TechQA.

Question

Clamp unsigned int to 0x10000 using SSE2

score 278 · Answer 1 · 2024-02-02T17:46:47.663000

0

Answer

278

Views

Clamp unsigned int to 0x10000 using SSE2

278 views Asked by Sanyin At 02 February 2024 at 17:46

score 170 · Answer 2 · 2023-10-24T13:43:02.090000

How to add an alpha channel very fast to a RGB image using SSE2 and c++

170 views Asked by bluetooth16 At 24 October 2023 at 13:43

score 117 · Answer 3 · 2023-09-04T11:46:20.447000

Suggestions on further optimising this chi-square function using SSE2 intrinsics

117 views Asked by Sanku At 04 September 2023 at 11:46

score 121 · Answer 4 · 2023-08-03T14:07:46.157000

Matrix multiplication using simd produces incorrect results when filled with floating point values

121 views Asked by Arheus At 03 August 2023 at 14:07

score 94 · Answer 5 · 2023-06-08T22:36:52.790000

Sum of bytes in an __m128 register

94 views Asked by user17784058 At 08 June 2023 at 22:36

score 279 · Answer 6 · 2023-02-15T10:58:37.470000

Why isn't Avx.Multiply significantly faster than the * operator?

279 views Asked by André Reichelt At 15 February 2023 at 10:58

score 418 · Answer 7 · 2022-12-17T04:24:44.633000

In SIMD, SSE2，many instructions named as "_mm_set_epi8"，"_mm_cmpgt_epi8 " and so on，what does "mm" "epi" mean?

418 views Asked by dongwang At 17 December 2022 at 04:24

score 815 · Answer 8 · 2022-11-08T12:20:38.980000

MOVDQU vs MOVDQA Instruction (x86/x64 assembly) better insights

815 views Asked by RajibTheKing At 08 November 2022 at 12:20

score 400 · Answer 9 · 2022-11-08T06:26:59.540000

Efficiently find indices of 1-bits in large array, using SIMD

400 views Asked by Arty At 08 November 2022 at 06:26

score 97 · Answer 10 · 2022-11-07T19:27:55.860000

C++ std::countr_zero() in SIMD 128/256/512 (find position of least significant 1 bit in 128/256/512-bit number)

97 views Asked by Arty At 07 November 2022 at 19:27

score 552 · Answer 11 · 2022-10-22T20:04:10.110000

Having array of 16/32/64 bytes how to quickly find index of first byte equal to given, using SSE2/AVX/AVX2/AVX-512

552 views Asked by Arty At 22 October 2022 at 20:04

score 430 · Answer 12 · 2022-10-13T04:04:54.657000

How can I implement Bit Shift Right and Bit Shift Left by Vector for 8-bit and 16-bit integers in SSE2?

430 views Asked by dave_thenerd At 13 October 2022 at 04:04

score 318 · Answer 13 · 2022-07-23T14:37:42.500000

Access value from __m128 in rust by index

318 views Asked by Marc At 23 July 2022 at 14:37

score 114 · Answer 14 · 2022-06-25T06:57:43.047000

Why some of sse intrinsics introduce move back and forth?

114 views Asked by DoodleNoodle At 25 June 2022 at 06:57

score 454 · Answer 15 · 2022-04-30T22:46:12.617000

AVX divide __m256i packed 32-bit integers by two (no AVX2)

454 views Asked by GlassBeaver At 30 April 2022 at 22:46

score 39 · Answer 16 · 2022-03-08T02:01:06.267000

Does packed data type in SSE2 imply alignment?

39 views Asked by aahlback At 08 March 2022 at 02:01

score 1279 · Answer 17 · 2022-01-30T04:35:48.627000

What are the names and meanings of the intrinsic vector element types, like epi64x or pi32?

1.2k views Asked by Brotcrunsher At 30 January 2022 at 04:35

score 257 · Answer 18 · 2021-12-05T18:35:59.667000

Can FP compares like SSE2 _mm_cmpeq_pd be used to compare 64 bit integers?

257 views Asked by Alex Guteniev At 05 December 2021 at 18:35

score 626 · Answer 19 · 2021-09-28T00:51:04.067000

Is there a difference between SVML vs. normal intrinsic square root functions?

626 views Asked by dave_thenerd At 28 September 2021 at 00:51

score 635 · Answer 20 · 2021-08-26T13:35:42.320000

can I assign the result of intrinsic that returns m128i to variable of the typem128i_u?

635 views Asked by vela18 At 26 August 2021 at 13:35

TechQA.

List Question

Clamp unsigned int to 0x10000 using SSE2

How to add an alpha channel very fast to a RGB image using SSE2 and c++

Suggestions on further optimising this chi-square function using SSE2 intrinsics

Matrix multiplication using simd produces incorrect results when filled with floating point values

Sum of bytes in an __m128 register

Why isn't Avx.Multiply significantly faster than the * operator?

In SIMD, SSE2，many instructions named as "_mm_set_epi8"，"_mm_cmpgt_epi8 " and so on，what does "mm" "epi" mean?

MOVDQU vs MOVDQA Instruction (x86/x64 assembly) better insights

Efficiently find indices of 1-bits in large array, using SIMD

C++ std::countr_zero() in SIMD 128/256/512 (find position of least significant 1 bit in 128/256/512-bit number)

Having array of 16/32/64 bytes how to quickly find index of first byte equal to given, using SSE2/AVX/AVX2/AVX-512

How can I implement Bit Shift Right and Bit Shift Left by Vector for 8-bit and 16-bit integers in SSE2?

Access value from __m128 in rust by index

Why some of sse intrinsics introduce move back and forth?

AVX divide __m256i packed 32-bit integers by two (no AVX2)

Does packed data type in SSE2 imply alignment?

What are the names and meanings of the intrinsic vector element types, like epi64x or pi32?

Can FP compares like SSE2 _mm_cmpeq_pd be used to compare 64 bit integers?

Is there a difference between SVML vs. normal intrinsic square root functions?

can I assign the result of intrinsic that returns m128i to variable of the typem128i_u?

Popular Questions

Trending Questions