Hadamard transform improvement for hevc using intel avx-512
High Efficiency Video Coding (HEVC) doubles the data compression ratio compared to previous generation compression technology, Moving Picture Expert Group-Advanced Video Codec (MPEG-AVC/H.264) without sacrificing the image quality. However, this superior compression comes at the cost of more computa...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/90183/1/UsmanUllahSheikh2019_HadamardTransformImprovement.pdf |
| _version_ | 1796864977971183616 |
|---|---|
| author | Sing, J. T. K. Ullah Sheikh, U. Mokji, M. Alias, N. E. |
| author_facet | Sing, J. T. K. Ullah Sheikh, U. Mokji, M. Alias, N. E. |
| author_sort | Sing, J. T. K. |
| collection | ePrints |
| description | High Efficiency Video Coding (HEVC) doubles the data compression ratio compared to previous generation compression technology, Moving Picture Expert Group-Advanced Video Codec (MPEG-AVC/H.264) without sacrificing the image quality. However, this superior compression comes at the cost of more computation payload resulting in longer time for encoding and decoding. This work proposes the vectorization on HEVC data heavy computation algorithm, Hadamard Transform or Sum of Absolute Transform Difference (SATD) and Sum of Absolute Difference (SAD) to achieve optimized compression performance. Single Instruction Multiple Data (SIMD) acceleration will be based on the Intel AVX-512 (Advanced Vector Extension) Instruction Set Architecture (ISA). Since HEVC supports more coding tree block (CTB) sizes, SATD and SAD algorithms eventually become more complex compared to AVC. As a result, SATD and SAD algorithms with various block sizes will be subjected to SIMD acceleration. We provide performance evaluation based on different SIMD ISA and without SIMD implementation on HEVC SATD and SAD and found that AVX-512 optimized implementation performed faster when compared to non- optimized SATD and SAD but showed signs of reduced performance when compared to SSE optimized SATD and SAD. |
| first_indexed | 2024-03-05T20:50:00Z |
| format | Conference or Workshop Item |
| id | utm.eprints-90183 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T20:50:00Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | utm.eprints-901832021-03-30T07:48:04Z http://eprints.utm.my/90183/ Hadamard transform improvement for hevc using intel avx-512 Sing, J. T. K. Ullah Sheikh, U. Mokji, M. Alias, N. E. TK Electrical engineering. Electronics Nuclear engineering High Efficiency Video Coding (HEVC) doubles the data compression ratio compared to previous generation compression technology, Moving Picture Expert Group-Advanced Video Codec (MPEG-AVC/H.264) without sacrificing the image quality. However, this superior compression comes at the cost of more computation payload resulting in longer time for encoding and decoding. This work proposes the vectorization on HEVC data heavy computation algorithm, Hadamard Transform or Sum of Absolute Transform Difference (SATD) and Sum of Absolute Difference (SAD) to achieve optimized compression performance. Single Instruction Multiple Data (SIMD) acceleration will be based on the Intel AVX-512 (Advanced Vector Extension) Instruction Set Architecture (ISA). Since HEVC supports more coding tree block (CTB) sizes, SATD and SAD algorithms eventually become more complex compared to AVC. As a result, SATD and SAD algorithms with various block sizes will be subjected to SIMD acceleration. We provide performance evaluation based on different SIMD ISA and without SIMD implementation on HEVC SATD and SAD and found that AVX-512 optimized implementation performed faster when compared to non- optimized SATD and SAD but showed signs of reduced performance when compared to SSE optimized SATD and SAD. 2019 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utm.my/90183/1/UsmanUllahSheikh2019_HadamardTransformImprovement.pdf Sing, J. T. K. and Ullah Sheikh, U. and Mokji, M. and Alias, N. E. (2019) Hadamard transform improvement for hevc using intel avx-512. In: 9th IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2019, 27-28 Apr 2019, Kota Kinabalu, Malaysia. http://dx.doi.org/10.1109/ISCAIE.2019.8743904 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Sing, J. T. K. Ullah Sheikh, U. Mokji, M. Alias, N. E. Hadamard transform improvement for hevc using intel avx-512 |
| title | Hadamard transform improvement for hevc using intel avx-512 |
| title_full | Hadamard transform improvement for hevc using intel avx-512 |
| title_fullStr | Hadamard transform improvement for hevc using intel avx-512 |
| title_full_unstemmed | Hadamard transform improvement for hevc using intel avx-512 |
| title_short | Hadamard transform improvement for hevc using intel avx-512 |
| title_sort | hadamard transform improvement for hevc using intel avx 512 |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.utm.my/90183/1/UsmanUllahSheikh2019_HadamardTransformImprovement.pdf |
| work_keys_str_mv | AT singjtk hadamardtransformimprovementforhevcusingintelavx512 AT ullahsheikhu hadamardtransformimprovementforhevcusingintelavx512 AT mokjim hadamardtransformimprovementforhevcusingintelavx512 AT aliasne hadamardtransformimprovementforhevcusingintelavx512 |