Commits · 47480a59bcca88743550d40cf3a76015b5a251b3 · one / TransferBench

09 Jan, 2024 1 commit
- v1.47 Fixing CUDA compilation (#83) · 47480a59
  gilbertlee-amd authored Jan 09, 2024
  
  47480a59
14 Dec, 2023 1 commit
- v1.46 Fixing GFX_UNROLL for gfx906, enabling GFX_SINGLE_TEAM by default (#80) · d5445b95
  gilbertlee-amd authored Dec 13, 2023
  
  d5445b95
05 Dec, 2023 1 commit
- V1.45 candidate (#78) · f33c7fd9
  gilbertlee-amd authored Dec 04, 2023
```
* v1.45 New GFX kernel
```
  f33c7fd9
01 Dec, 2023 1 commit
- v1.44 Adding rwrite preset benchmark (#77) · 33a5435c
  gilbertlee-amd authored Dec 01, 2023
  
  33a5435c
30 Nov, 2023 4 commits
- v1.43 Minor changes to a2a output (#76) · 30f1c584
  gilbertlee-amd authored Nov 30, 2023
  
  30f1c584
- v1.42 Fixing schmoo optional arg, cleaning up schmoo output (#74) · 8b2cd85d
  gilbertlee-amd authored Nov 30, 2023
  
  8b2cd85d
- v1.41 Adding schmoo benchmark, fixing timing reports for variable-iteration modes (#73) · f5e9cf34
  gilbertlee-amd authored Nov 29, 2023
```
* v1.41 Adding schmoo benchmark, fixing timing reports for variable-iteration modes
```
  f5e9cf34
- v1.40 Fixing USE_XCC_FILTER for preset configurations (#72) · 437b6e70
  gilbertlee-amd authored Nov 29, 2023
  
  437b6e70
29 Nov, 2023 1 commit
- v1.39 Removing deprecated gcnArch. Adding experimental executor subindex support (#71) · 7a1dbd6a
  gilbertlee-amd authored Nov 29, 2023
  
  7a1dbd6a
28 Nov, 2023 1 commit
- v1.38 Adding missing __threadfence_system() (#70) · c5197729
  gilbertlee-amd authored Nov 28, 2023
  
  c5197729
24 Nov, 2023 2 commits
- v1.37 Fixing token error, enabling single-stream mode by default (#68) · 9e3a04c3
  gilbertlee-amd authored Nov 24, 2023
  
  9e3a04c3
- v1.36 - Adding experimental USE_XCC_FILTER (#67) · 08997e88
  gilbertlee-amd authored Nov 23, 2023
  
  08997e88
22 Nov, 2023 1 commit
- v1.35 - Adding USE_FINE_GRAIN to a2a preset (#66) · e047656f
  gilbertlee-amd authored Nov 22, 2023
  
  e047656f
07 Nov, 2023 1 commit
- Setting default GPU_KERNEL=3 for gfx942 (#64) · 004710fb
  gilbertlee-amd authored Nov 07, 2023
  
  004710fb
02 Nov, 2023 2 commits
- Update CHANGELOG.md · 70aff133
  Lisa authored Nov 02, 2023
```
Co-authored-by: Saad Rahim (AMD) <44449863+saadrahim@users.noreply.github.com>
```
  70aff133
- changelog updates · 80db71fc
  Lisa Delaney authored Nov 02, 2023
  
  80db71fc
30 Oct, 2023 1 commit
- Adding ALWAYS_VALIDATE to allow per-iteration validation (#61) · 1d34a197
  gilbertlee-amd authored Oct 30, 2023
  
  1d34a197
19 Oct, 2023 1 commit
- v1.32 - Increasing line limit from 2048 to 32768 (#60) · 9c2ecae2
  gilbertlee-amd authored Oct 19, 2023
  
  9c2ecae2
17 Oct, 2023 1 commit
- V1.31 candidate (#58) · 79a3a003
  gilbertlee-amd authored Oct 17, 2023
```
* Adding xccID output to SHOW_ITERATIONS
```
  79a3a003
13 Oct, 2023 1 commit
- Adding BLOCK_SIZE and BLOCK_ORDER (#57) · e7cfab75
  gilbertlee-amd authored Oct 13, 2023
  
  e7cfab75
11 Oct, 2023 1 commit
- Fix inf, CU labelling. Update default kernels for gfx94x (#56) · 0b29707e
  gilbertlee-amd authored Oct 11, 2023
  
  0b29707e
28 Sep, 2023 1 commit
- Minor changes to p2p, a2a (#55) · 0b7b979e
  gilbertlee-amd authored Sep 28, 2023
  
  0b7b979e
19 Sep, 2023 1 commit
- v1.27 CU Masking, cmdline preset, CUDA fixes (#53) · 3d284dd7
  gilbertlee-amd authored Sep 19, 2023
  
  3d284dd7
14 Aug, 2023 1 commit
- Adding SHOW_ITERATIONS to provide additional per-iteration timing info (#50) · 9ab74205
  gilbertlee-amd authored Aug 14, 2023
  
  9ab74205
19 Jul, 2023 1 commit
- Fixing #SubExec bug in P2PBenchmark (#47) · d32b88fe
  gilbertlee-amd authored Jul 19, 2023
  
  d32b88fe
14 Jul, 2023 1 commit
- Add All2All Benchmark (#46) · 0bdcd635
  gilbertlee-amd authored Jul 14, 2023
```
* Adding a2a preset benchmark, fixing some gfx941 values
```
  0bdcd635
12 Jul, 2023 1 commit
- Adding preset scaling benchmark (#45) · 9132801d
  gilbertlee-amd authored Jul 12, 2023
  
  9132801d
05 Jun, 2023 1 commit
- Changing to wall_clock64() (#35) · f903fda3
  gilbertlee-amd authored Jun 05, 2023
  
  f903fda3
27 Apr, 2023 1 commit
- Fixing SAMPLING_FACTOR (#26) · b7215502
  gilbertlee-amd authored Apr 27, 2023
  
  b7215502
05 Apr, 2023 1 commit
- Fixing USE_PREP_KERNEL vs VALIDATE_DIRECT (#21) · 989cdd9b
  gilbertlee-amd authored Apr 05, 2023
  
  989cdd9b
04 Apr, 2023 1 commit
- Src validate direct (#20) · 633e3b91
  gilbertlee-amd authored Apr 04, 2023
```
* Validating source directly, extra nullptr deallocation checks
```
  633e3b91
31 Mar, 2023 1 commit
- Adding direct destination mem validation, env var refactor (#19) · 5901ce0e
  gilbertlee-amd authored Mar 30, 2023
  
  5901ce0e
29 Mar, 2023 1 commit

Source Prep Kernel / Better NVCC support (#18) · e6f64e97

gilbertlee-amd authored Mar 28, 2023

* Adding source prep kernel (USE_PREP_KERNEL)
* Adding nvcc-only compilation path
* Fix for NVIDIA - set shared mem usage to 0 by default
* Updating default fill pattern for source data
* Restoring missing example.cfg file

e6f64e97

24 Mar, 2023 1 commit
- Adding src array check, CONTINUE_ON_ERROR, gpu mem clear (#16) · b5439548
  gilbertlee-amd authored Mar 24, 2023
  
  b5439548
20 Mar, 2023 1 commit
- Fixing large Transfers, more mismatch debug (#14) · 5087ad50
  gilbertlee-amd authored Mar 20, 2023
  
  5087ad50
15 Mar, 2023 3 commits
- Added Hex value printed off for better debugging · 125dfffc
  PedramAlizadeh authored Mar 15, 2023
  
  125dfffc
- Added pthread linking · 3282bbb5
  PedramAlizadeh authored Mar 15, 2023
  
  3282bbb5
- Added documentation · 5b686add
  PedramAlizadeh authored Mar 15, 2023
  
  5b686add
06 Mar, 2023 1 commit
- adding cmake support · 0b2ba908
  PedramAlizadeh authored Mar 02, 2023
  
  0b2ba908
31 Jan, 2023 1 commit
- v1.12 Adding NVIDIA platform support (#10) · c72a105f
  gilbertlee-amd authored Jan 31, 2023
  
  c72a105f