GPU · PRE-SALE VERIFICATION
Tesla V100 32GB
PG500-216 售前检测记录
检测日期 · 2026年11月7日(台北时间 UTC+08:00)
完整 10 分钟校验正常完成 · 程序退出码 0
28 GiB 显存多模式读写与 FP32 矩阵计算交替验证。本次已执行的校验未发现数据错误,ECC 与退役页计数未增加。
10 分钟负载实测 600.031 秒
118 轮每轮校验 28 GiB 显存
388,771矩阵计算结果校验次数
0记录到的校验错误
核对这张卡
- 设备名称
- Tesla PG500-216 · 32,768 MiB
- 序列号 SN
1565221004035- GPU UUID
GPU-ddc919c1-d37d-ffb1-bc58-874e4c375fb4- PCI 地址
00000000:42:00.0- VBIOS
88.00.9C.00.01- 驱动版本
580.178.04
检测结果
| 检查项目 | 记录结果 |
|---|---|
| HBM2 写入 / 读取 / 数据保留复查 | 未发现错误 |
| FP32 矩阵结果与整数参考值比较 | 未发现错误 |
| ECC volatile / aggregate 可读计数 | 起止均为 0 |
| 单 / 双比特 retired pages | 起止均为 0,无待退役页 |
| 新增内核 Xid 错误 | 监控及区间复核未发现 |
| 最高核心 / 显存温度 | 82°C / 79°C |
| 程序结束状态 | 正常完成,exit 0 |
测试时间:16:05:01–16:15:04;监控窗口含初始化约 602.44 秒。采样峰值功耗 259.20 W;瞬时读数不等于持续功耗。
完整 10 分钟结束
- 开始时间
- 2026年11月7日 16:05:01(台北时间)
- 结束时间
- 2026年11月7日 16:15:04(台北时间)
- 负载时间
- 600.031 秒
- 监控时间
- 602.44 秒(含初始化)
- 结束状态
- 正常完成,程序退出码 0
方法与适用范围
- 28 GiB HBM2(30,064,771,072 字节)逐字校验,循环使用零、全一、AA、55、地址哈希及反相地址哈希模式。
- 与约 5 秒 FP32 cuBLAS SGEMM 交替执行,矩阵尺寸 2048×2048,使用 pedantic math;每次输出对比独立整数求和参考值,随后复查显存保留数据。
- 使用已有 CUDA / cuBLAS 编译随附测试源码;没有修改频率、功耗上限、ECC、风扇或 BIOS 设置。
- 监控检查温度、ECC、退役页、Xid、热降频及程序退出状态。
这是卖家自测记录,非第三方鉴定或 NVIDIA 认证;未覆盖全部 32GB 物理显存、FP64、Tensor Core、所有算子或长期可靠性。历史热降频累计计时未清零;驱动 SW Power Cap 累计时长存在异常大值,原始报告保留,不据此推导真实限功耗时长。文件哈希用于核对内容一致,不构成独立可信时间戳。
原始记录 · 可直接展开
原始日志时间含 UTC−05:00 或 UTC,与上方台北时间为同一时刻。公开文件保持原始内容;校验清单使用公开文件名。
原始身份与 ECC 检测
========================================
NVIDIA V100 PRE-SALE REPORT
========================================
Test Time: 2026-11-07T02:37:17-05:00
========== GPU IDENTITY ==========
index, name, serial, uuid, pci.bus_id, memory.total [MiB], vbios_version, driver_version
1, Tesla PG500-216, 1565221004035, GPU-ddc919c1-d37d-ffb1-bc58-874e4c375fb4, 00000000:42:00.0, 32768 MiB, 88.00.9C.00.01, 580.178.04
========== GPU LIVE STATUS ==========
Sat Nov 7 02:37:17 2026
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.178.04 Driver Version: 580.178.04 CUDA Version: 13.0 |
+-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 1 Tesla PG500-216 Off | 00000000:42:00.0 Off | 0 |
| N/A 44C P0 31W / 250W | 11MiB / 32768MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 1 N/A N/A 2860 G /usr/bin/gnome-shell 5MiB |
+-----------------------------------------------------------------------------------------+
========== ECC & MEMORY HEALTH ==========
==============NVSMI LOG==============
Timestamp : Sat Nov 7 02:37:17 2026
Driver Version : 580.178.04
CUDA Version : 13.0
Attached GPUs : 2
GPU 00000000:42:00.0
ECC Mode
Current : Enabled
Pending : Enabled
ECC Errors
Volatile
Single Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : 0
Double Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : 0
Total : 0
Aggregate
Single Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : 0
Double Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : 0
Total : 0
Retired Pages
Single Bit ECC : 0
Double Bit ECC : 0
Pending Page Blacklist : No
========== TEMPERATURE & POWER ==========
==============NVSMI LOG==============
Timestamp : Sat Nov 7 02:37:17 2026
Driver Version : 580.178.04
CUDA Version : 13.0
Attached GPUs : 2
GPU 00000000:42:00.0
Temperature
GPU Current Temp : 44 C
GPU T.Limit Temp : N/A
GPU Shutdown Temp : 91 C
GPU Slowdown Temp : 88 C
GPU Max Operating Temp : 83 C
GPU Target Temperature : N/A
Memory Current Temp : 44 C
Memory Max Operating Temp : 85 C
GPU Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : 31.51 W
Current Power Limit : 250.00 W
Requested Power Limit : 250.00 W
Default Power Limit : 250.00 W
Min Power Limit : 100.00 W
Max Power Limit : 250.00 W
Power Samples
Duration : 2.38 sec
Number of Samples : 119
Max : 31.61 W
Min : 31.41 W
Avg : 31.51 W
GPU Memory Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : N/A
Module Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : N/A
Current Power Limit : N/A
Requested Power Limit : N/A
Default Power Limit : N/A
Min Power Limit : N/A
Max Power Limit : N/A
========== TEST COMPLETED ==========
Test Time: 2026-11-07T02:37:17-05:00
完整 10 分钟负载日志
DEVICE name=Tesla PG500-216 pci=0000:42:00.0 total_bytes=34072559616 duration_seconds=600 METHOD memory_bytes=30064771072 patterns=zero,ones,AA,55,address_hash,inverted_address_hash compute=FP32_SGEMM N=2048 exact_integer_reference pedantic_math=1 HBM elapsed=0.071 pass=0 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=5.103 checked_gemms=3155 total_gemms=3155 retention_errors=0 HBM elapsed=5.173 pass=1 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=10.205 checked_gemms=3250 total_gemms=6405 retention_errors=0 HBM elapsed=10.276 pass=2 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=15.308 checked_gemms=3193 total_gemms=9598 retention_errors=0 HBM elapsed=15.379 pass=3 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=20.412 checked_gemms=3251 total_gemms=12849 retention_errors=0 HBM elapsed=20.484 pass=4 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=25.516 checked_gemms=3265 total_gemms=16114 retention_errors=0 HBM elapsed=25.588 pass=5 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=30.621 checked_gemms=3252 total_gemms=19366 retention_errors=0 HBM elapsed=30.690 pass=6 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=35.722 checked_gemms=3216 total_gemms=22582 retention_errors=0 HBM elapsed=35.793 pass=7 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=40.824 checked_gemms=3254 total_gemms=25836 retention_errors=0 HBM elapsed=40.895 pass=8 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=45.926 checked_gemms=3254 total_gemms=29090 retention_errors=0 HBM elapsed=45.998 pass=9 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=51.029 checked_gemms=3223 total_gemms=32313 retention_errors=0 HBM elapsed=51.101 pass=10 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=56.134 checked_gemms=3269 total_gemms=35582 retention_errors=0 HBM elapsed=56.206 pass=11 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=61.237 checked_gemms=3266 total_gemms=38848 retention_errors=0 HBM elapsed=61.307 pass=12 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=66.338 checked_gemms=3255 total_gemms=42103 retention_errors=0 HBM elapsed=66.409 pass=13 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=71.440 checked_gemms=3263 total_gemms=45366 retention_errors=0 HBM elapsed=71.511 pass=14 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=76.542 checked_gemms=3283 total_gemms=48649 retention_errors=0 HBM elapsed=76.614 pass=15 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=81.646 checked_gemms=3257 total_gemms=51906 retention_errors=0 HBM elapsed=81.718 pass=16 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=86.749 checked_gemms=3290 total_gemms=55196 retention_errors=0 HBM elapsed=86.821 pass=17 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=91.853 checked_gemms=3268 total_gemms=58464 retention_errors=0 HBM elapsed=91.922 pass=18 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=96.954 checked_gemms=3259 total_gemms=61723 retention_errors=0 HBM elapsed=97.025 pass=19 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=102.057 checked_gemms=3262 total_gemms=64985 retention_errors=0 HBM elapsed=102.127 pass=20 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=107.159 checked_gemms=3299 total_gemms=68284 retention_errors=0 HBM elapsed=107.231 pass=21 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=112.262 checked_gemms=3293 total_gemms=71577 retention_errors=0 HBM elapsed=112.334 pass=22 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=117.367 checked_gemms=3269 total_gemms=74846 retention_errors=0 HBM elapsed=117.439 pass=23 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=122.471 checked_gemms=3329 total_gemms=78175 retention_errors=0 HBM elapsed=122.540 pass=24 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=127.572 checked_gemms=3337 total_gemms=81512 retention_errors=0 HBM elapsed=127.642 pass=25 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=132.673 checked_gemms=3338 total_gemms=84850 retention_errors=0 HBM elapsed=132.744 pass=26 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=137.775 checked_gemms=3338 total_gemms=88188 retention_errors=0 HBM elapsed=137.847 pass=27 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=142.878 checked_gemms=3329 total_gemms=91517 retention_errors=0 HBM elapsed=142.949 pass=28 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=147.981 checked_gemms=3291 total_gemms=94808 retention_errors=0 HBM elapsed=148.053 pass=29 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=153.085 checked_gemms=3334 total_gemms=98142 retention_errors=0 HBM elapsed=153.154 pass=30 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=158.185 checked_gemms=3337 total_gemms=101479 retention_errors=0 HBM elapsed=158.256 pass=31 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=163.287 checked_gemms=3338 total_gemms=104817 retention_errors=0 HBM elapsed=163.358 pass=32 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=168.389 checked_gemms=3338 total_gemms=108155 retention_errors=0 HBM elapsed=168.460 pass=33 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=173.492 checked_gemms=3294 total_gemms=111449 retention_errors=0 HBM elapsed=173.563 pass=34 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=178.595 checked_gemms=3329 total_gemms=114778 retention_errors=0 HBM elapsed=178.667 pass=35 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=183.698 checked_gemms=3328 total_gemms=118106 retention_errors=0 HBM elapsed=183.768 pass=36 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=188.799 checked_gemms=3333 total_gemms=121439 retention_errors=0 HBM elapsed=188.869 pass=37 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=193.901 checked_gemms=3333 total_gemms=124772 retention_errors=0 HBM elapsed=193.971 pass=38 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=199.003 checked_gemms=3321 total_gemms=128093 retention_errors=0 HBM elapsed=199.075 pass=39 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=204.106 checked_gemms=3312 total_gemms=131405 retention_errors=0 HBM elapsed=204.178 pass=40 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=209.210 checked_gemms=3338 total_gemms=134743 retention_errors=0 HBM elapsed=209.283 pass=41 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=214.315 checked_gemms=3338 total_gemms=138081 retention_errors=0 HBM elapsed=214.385 pass=42 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=219.417 checked_gemms=3338 total_gemms=141419 retention_errors=0 HBM elapsed=219.487 pass=43 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=224.518 checked_gemms=3336 total_gemms=144755 retention_errors=0 HBM elapsed=224.588 pass=44 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=229.619 checked_gemms=3290 total_gemms=148045 retention_errors=0 HBM elapsed=229.691 pass=45 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=234.721 checked_gemms=3338 total_gemms=151383 retention_errors=0 HBM elapsed=234.794 pass=46 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=239.826 checked_gemms=3338 total_gemms=154721 retention_errors=0 HBM elapsed=239.898 pass=47 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=244.930 checked_gemms=3335 total_gemms=158056 retention_errors=0 HBM elapsed=245.000 pass=48 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=250.032 checked_gemms=3338 total_gemms=161394 retention_errors=0 HBM elapsed=250.102 pass=49 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=255.134 checked_gemms=3294 total_gemms=164688 retention_errors=0 HBM elapsed=255.205 pass=50 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=260.235 checked_gemms=3336 total_gemms=168024 retention_errors=0 HBM elapsed=260.307 pass=51 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=265.337 checked_gemms=3340 total_gemms=171364 retention_errors=0 HBM elapsed=265.409 pass=52 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=270.441 checked_gemms=3339 total_gemms=174703 retention_errors=0 HBM elapsed=270.513 pass=53 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=275.546 checked_gemms=3336 total_gemms=178039 retention_errors=0 HBM elapsed=275.615 pass=54 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=280.646 checked_gemms=3332 total_gemms=181371 retention_errors=0 HBM elapsed=280.716 pass=55 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=285.748 checked_gemms=3300 total_gemms=184671 retention_errors=0 HBM elapsed=285.818 pass=56 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=290.849 checked_gemms=3337 total_gemms=188008 retention_errors=0 HBM elapsed=290.921 pass=57 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=295.952 checked_gemms=3339 total_gemms=191347 retention_errors=0 HBM elapsed=296.023 pass=58 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=301.056 checked_gemms=3336 total_gemms=194683 retention_errors=0 HBM elapsed=301.129 pass=59 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=306.161 checked_gemms=3337 total_gemms=198020 retention_errors=0 HBM elapsed=306.230 pass=60 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=311.261 checked_gemms=3290 total_gemms=201310 retention_errors=0 HBM elapsed=311.331 pass=61 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=316.363 checked_gemms=3338 total_gemms=204648 retention_errors=0 HBM elapsed=316.433 pass=62 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=321.465 checked_gemms=3336 total_gemms=207984 retention_errors=0 HBM elapsed=321.537 pass=63 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=326.568 checked_gemms=3340 total_gemms=211324 retention_errors=0 HBM elapsed=326.640 pass=64 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=331.672 checked_gemms=3338 total_gemms=214662 retention_errors=0 HBM elapsed=331.744 pass=65 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=336.775 checked_gemms=3298 total_gemms=217960 retention_errors=0 HBM elapsed=336.845 pass=66 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=341.877 checked_gemms=3326 total_gemms=221286 retention_errors=0 HBM elapsed=341.947 pass=67 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=346.978 checked_gemms=3337 total_gemms=224623 retention_errors=0 HBM elapsed=347.049 pass=68 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=352.080 checked_gemms=3336 total_gemms=227959 retention_errors=0 HBM elapsed=352.152 pass=69 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=357.183 checked_gemms=3336 total_gemms=231295 retention_errors=0 HBM elapsed=357.256 pass=70 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=362.287 checked_gemms=3334 total_gemms=234629 retention_errors=0 HBM elapsed=362.360 pass=71 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=367.392 checked_gemms=3290 total_gemms=237919 retention_errors=0 HBM elapsed=367.462 pass=72 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=372.493 checked_gemms=3327 total_gemms=241246 retention_errors=0 HBM elapsed=372.563 pass=73 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=377.595 checked_gemms=3074 total_gemms=244320 retention_errors=0 HBM elapsed=377.665 pass=74 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=382.697 checked_gemms=3327 total_gemms=247647 retention_errors=0 HBM elapsed=382.769 pass=75 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=387.801 checked_gemms=3338 total_gemms=250985 retention_errors=0 HBM elapsed=387.872 pass=76 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=392.904 checked_gemms=3285 total_gemms=254270 retention_errors=0 HBM elapsed=392.977 pass=77 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=398.008 checked_gemms=3336 total_gemms=257606 retention_errors=0 HBM elapsed=398.078 pass=78 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=403.109 checked_gemms=3336 total_gemms=260942 retention_errors=0 HBM elapsed=403.180 pass=79 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=408.211 checked_gemms=3327 total_gemms=264269 retention_errors=0 HBM elapsed=408.281 pass=80 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=413.312 checked_gemms=3336 total_gemms=267605 retention_errors=0 HBM elapsed=413.384 pass=81 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=418.416 checked_gemms=3329 total_gemms=270934 retention_errors=0 HBM elapsed=418.488 pass=82 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=423.519 checked_gemms=3298 total_gemms=274232 retention_errors=0 HBM elapsed=423.592 pass=83 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=428.624 checked_gemms=3333 total_gemms=277565 retention_errors=0 HBM elapsed=428.693 pass=84 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=433.725 checked_gemms=3339 total_gemms=280904 retention_errors=0 HBM elapsed=433.803 pass=85 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=438.834 checked_gemms=3161 total_gemms=284065 retention_errors=0 HBM elapsed=438.905 pass=86 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=443.937 checked_gemms=3293 total_gemms=287358 retention_errors=0 HBM elapsed=444.008 pass=87 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=449.039 checked_gemms=3291 total_gemms=290649 retention_errors=0 HBM elapsed=449.111 pass=88 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=454.144 checked_gemms=3333 total_gemms=293982 retention_errors=0 HBM elapsed=454.216 pass=89 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=459.248 checked_gemms=3332 total_gemms=297314 retention_errors=0 HBM elapsed=459.317 pass=90 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=464.348 checked_gemms=3336 total_gemms=300650 retention_errors=0 HBM elapsed=464.418 pass=91 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=469.449 checked_gemms=3306 total_gemms=303956 retention_errors=0 HBM elapsed=469.519 pass=92 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=474.551 checked_gemms=3292 total_gemms=307248 retention_errors=0 HBM elapsed=474.622 pass=93 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=479.654 checked_gemms=3331 total_gemms=310579 retention_errors=0 HBM elapsed=479.726 pass=94 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=484.758 checked_gemms=3336 total_gemms=313915 retention_errors=0 HBM elapsed=484.831 pass=95 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=489.862 checked_gemms=3332 total_gemms=317247 retention_errors=0 HBM elapsed=489.932 pass=96 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=494.963 checked_gemms=3338 total_gemms=320585 retention_errors=0 HBM elapsed=495.034 pass=97 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=500.066 checked_gemms=3285 total_gemms=323870 retention_errors=0 HBM elapsed=500.137 pass=98 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=505.168 checked_gemms=3238 total_gemms=327108 retention_errors=0 HBM elapsed=505.240 pass=99 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=510.271 checked_gemms=3331 total_gemms=330439 retention_errors=0 HBM elapsed=510.343 pass=100 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=515.376 checked_gemms=3334 total_gemms=333773 retention_errors=0 HBM elapsed=515.448 pass=101 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=520.480 checked_gemms=3326 total_gemms=337099 retention_errors=0 HBM elapsed=520.550 pass=102 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=525.580 checked_gemms=3333 total_gemms=340432 retention_errors=0 HBM elapsed=525.651 pass=103 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=530.682 checked_gemms=3277 total_gemms=343709 retention_errors=0 HBM elapsed=530.752 pass=104 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=535.784 checked_gemms=3334 total_gemms=347043 retention_errors=0 HBM elapsed=535.855 pass=105 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=540.886 checked_gemms=3337 total_gemms=350380 retention_errors=0 HBM elapsed=540.958 pass=106 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=545.990 checked_gemms=3334 total_gemms=353714 retention_errors=0 HBM elapsed=546.062 pass=107 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=551.094 checked_gemms=3332 total_gemms=357046 retention_errors=0 HBM elapsed=551.164 pass=108 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=556.196 checked_gemms=3326 total_gemms=360372 retention_errors=0 HBM elapsed=556.266 pass=109 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=561.297 checked_gemms=3262 total_gemms=363634 retention_errors=0 HBM elapsed=561.368 pass=110 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=566.400 checked_gemms=3268 total_gemms=366902 retention_errors=0 HBM elapsed=566.472 pass=111 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=571.503 checked_gemms=3334 total_gemms=370236 retention_errors=0 HBM elapsed=571.576 pass=112 pattern=4 bytes=30064771072 errors=0 COMPUTE elapsed=576.608 checked_gemms=3333 total_gemms=373569 retention_errors=0 HBM elapsed=576.680 pass=113 pattern=5 bytes=30064771072 errors=0 COMPUTE elapsed=581.712 checked_gemms=3326 total_gemms=376895 retention_errors=0 HBM elapsed=581.782 pass=114 pattern=0 bytes=30064771072 errors=0 COMPUTE elapsed=586.813 checked_gemms=3284 total_gemms=380179 retention_errors=0 HBM elapsed=586.883 pass=115 pattern=1 bytes=30064771072 errors=0 COMPUTE elapsed=591.915 checked_gemms=3322 total_gemms=383501 retention_errors=0 HBM elapsed=591.985 pass=116 pattern=2 bytes=30064771072 errors=0 COMPUTE elapsed=597.016 checked_gemms=3327 total_gemms=386828 retention_errors=0 HBM elapsed=597.088 pass=117 pattern=3 bytes=30064771072 errors=0 COMPUTE elapsed=600.031 checked_gemms=1943 total_gemms=388771 retention_errors=0 TEST_COMPLETE elapsed=600.031 memory_passes=118 checked_gemms=388771 errors=0
10 分钟测试前 GPU 状态
==============NVSMI LOG==============
Timestamp : Sat Nov 7 03:05:02 2026
Driver Version : 580.178.04
CUDA Version : 13.0
Attached GPUs : 2
GPU 00000000:42:00.0
Product Name : Tesla PG500-216
Product Brand : Tesla
Product Architecture : Volta
Display Mode : Requested functionality has been deprecated
Display Attached : No
Display Active : Disabled
Persistence Mode : Disabled
Addressing Mode : N/A
MIG Mode
Current : N/A
Pending : N/A
Accounting Mode : Disabled
Accounting Mode Buffer Size : 4000
Driver Model
Current : N/A
Pending : N/A
Serial Number : 1565221004035
GPU UUID : GPU-ddc919c1-d37d-ffb1-bc58-874e4c375fb4
GPU PDI : 0x7b2acfe0ce89
Minor Number : 1
VBIOS Version : 88.00.9C.00.01
MultiGPU Board : No
Board ID : 0x4200
Board Part Number : 900-2G500-0150-000
GPU Part Number : 1DF0-887-A1
FRU Part Number : N/A
Platform Info
Chassis Serial Number : N/A
Slot Number : N/A
Tray Index : N/A
Host ID : N/A
Peer Type : N/A
Module Id : 1
GPU Fabric GUID : N/A
Inforom Version
Image Version : G500.0216.00.02
OEM Object : 1.1
ECC Object : 5.0
Power Management Object : N/A
Inforom BBX Object Flush
Latest Timestamp : N/A
Latest Duration : N/A
GPU Operation Mode
Current : N/A
Pending : N/A
GPU C2C Mode : N/A
GPU Virtualization Mode
Virtualization Mode : None
Host VGPU Mode : N/A
vGPU Heterogeneous Mode : N/A
GPU Recovery Action : None
GSP Firmware Version : N/A
IBMNPU
Relaxed Ordering Mode : N/A
PCI
Bus : 0x42
Device : 0x00
Domain : 0x0000
Base Classcode : 0x3
Sub Classcode : 0x2
Device Id : 0x1DF010DE
Bus Id : 00000000:42:00.0
Sub System Id : 0x13F510DE
GPU Link Info
PCIe Generation
Max : 3
Current : 3
Device Current : 3
Device Max : 3
Host Max : 3
Link Width
Max : 16x
Current : 16x
Bridge Chip
Type : N/A
Firmware : N/A
Replays Since Reset : 0
Replay Number Rollovers : 0
Tx Throughput : 0 KB/s
Rx Throughput : 48 KB/s
Atomic Caps Outbound : N/A
Atomic Caps Inbound : N/A
Fan Speed : N/A
Performance State : P0
Clocks Event Reasons
Idle : Active
Applications Clocks Setting : Not Active
SW Power Cap : Not Active
HW Slowdown : Not Active
HW Thermal Slowdown : Not Active
HW Power Brake Slowdown : Not Active
Sync Boost : Not Active
SW Thermal Slowdown : Not Active
Display Clock Setting : Not Active
Clocks Event Reasons Counters
SW Power Capping : 158981758 us
Sync Boost : 0 us
SW Thermal Slowdown : 1893290814 us
HW Thermal Slowdown : 0 us
HW Power Braking : 0 us
Sparse Operation Mode : N/A
FB Memory Usage
Total : 32768 MiB
Reserved : 274 MiB
Used : 11 MiB
Free : 32484 MiB
BAR1 Memory Usage
Total : 32768 MiB
Used : 5 MiB
Free : 32763 MiB
Conf Compute Protected Memory Usage
Total : 0 MiB
Used : 0 MiB
Free : 0 MiB
Compute Mode : Default
Utilization
GPU : 0 %
Memory : 0 %
Encoder : 0 %
Decoder : 0 %
JPEG : N/A
OFA : N/A
Encoder Stats
Active Sessions : 0
Average FPS : 0
Average Latency : 0
FBC Stats
Active Sessions : 0
Average FPS : 0
Average Latency : 0
DRAM Encryption Mode
Current : N/A
Pending : N/A
ECC Mode
Current : Enabled
Pending : Enabled
ECC Errors
Volatile
Single Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : 0
Double Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : 0
Total : 0
Aggregate
Single Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : 0
Double Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : 0
Total : 0
Retired Pages
Single Bit ECC : 0
Double Bit ECC : 0
Pending Page Blacklist : No
Remapped Rows : N/A
Temperature
GPU Current Temp : 48 C
GPU T.Limit Temp : N/A
GPU Shutdown Temp : 91 C
GPU Slowdown Temp : 88 C
GPU Max Operating Temp : 83 C
GPU Target Temperature : N/A
Memory Current Temp : 48 C
Memory Max Operating Temp : 85 C
GPU Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : 33.23 W
Current Power Limit : 250.00 W
Requested Power Limit : 250.00 W
Default Power Limit : 250.00 W
Min Power Limit : 100.00 W
Max Power Limit : 250.00 W
GPU Memory Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : N/A
Module Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : N/A
Current Power Limit : N/A
Requested Power Limit : N/A
Default Power Limit : N/A
Min Power Limit : N/A
Max Power Limit : N/A
Power Smoothing : N/A
Workload Power Profiles
Requested Profiles : N/A
Enforced Profiles : N/A
Clocks
Graphics : 135 MHz
SM : 135 MHz
Memory : 1107 MHz
Video : 555 MHz
Applications Clocks
Graphics : 1260 MHz
Memory : 1107 MHz
Default Applications Clocks
Graphics : 1260 MHz
Memory : 1107 MHz
Deferred Clocks
Memory : N/A
Max Clocks
Graphics : 1380 MHz
SM : 1380 MHz
Memory : 1107 MHz
Video : 1237 MHz
Max Customer Boost Clocks
Graphics : 1380 MHz
Clock Policy
Auto Boost : N/A
Auto Boost Default : N/A
Fabric
State : N/A
Status : N/A
CliqueId : N/A
ClusterUUID : N/A
Health
Summary : N/A
Bandwidth : N/A
Route Recovery in progress : N/A
Route Unhealthy : N/A
Access Timeout Recovery : N/A
Incorrect Configuration : N/A
Partition Assigned : N/A
Processes
GPU instance ID : N/A
Compute instance ID : N/A
Process ID : 2860
Type : G
Name : /usr/bin/gnome-shell
Used GPU Memory : 5 MiB
Capabilities
EGM : disabled
10 分钟测试后 GPU 状态
==============NVSMI LOG==============
Timestamp : Sat Nov 7 03:15:04 2026
Driver Version : 580.178.04
CUDA Version : 13.0
Attached GPUs : 2
GPU 00000000:42:00.0
Product Name : Tesla PG500-216
Product Brand : Tesla
Product Architecture : Volta
Display Mode : Requested functionality has been deprecated
Display Attached : No
Display Active : Disabled
Persistence Mode : Disabled
Addressing Mode : N/A
MIG Mode
Current : N/A
Pending : N/A
Accounting Mode : Disabled
Accounting Mode Buffer Size : 4000
Driver Model
Current : N/A
Pending : N/A
Serial Number : 1565221004035
GPU UUID : GPU-ddc919c1-d37d-ffb1-bc58-874e4c375fb4
GPU PDI : 0x7b2acfe0ce89
Minor Number : 1
VBIOS Version : 88.00.9C.00.01
MultiGPU Board : No
Board ID : 0x4200
Board Part Number : 900-2G500-0150-000
GPU Part Number : 1DF0-887-A1
FRU Part Number : N/A
Platform Info
Chassis Serial Number : N/A
Slot Number : N/A
Tray Index : N/A
Host ID : N/A
Peer Type : N/A
Module Id : 1
GPU Fabric GUID : N/A
Inforom Version
Image Version : G500.0216.00.02
OEM Object : 1.1
ECC Object : 5.0
Power Management Object : N/A
Inforom BBX Object Flush
Latest Timestamp : N/A
Latest Duration : N/A
GPU Operation Mode
Current : N/A
Pending : N/A
GPU C2C Mode : N/A
GPU Virtualization Mode
Virtualization Mode : None
Host VGPU Mode : N/A
vGPU Heterogeneous Mode : N/A
GPU Recovery Action : None
GSP Firmware Version : N/A
IBMNPU
Relaxed Ordering Mode : N/A
PCI
Bus : 0x42
Device : 0x00
Domain : 0x0000
Base Classcode : 0x3
Sub Classcode : 0x2
Device Id : 0x1DF010DE
Bus Id : 00000000:42:00.0
Sub System Id : 0x13F510DE
GPU Link Info
PCIe Generation
Max : 3
Current : 3
Device Current : 3
Device Max : 3
Host Max : 3
Link Width
Max : 16x
Current : 16x
Bridge Chip
Type : N/A
Firmware : N/A
Replays Since Reset : 0
Replay Number Rollovers : 0
Tx Throughput : 48 KB/s
Rx Throughput : 1416 KB/s
Atomic Caps Outbound : N/A
Atomic Caps Inbound : N/A
Fan Speed : N/A
Performance State : P0
Clocks Event Reasons
Idle : Not Active
Applications Clocks Setting : Not Active
SW Power Cap : Not Active
HW Slowdown : Not Active
HW Thermal Slowdown : Not Active
HW Power Brake Slowdown : Not Active
Sync Boost : Not Active
SW Thermal Slowdown : Not Active
Display Clock Setting : Not Active
Clocks Event Reasons Counters
SW Power Capping : 158981758 us
Sync Boost : 0 us
SW Thermal Slowdown : 1893290814 us
HW Thermal Slowdown : 0 us
HW Power Braking : 0 us
Sparse Operation Mode : N/A
FB Memory Usage
Total : 32768 MiB
Reserved : 274 MiB
Used : 11 MiB
Free : 32484 MiB
BAR1 Memory Usage
Total : 32768 MiB
Used : 5 MiB
Free : 32763 MiB
Conf Compute Protected Memory Usage
Total : 0 MiB
Used : 0 MiB
Free : 0 MiB
Compute Mode : Default
Utilization
GPU : 0 %
Memory : 0 %
Encoder : 0 %
Decoder : 0 %
JPEG : N/A
OFA : N/A
Encoder Stats
Active Sessions : 0
Average FPS : 0
Average Latency : 0
FBC Stats
Active Sessions : 0
Average FPS : 0
Average Latency : 0
DRAM Encryption Mode
Current : N/A
Pending : N/A
ECC Mode
Current : Enabled
Pending : Enabled
ECC Errors
Volatile
Single Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : 0
Double Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : 0
Total : 0
Aggregate
Single Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : 0
Double Bit
Device Memory : 0
Register File : 0
L1 Cache : 0
L2 Cache : 0
Texture Memory : N/A
Texture Shared : N/A
CBU : 0
Total : 0
Retired Pages
Single Bit ECC : 0
Double Bit ECC : 0
Pending Page Blacklist : No
Remapped Rows : N/A
Temperature
GPU Current Temp : 72 C
GPU T.Limit Temp : N/A
GPU Shutdown Temp : 91 C
GPU Slowdown Temp : 88 C
GPU Max Operating Temp : 83 C
GPU Target Temperature : N/A
Memory Current Temp : 71 C
Memory Max Operating Temp : 85 C
GPU Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : 70.25 W
Current Power Limit : 250.00 W
Requested Power Limit : 250.00 W
Default Power Limit : 250.00 W
Min Power Limit : 100.00 W
Max Power Limit : 250.00 W
GPU Memory Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : N/A
Module Power Readings
Average Power Draw : N/A
Instantaneous Power Draw : N/A
Current Power Limit : N/A
Requested Power Limit : N/A
Default Power Limit : N/A
Min Power Limit : N/A
Max Power Limit : N/A
Power Smoothing : N/A
Workload Power Profiles
Requested Profiles : N/A
Enforced Profiles : N/A
Clocks
Graphics : 1380 MHz
SM : 1380 MHz
Memory : 1107 MHz
Video : 1237 MHz
Applications Clocks
Graphics : 1260 MHz
Memory : 1107 MHz
Default Applications Clocks
Graphics : 1260 MHz
Memory : 1107 MHz
Deferred Clocks
Memory : N/A
Max Clocks
Graphics : 1380 MHz
SM : 1380 MHz
Memory : 1107 MHz
Video : 1237 MHz
Max Customer Boost Clocks
Graphics : 1380 MHz
Clock Policy
Auto Boost : N/A
Auto Boost Default : N/A
Fabric
State : N/A
Status : N/A
CliqueId : N/A
ClusterUUID : N/A
Health
Summary : N/A
Bandwidth : N/A
Route Recovery in progress : N/A
Route Unhealthy : N/A
Access Timeout Recovery : N/A
Incorrect Configuration : N/A
Partition Assigned : N/A
Processes
GPU instance ID : N/A
Compute instance ID : N/A
Process ID : 2860
Type : G
Name : /usr/bin/gnome-shell
Used GPU Memory : 5 MiB
Capabilities
EGM : disabled