Skip to content

Fix NumPy CI failures #86

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 17, 2023
Merged

Fix NumPy CI failures #86

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
62c0721
Avoid using _mm512_set_epi16: missing in gcc-8
Oct 16, 2023
48594f1
Convert to char* to comply with _mm_prefetch(char*, ..)
Oct 16, 2023
65e04b6
Use popcnt_u32
Oct 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
148 changes: 20 additions & 128 deletions src/avx512-16bit-common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,38 +99,11 @@ struct avx512_16bit_swizzle_ops {
__m512i v = vtype::cast_to(reg);

if constexpr (scale == 2) {
__m512i mask = _mm512_set_epi16(30,
31,
28,
29,
26,
27,
24,
25,
22,
23,
20,
21,
18,
19,
16,
17,
14,
15,
12,
13,
10,
11,
8,
9,
6,
7,
4,
5,
2,
3,
0,
1);
std::vector<uint16_t> arr
= {1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11,
10, 13, 12, 15, 14, 17, 16, 19, 18, 21, 20,
23, 22, 25, 24, 27, 26, 29, 28, 31, 30};
__m512i mask = _mm512_loadu_si512(arr.data());
v = _mm512_permutexvar_epi16(mask, v);
}
else if constexpr (scale == 4) {
Expand Down Expand Up @@ -160,108 +133,27 @@ struct avx512_16bit_swizzle_ops {

if constexpr (scale == 2) { return swap_n<vtype, 2>(reg); }
else if constexpr (scale == 4) {
__m512i mask = _mm512_set_epi16(28,
29,
30,
31,
24,
25,
26,
27,
20,
21,
22,
23,
16,
17,
18,
19,
12,
13,
14,
15,
8,
9,
10,
11,
4,
5,
6,
7,
0,
1,
2,
3);
std::vector<uint16_t> arr
= {3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9,
8, 15, 14, 13, 12, 19, 18, 17, 16, 23, 22,
21, 20, 27, 26, 25, 24, 31, 30, 29, 28};
__m512i mask = _mm512_loadu_si512(arr.data());
v = _mm512_permutexvar_epi16(mask, v);
}
else if constexpr (scale == 8) {
__m512i mask = _mm512_set_epi16(24,
25,
26,
27,
28,
29,
30,
31,
16,
17,
18,
19,
20,
21,
22,
23,
8,
9,
10,
11,
12,
13,
14,
15,
0,
1,
2,
3,
4,
5,
6,
7);
std::vector<uint16_t> arr
= {7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13,
12, 11, 10, 9, 8, 23, 22, 21, 20, 19, 18,
17, 16, 31, 30, 29, 28, 27, 26, 25, 24};
__m512i mask = _mm512_loadu_si512(arr.data());
v = _mm512_permutexvar_epi16(mask, v);
}
else if constexpr (scale == 16) {
__m512i mask = _mm512_set_epi16(16,
17,
18,
19,
20,
21,
22,
23,
24,
25,
26,
27,
28,
29,
30,
31,
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15);
std::vector<uint16_t> arr
= {15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5,
4, 3, 2, 1, 0, 31, 30, 29, 28, 27, 26,
25, 24, 23, 22, 21, 20, 19, 18, 17, 16};
__m512i mask = _mm512_loadu_si512(arr.data());
v = _mm512_permutexvar_epi16(mask, v);
}
else if constexpr (scale == 32) {
Expand Down
11 changes: 6 additions & 5 deletions src/avx512-common-qsort.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
#include <cstring>
#include <immintrin.h>
#include <limits>
#include <vector>

#define X86_SIMD_SORT_INFINITY std::numeric_limits<double>::infinity()
#define X86_SIMD_SORT_INFINITYF std::numeric_limits<float>::infinity()
Expand Down Expand Up @@ -249,7 +250,7 @@ X86_SIMD_SORT_INLINE arrsize_t partition_vec(type_t *l_store,
reg_t &biggest_vec)
{
typename vtype::opmask_t ge_mask = vtype::ge(curr_vec, pivot_vec);
arrsize_t amount_ge_pivot = _mm_popcnt_u64(ge_mask);
int amount_ge_pivot = _mm_popcnt_u32((int)ge_mask);

vtype::mask_compressstoreu(l_store, vtype::knot_opmask(ge_mask), curr_vec);
vtype::mask_compressstoreu(
Expand Down Expand Up @@ -450,17 +451,17 @@ X86_SIMD_SORT_INLINE arrsize_t partition_avx512_unrolled(type_t *arr,
X86_SIMD_SORT_UNROLL_LOOP(8)
for (int ii = 0; ii < num_unroll; ++ii) {
curr_vec[ii] = vtype::loadu(arr + right + ii * vtype::numlanes);
_mm_prefetch(arr + right + ii * vtype::numlanes
- num_unroll * vtype::numlanes,
_mm_prefetch((char *)(arr + right + ii * vtype::numlanes
- num_unroll * vtype::numlanes),
_MM_HINT_T0);
}
}
else {
X86_SIMD_SORT_UNROLL_LOOP(8)
for (int ii = 0; ii < num_unroll; ++ii) {
curr_vec[ii] = vtype::loadu(arr + left + ii * vtype::numlanes);
_mm_prefetch(arr + left + ii * vtype::numlanes
+ num_unroll * vtype::numlanes,
_mm_prefetch((char *)(arr + left + ii * vtype::numlanes
+ num_unroll * vtype::numlanes),
_MM_HINT_T0);
}
left += num_unroll * vtype::numlanes;
Expand Down