CI run 6fa311f
- Run: link
- Time: Denver
2025-08-25 08:46:50 MDT • Brussels 2025-08-25 16:46:50 CEST
GEMM Deployment Summary
- Workflow:
AIE Deployment Gemm - Commit:
6fa311fc58c5e37ac9348590b342aa59b3a1f9a6 - Runner:
venus - Run time: Denver
2025-08-25 08:46:32 MDT • Brussels 2025-08-25 16:46:32 CEST - Run: #34; Attempt 1
| HW | M | K | N | Status | Note |
| single_col | 64 | 128 | 128 | ✅ success | |
| single_col | 64 | 128 | 64 | ✅ success | |
| single_col | 64 | 64 | 128 | ✅ success | |
| single_col | 64 | 64 | 64 | ✅ success | |
| single_core | 64 | 128 | 64 | ✅ success | |
| single_core | 64 | 64 | 64 | ✅ success | |
| whole_array | 128 | 128 | 128 | ✅ success | |
| whole_array | 128 | 128 | 64 | ✅ success | |
| whole_array | 128 | 64 | 128 | ✅ success | |
| whole_array | 128 | 64 | 64 | ✅ success | |
| whole_array | 64 | 128 | 128 | ✅ success | |
| whole_array | 64 | 128 | 64 | ✅ success | |
| whole_array | 64 | 64 | 128 | ✅ success | |
| whole_array | 64 | 64 | 64 | ✅ success | |
Totals: ✅ 14 • ❌ 0 • All: 14
Details for Successful Runs
[single_col] M=64 K=128 N=128
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,1 | 16 | 28,276 | 1,038.00 | 31.57 | 49.33 | 18.54 | 28.97 | | tile2,1 | 16 | 28,791 | 1,038.00 | 31.57 | 49.33 | 18.21 | 28.45 | Details for Successful Runs
[single_col] M=64 K=128 N=64
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,1 | 8 | 11,988 | 1,038.00 | 31.57 | 49.33 | 21.87 | 34.17 | | tile2,1 | 8 | 12,504 | 1,038.00 | 31.57 | 49.33 | 20.96 | 32.76 | Details for Successful Runs
[single_col] M=64 K=64 N=128
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,1 | 8 | 13,820 | 1,135.00 | 28.87 | 45.11 | 18.97 | 29.64 | | tile2,1 | 8 | 14,178 | 1,135.00 | 28.87 | 45.11 | 18.49 | 28.89 | Details for Successful Runs
[single_col] M=64 K=64 N=64
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,1 | 4 | 4,506 | 1,070.00 | 30.62 | 47.85 | 29.09 | 45.45 | | tile2,1 | 4 | 4,506 | 1,070.00 | 30.62 | 47.85 | 29.09 | 45.45 | Details for Successful Runs
[single_core] M=64 K=128 N=64
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile2,1 | 16 | 26,237 | 1,038.00 | 31.57 | 49.33 | 19.98 | 31.22 | Details for Successful Runs
[single_core] M=64 K=64 N=64
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile2,1 | 8 | 11,247 | 1,070.00 | 30.62 | 47.85 | 23.31 | 36.42 | Details for Successful Runs
[whole_array] M=128 K=128 N=128
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile2,1 | 16 | 28,184 | 1,098.00 | 29.84 | 46.63 | 18.60 | 29.07 | | tile3,1 | 16 | 28,718 | 1,038.00 | 31.57 | 49.33 | 18.26 | 28.53 | | tile2,2 | 16 | 28,851 | 1,098.00 | 29.84 | 46.63 | 18.17 | 28.39 | | tile3,2 | 16 | 29,394 | 1,038.00 | 31.57 | 49.33 | 17.84 | 27.87 | Details for Successful Runs
[whole_array] M=128 K=128 N=64
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,1 | 8 | 11,988 | 1,038.00 | 31.57 | 49.33 | 21.87 | 34.17 | | tile2,1 | 8 | 12,469 | 1,098.00 | 29.84 | 46.63 | 21.02 | 32.85 | | tile3,2 | 8 | 13,183 | 1,038.00 | 31.57 | 49.33 | 19.89 | 31.07 | | tile2,2 | 8 | 13,658 | 1,098.00 | 29.84 | 46.63 | 19.19 | 29.99 | Details for Successful Runs
[whole_array] M=128 K=64 N=128
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,1 | 8 | 12,801 | 1,135.00 | 28.87 | 45.11 | 20.48 | 32.00 | | tile2,1 | 8 | 12,810 | 1,135.00 | 28.87 | 45.11 | 20.46 | 31.98 | | tile2,2 | 8 | 13,850 | 1,135.00 | 28.87 | 45.11 | 18.93 | 29.57 | | tile3,2 | 8 | 13,967 | 1,135.00 | 28.87 | 45.11 | 18.77 | 29.33 | Details for Successful Runs
[whole_array] M=128 K=64 N=64
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile2,2 | 4 | 4,314 | 1,022.00 | 32.06 | 50.10 | 30.38 | 47.47 | | tile2,1 | 4 | 4,314 | 1,022.00 | 32.06 | 50.10 | 30.38 | 47.47 | | tile3,2 | 4 | 4,506 | 1,070.00 | 30.62 | 47.85 | 29.09 | 45.45 | | tile3,1 | 4 | 4,506 | 1,070.00 | 30.62 | 47.85 | 29.09 | 45.45 | Details for Successful Runs
[whole_array] M=64 K=128 N=128
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,1 | 8 | 12,546 | 1,102.00 | 29.74 | 46.46 | 20.89 | 32.65 | | tile3,2 | 8 | 12,547 | 1,102.00 | 29.74 | 46.46 | 20.89 | 32.65 | | tile2,2 | 8 | 12,593 | 1,022.00 | 32.06 | 50.10 | 20.82 | 32.53 | | tile2,1 | 8 | 12,594 | 1,022.00 | 32.06 | 50.10 | 20.81 | 32.52 | Details for Successful Runs
[whole_array] M=64 K=128 N=64
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile2,1 | 4 | 6,178 | 1,150.00 | 28.49 | 44.52 | 21.22 | 33.15 | | tile3,1 | 4 | 6,178 | 1,150.00 | 28.49 | 44.52 | 21.22 | 33.15 | | tile2,2 | 4 | 6,180 | 1,150.00 | 28.49 | 44.52 | 21.21 | 33.14 | | tile3,2 | 4 | 6,997 | 1,150.00 | 28.49 | 44.52 | 18.73 | 29.27 | Details for Successful Runs
[whole_array] M=64 K=64 N=128
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,2 | 4 | 4,378 | 1,038.00 | 31.57 | 49.33 | 29.94 | 46.78 | | tile3,1 | 4 | 4,378 | 1,038.00 | 31.57 | 49.33 | 29.94 | 46.78 | | tile2,2 | 4 | 4,474 | 1,062.00 | 30.85 | 48.21 | 29.30 | 45.78 | | tile2,1 | 4 | 4,474 | 1,062.00 | 30.85 | 48.21 | 29.30 | 45.78 | Details for Successful Runs
[whole_array] M=64 K=64 N=64
| Tile | Kernels | Total cycles | Avg cycles per kernel | MACs/cycle (kernel) | Peak eff. kernel % | MACs/cycle (system) | Peak eff. system % | |------|---------|--------------|-----------------------|---------------------|--------------------|---------------------|--------------------| | tile3,1 | 2 | 2,317 | 1,150.00 | 28.49 | 44.52 | 28.28 | 44.20 | | tile3,2 | 2 | 2,317 | 1,150.00 | 28.49 | 44.52 | 28.28 | 44.20 | | tile2,2 | 2 | 2,317 | 1,150.00 | 28.49 | 44.52 | 28.28 | 44.20 | | tile2,1 | 2 | 2,317 | 1,150.00 | 28.49 | 44.52 | 28.28 | 44.20 |