igneum-network/igneum
1
0
Fork 0
Code Issues Pull requests Releases Activity

Class v6 floor lane 4: the 3090, H100 and A100 class v5 stock rows measured (the denominator sweep, 13:25 UK), stock with the lock owed

Browse source 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

Documents-only replay of af23bd60e (2a8572e489) for the box mirror master
This commit is contained in:
igneum-labs 2026-10-08 12:28:12 +00:00
parent 75618b8a50
commit 876ccc1975
1 changed files with 48 additions and 48 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

96
app/igneum-app/tiers/class-v5-tiers.json
View file

@ -767,10 +767,10 @@
"memory_gb": 24,
"label": "estimated",
"stock": {
"mhs": 50.0,
"w": 360.0,
"uj": 7.2,
"class": "v4"
"mhs": 61.49,
"w": 309.4,
"uj": 5.03,
"class": "v5"
},
"tiers": [
{
@ -779,13 +779,13 @@
"power_pct": 80,
"mem_mhz": 0,
"limit_w": 350,
"mhs": 50.0,
"w": 320.0,
"mhw": 0.1563,
"mhs": 61.0,
"w": 275.0,
"mhw": 0.2218,
"source": "measured",
"label": "estimated",
"uj": 6.4,
"note": "the Ampere lever is the power cap and small: the knee sits near 1,800 MHz against a 1,900 to 2,000 MHz stock clock (10 to 15 percent of the draw); a cap that takes the SM under 1,800 costs rate (the 3080 Ti at 63 percent lost 24 to 28 percent); the 3090 Ti read class v3 61.95 MH/s at 249.5 W (4.03)"
"uj": 4.51,
"note": "the Ampere cap lever (10 to 15 percent of the draw; a cap that takes the SM under 1,800 MHz costs rate) on the measured class v5 stock row; the 3090 Ti read class v3 61.95 MH/s at 249.5 W (4.03)"
},
{
"id": "balanced",
@ -793,12 +793,12 @@
"power_pct": 90,
"mem_mhz": 0,
"limit_w": 350,
"mhs": 50.0,
"w": 340.0,
"mhw": 0.1471,
"mhs": 61.49,
"w": 290.0,
"mhw": 0.212,
"source": "measured",
"label": "estimated",
"uj": 6.8,
"uj": 4.72,
"note": "one power rung under stock, no lock"
},
{
@ -807,16 +807,16 @@
"power_pct": 100,
"mem_mhz": 0,
"limit_w": 350,
"mhs": 50.0,
"w": 360.0,
"mhw": 0.1389,
"mhs": 61.49,
"w": 309.4,
"mhw": 0.1987,
"source": "stock",
"label": "estimated",
"uj": 7.2,
"note": "the 0.3.12 rented row 37.79 MH/s at 228.8 W was an earlier class; the standing voters read 42 to 50 MH/s; the class v3 and v4 stock rows are owed to the denominator sweep"
"label": "measured",
"uj": 5.03,
"note": "the denominator sweep, RunPod, 8 October 13:25 UK: class v3 60.01 MH/s at 294.6 W (4.91), class v5 61.49 at 309.4 W (5.03, 46 samples, SM 1,673 MHz, memory 9,501); the class v5 premium on this card 5 percent at stock; stock, lock owed (the host refused -lgc and -lmc)"
}
],
"src": "docs/analysis/prover-tiers-real-cards.md; site/miner-bench.json; the sweep pending"
"src": "~/igneum-fleet/cardbench/rows.jsonl, the denominator sweep 8 October (sweep 2026-10-08-denominator-v5)"
},
{
"card": "NVIDIA GeForce RTX 3080",
@ -1352,10 +1352,10 @@
"memory_gb": 80,
"label": "estimated",
"stock": {
"mhs": 250.6,
"w": 695.1,
"uj": 2.77,
"class": "v4"
"mhs": 241.3,
"w": 621.6,
"uj": 2.58,
"class": "v5"
},
"tiers": [
{
@ -1370,7 +1370,7 @@
"source": "measured",
"label": "estimated",
"uj": 2.0,
"note": "the premium 283 W at stock (11.2 pJ per op); a lock on an owned host (Hopper at 1,980 MHz boost, HBM3-bound): band 1.9 to 2.4; rented hosts refuse -lgc"
"note": "the premium 240 to 280 W at stock says half of it is the clock; a lock on an owned host (Hopper at 1,980 MHz boost, HBM3-bound): about 500 W (2.0); band 1.9 to 2.4; rented hosts refuse -lgc"
},
{
"id": "balanced",
@ -1392,13 +1392,13 @@
"power_pct": 100,
"mem_mhz": 0,
"limit_w": 700,
"mhs": 250.6,
"w": 695.1,
"mhw": 0.3605,
"mhs": 241.3,
"w": 621.6,
"mhw": 0.3882,
"source": "stock",
"label": "measured",
"uj": 2.77,
"note": "rented pods 7 and 8 October (class v3 248.9 MH/s at 411.7 W; class v4 250.6 at 695.1 W); floor lane 1 read class v3 254.6 at 450.4 W (1.77) and class v4 251.9 at 699 W (2.78, the 700 W cap binding, the clock throttled to 1,750 MHz), class v5 250.2 at 698.8 W: v5 = v4 on this card"
"uj": 2.58,
"note": "the denominator sweep, RunPod, 13:25 UK: class v3 252.96 MH/s at 382.4 W (1.51), class v5 241.34 at 621.6 W (2.58, 7 samples, the SM throttled to 1,590 MHz under the 700 W cap); the 7 and 8 October pods read class v4 250.6 at 695.1 W (2.77); -lmc answered 'use --lock-memory-clocks-deferred' and the memory clock stayed 2,619; stock, lock owed"
}
],
"src": "~/igneum-fleet/cardbench/rows.jsonl, 8 October"
@ -1474,10 +1474,10 @@
"memory_gb": 80,
"label": "estimated",
"stock": {
"mhs": 138.0,
"w": 489.3,
"uj": 3.54,
"class": "v4"
"mhs": 133.1,
"w": 398.1,
"uj": 2.99,
"class": "v5"
},
"tiers": [
{
@ -1486,13 +1486,13 @@
"power_pct": 80,
"mem_mhz": 0,
"limit_w": 400,
"mhs": 138.0,
"w": 430.0,
"mhw": 0.3209,
"mhs": 133.0,
"w": 385.0,
"mhw": 0.3455,
"source": "measured",
"label": "estimated",
"uj": 3.1,
"note": "the premium 221 W at stock (15.8 pJ per op, the dearest ALU in the record); the card already runs at 1,410 MHz, so a cap recovers about 60 W"
"uj": 2.89,
"note": "the card already runs at 1,410 MHz and the 400 W host limit binds under class v5 (SM clock gives); a cap under it costs rate on Ampere, so the floor is within 5 percent of the measured stock row"
},
{
"id": "balanced",
@ -1500,12 +1500,12 @@
"power_pct": 90,
"mem_mhz": 0,
"limit_w": 400,
"mhs": 138.0,
"w": 460.0,
"mhw": 0.3,
"mhs": 133.1,
"w": 392.0,
"mhw": 0.3396,
"source": "measured",
"label": "estimated",
"uj": 3.33,
"uj": 2.95,
"note": "one power rung under stock"
},
{
@ -1514,13 +1514,13 @@
"power_pct": 100,
"mem_mhz": 0,
"limit_w": 400,
"mhs": 138.0,
"w": 489.3,
"mhw": 0.282,
"mhs": 133.1,
"w": 398.1,
"mhw": 0.3343,
"source": "stock",
"label": "measured",
"uj": 3.54,
"note": "rented pods 8 October (class v3 138.3 MH/s at 268.6 W; class v4 138.0 at 489.3 W on a 500 W host limit)"
"uj": 2.99,
"note": "the denominator sweep, RunPod, 13:24 UK: class v3 138.06 MH/s at 294.9 W (2.14), class v5 133.11 at 398.1 W (2.99, 19 samples, at the host's 400 W limit, memory 1,593 MHz); the v4watts pod on a 500 W host read class v4 138.0 at 489.3 W (3.54); -lmc 'not supported' on this card; stock, lock owed"
}
],
"src": "~/igneum-fleet/cardbench/rows.jsonl, 8 October"