mm512_extractf64x2_pd
264+
* [x] _mm512_mask_extractf64x2_pd
265+
* [x] _mm512_maskz_extractf64x2_pd
266+
* [x] _mm512_extracti32x8_epi32
267+
* [x] _mm512_mask_extracti32x8_epi32
268+
* [x] _mm512_maskz_extracti32x8_epi32
269+
* [x] _mm256_extracti64x2_epi64
270+
* [x] _mm256_mask_extracti64x2_epi64
271+
* [x] _mm256_maskz_extracti64x2_epi64
272+
* [x] _mm512_extracti64x2_epi64
273+
* [x] _mm512_mask_extracti64x2_epi64
274+
* [x] _mm512_maskz_extracti64x2_epi64
273275

274276

275277
- Element Insert:
276-
* [ ] _mm512_insertf32x8
277-
* [ ] _mm512_mask_insertf32x8
278-
* [ ] _mm512_maskz_insertf32x8
279-
* [ ] _mm256_insertf64x2
280-
* [ ] _mm256_mask_insertf64x2
281-
* [ ] _mm256_maskz_insertf64x2
282-
* [ ] _mm512_insertf64x2
283-
* [ ] _mm512_mask_insertf64x2
284-
* [ ] _mm512_maskz_insertf64x2
285-
* [ ] _mm512_inserti32x8
286-
* [ ] _mm512_mask_inserti32x8
287-
* [ ] _mm512_maskz_inserti32x8
288-
* [ ] _mm256_inserti64x2
289-
* [ ] _mm256_mask_inserti64x2
290-
* [ ] _mm256_maskz_inserti64x2
291-
* [ ] _mm512_inserti64x2
292-
* [ ] _mm512_mask_inserti64x2
293-
* [ ] _mm512_maskz_inserti64x2
278+
* [x] _mm512_insertf32x8
279+
* [x] _mm512_mask_insertf32x8
280+
* [x] _mm512_maskz_insertf32x8
281+
* [x] _mm256_insertf64x2
282+
* [x] _mm256_mask_insertf64x2
283+
* [x] _mm256_maskz_insertf64x2
284+
* [x] _mm512_insertf64x2
285+
* [x] _mm512_mask_insertf64x2
286+
* [x] _mm512_maskz_insertf64x2
287+
* [x] _mm512_inserti32x8
288+
* [x] _mm512_mask_inserti32x8
289+
* [x] _mm512_maskz_inserti32x8
290+
* [x] _mm256_inserti64x2
291+
* [x] _mm256_mask_inserti64x2
292+
* [x] _mm256_maskz_inserti64x2
293+
* [x] _mm512_inserti64x2
294+
* [x] _mm512_mask_inserti64x2
295+
* [x] _mm512_maskz_inserti64x2
294296

295297

296298
- FP-Class

0 commit comments

Comments
 (0)