Commit fb66367
decode_prof: --trace saves a jobque lane trace of the window (archived-tool parity)
Lifted from history/dasLLAMA/benchmarks/decode_prof.das (the archived predecessor — which
this file should have credited instead of assuming deletion). First use settled the lane
question: at -t N all N lanes (N-1 workers + the computing caller) run 95-97% busy in the
decode window; t7 and t8 do equal wall work, so the t7==t8 pace plateau is shared-resource
saturation, not a parked or half-productive lane.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>1 parent a0e9480 commit fb66367
1 file changed
Lines changed: 12 additions & 0 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
47 | 47 | | |
48 | 48 | | |
49 | 49 | | |
| 50 | + | |
| 51 | + | |
| 52 | + | |
50 | 53 | | |
51 | 54 | | |
52 | 55 | | |
| |||
112 | 115 | | |
113 | 116 | | |
114 | 117 | | |
| 118 | + | |
| 119 | + | |
| 120 | + | |
| 121 | + | |
115 | 122 | | |
116 | 123 | | |
117 | 124 | | |
118 | 125 | | |
119 | 126 | | |
120 | 127 | | |
| 128 | + | |
| 129 | + | |
| 130 | + | |
| 131 | + | |
| 132 | + | |
121 | 133 | | |
122 | 134 | | |
123 | 135 | | |
| |||
0 commit comments