- 显卡精度档(B=1,K=8,steps=1):推理 FP32 7.68 / FP16 8.31 / BF16 8.58 ms,整周期不变而FP16 P99 46.6→55.6; 动作偏差 FP16 0.0050°、BF16 0.0377° ⇒ 该批量下不是算力受限,保持 FP32 - float32 认证:48段×9点×15组对的间隙差 max 1.32e-4 mm(有1例高估)→ 现 eps=1e-4 已被越界,要用需 ≥2e-4; 判据结果两边一致(各24接受、0 仅f32安全、0 符号翻转),暂不放宽 dtype 守卫 - 流水线复用特征间隙:第一版42.1→31.8ms 但等价性检查不过(我取缓存行索引取错,差3.19mm); 修正后只剩 −3.1ms 且缓存行与新算差 6.3e-5mm(不同 batch 的结合序)⇒ 放弃 - 顺带修掉轮次34日志里重复的章节标题
58 lines
1.0 KiB
JSON
58 lines
1.0 KiB
JSON
{
|
|
"device": "NVIDIA GeForce RTX 3090",
|
|
"torch": "2.10.0+cu130",
|
|
"K": 8,
|
|
"steps": 1,
|
|
"B": 1,
|
|
"act_scale": 1.0,
|
|
"inference": {
|
|
"fp32": {
|
|
"p50": 7.681,
|
|
"p95": 9.426,
|
|
"p99": 10.631,
|
|
"max": 15.837
|
|
},
|
|
"fp16": {
|
|
"p50": 8.309,
|
|
"p95": 10.791,
|
|
"p99": 12.031,
|
|
"max": 12.322
|
|
},
|
|
"bf16": {
|
|
"p50": 8.577,
|
|
"p95": 11.057,
|
|
"p99": 14.174,
|
|
"max": 17.1
|
|
}
|
|
},
|
|
"cycle": {
|
|
"fp32": {
|
|
"p50": 36.507,
|
|
"p95": 43.688,
|
|
"p99": 46.568,
|
|
"max": 50.598
|
|
},
|
|
"fp16": {
|
|
"p50": 36.162,
|
|
"p95": 50.43,
|
|
"p99": 55.598,
|
|
"max": 57.043
|
|
}
|
|
},
|
|
"output_deviation": {
|
|
"fp16": {
|
|
"act_max_abs": 0.002096,
|
|
"act_p99_abs": 0.001059,
|
|
"deg_max_abs": 0.005,
|
|
"deg_p99_abs": 0.00219,
|
|
"would_change_execution_order": false
|
|
},
|
|
"bf16": {
|
|
"act_max_abs": 0.017171,
|
|
"act_p99_abs": 0.012661,
|
|
"deg_max_abs": 0.03766,
|
|
"deg_p99_abs": 0.03008,
|
|
"would_change_execution_order": true
|
|
}
|
|
}
|
|
} |