• Joined on 2023-09-27
Daniel pushed to 1-performance-256-blocksize at Daniel/master-thesis 2025-04-12 10:27:09 +02:00
Daniel created branch 2-performance-inbounds in Daniel/master-thesis 2025-04-12 10:26:40 +02:00
Daniel pushed to 2-performance-inbounds at Daniel/master-thesis 2025-04-12 10:26:40 +02:00
Daniel pushed to main at Daniel/master-thesis 2025-04-12 10:25:09 +02:00
9746db56c0 benchmarking: added tests for performance tuning with Nsight compute and systems
Daniel pushed to main at Daniel/master-thesis 2025-04-10 11:18:06 +02:00
5a9760d221 concept and design: minor improvements
Daniel pushed to main at Daniel/master-thesis 2025-04-10 10:21:18 +02:00
c68e0d04a0 concept and design: improved wording and added overview diagram of kernel usage
Daniel pushed to main at Daniel/master-thesis 2025-04-06 14:29:20 +02:00
258d33c338 benchmarking: redid inbounds tests because first test run did not use inbounds everywhere
Daniel pushed to main at Daniel/master-thesis 2025-04-06 13:59:28 +02:00
20fcbab4ca concept and design: added transpiler section
Daniel pushed to main at Daniel/master-thesis 2025-04-05 12:56:16 +02:00
9e1094ac43 benchmarking: added reminder to redo one of the performance tests
Daniel pushed to main at Daniel/master-thesis 2025-04-05 12:54:43 +02:00
2a8de064a6 concept & design: improved existing sections
Daniel pushed to main at Daniel/master-thesis 2025-04-04 14:19:08 +02:00
8afc3a5e3b concept and design: continued with architecture
Daniel pushed to main at Daniel/master-thesis 2025-04-03 13:43:42 +02:00
d8f5454e9c concept and design: started writing this chapter
Daniel pushed to main at Daniel/master-thesis 2025-04-01 21:49:14 +02:00
2b9c394f1b benchmarking: improved performance with @inbounds. still slower in most cases
Daniel pushed to initial-implementation at Daniel/master-thesis 2025-03-30 13:57:23 +02:00
Daniel created branch initial-implementation in Daniel/master-thesis 2025-03-30 13:57:23 +02:00
Daniel pushed to main at Daniel/master-thesis 2025-03-30 13:56:34 +02:00
d9c83caad9 benchmarking: updated blocksize to 256 with moderate improvements
Daniel pushed to main at Daniel/master-thesis 2025-03-30 12:54:59 +02:00
1dc0c1898d benchmarking: fixed bugs; took initial_benchmark
Daniel pushed to main at Daniel/master-thesis 2025-03-29 13:36:09 +01:00
ad175abac0 benchmarking: added gpu evaluators to performance testing. getting execution errors still
Daniel pushed to main at Daniel/master-thesis 2025-03-29 12:01:16 +01:00
690ee33db1 benchmarks: started preparing benchmarks
Daniel opened issue Daniel/master-thesis#13 2025-03-29 09:23:48 +01:00
ExpressionProcessing & GPU Evaluators: Add support for powabs(EXPR)