Hacker News
- Beating OpenAI CLIP with 100x less data and compute https://www.unum.cloud/blog/2023-02-20-efficient-multimodality 57 comments
- Unum Rocks: 10 TBs, 64 Cores and CUDA https://unum.cloud/post/2022-09-13-ucsb-10tb/ 2 comments
- UnumDB Crushing Benchmarks: YCSB, pt. 2 https://unum.cloud/post/2021-11-25-ycsb/ 2 comments
- Failing to reach DDR4 bandwidth https://unum.cloud/post/2022-01-29-ddr4/ 71 comments
- Server Hardware Super-Cycle 2022 https://unum.cloud/post/2021-12-07-supercycle/ 29 comments
- 2021 in Database Startups: Gold Rush https://unum.cloud/post/2021-12-31-dbms-startups/ 36 comments
- Apple to Apple Comparison: M1 Max vs. Intel https://unum.cloud/post/2021-12-21-macbook/ 214 comments
- [P] USearch HNSW implementation is 10x faster than FAISS at scale https://www.unum.cloud/blog/2023-11-07-scaling-vector-search-with-intel 4 comments machinelearning
- Benchmarking Pandas, CuDF, Modin, Apache Arrow and Spark on a Billion Taxi Rides dataset https://unum.cloud/post/2022-09-20-pandas/ 11 comments python
- C++ Benchmarking Tips for Beginners https://unum.cloud/post/2022-03-04-gbench/ 9 comments cpp
- Best CPU vs GPU: 879 GB/s Reductions in C++ https://unum.cloud/post/2022-01-27-accumulate/ 45 comments cpp
- Best CPU vs Best GPU: NumPy vs CuPy - Unum | Unifying CS and HPC for the future of AGI https://unum.cloud/post/2022-01-25-cupy/ 8 comments python
- Unum blog: Apple to Apple Comparison: M1 Max vs Intel. How a DDR5-powered MacBook beat a DDR4-powered MacBook and approached a $50K Server in Hash-Table Benchmarks https://unum.cloud/post/2021-12-21-macbook/ 66 comments apple
- Benchmarking Hash-Tables Speed on M1 Max MacBooks with DDR5, Intel MacBooks with DDR4 and a $50K AMD Server https://unum.cloud/post/2021-12-21-macbook/ 5 comments programming
- Benchmarking C++ Hash-Tables on M1 Max MacBooks with DDR5, Intel MacBooks with DDR4 and a $50K AMD Server https://unum.cloud/post/2021-12-21-macbook/ 25 comments cpp