以下部分引用 AI 总结,现阶段 AI 仍然有幻觉。请以内容的原文为准。
数据新鲜度群聊 07-14 ✓卖方 07-14 ✓Wrap 断档15天 ✕News 07-15 ✓X 断档12天 ✕页面生成 07-15
Tenstorrent Wormhole n300
6 atoms · 跨 3 天 · 首见 2026-05-05 · 最近 2026-06-27
三色: 🟦 fact 6 · 🟥 take 0 · stance ▲2/▼1/◆0
来源: X 6
时态: fresh:6
标签: 好数字:6
事实 (fact) (6)
- 2026-06-27 · 显存容量
Tenstorrent Wormhole n300: 24GB @ 576 GB/s
tags: 好数字 · → daily
value: qty=24GB
- 2026-06-27 · 内存带宽
Tenstorrent Wormhole n300: 24GB @ 576 GB/s
tags: 好数字 · → daily
value: qty=576 GB/s
- 2026-06-21 · 内存容量与内存带宽
Tenstorrent Wormhole n300: 24GB @ 576 GB/s
tags: 好数字 · → daily
value: qty=24GB @ 576 GB/s · date=2025-06
- 2026-05-05 · 加速code相比优化基线x86-64速度提升
The accelerated code was evaluated on the Tenstorrent Wormhole n300 card. Performance measurements show that it achieves over a 2x speedup and roughly 2x higher energy efficiency compared to a highly optimized baseline version executed on x86-64.
tags: 好数字 · → daily
value: qty=>2x · direction=高于
- 2026-05-05 · 加速code相比优化基线x86-64能效提升
The accelerated code was evaluated on the Tenstorrent Wormhole n300 card. Performance measurements show that it achieves over a 2x speedup and roughly 2x higher energy efficiency compared to a highly optimized baseline version executed on x86-64.
tags: 好数字 · → daily
value: qty=~2x · direction=高于
- 2026-05-05 · 第一和第二种方法四MPI任务并行效率
In terms of scalability, the first and second approaches showed comparable behavior, both exhibiting relatively low parallel efficiency at four MPI tasks, suggesting that further optimization is required.
tags: 好数字 · → daily
value: direction=低
时间轴 (近 20)
- 2026-06-27 ·
fact · 显存容量 · → daily
- 2026-06-27 ·
fact · 内存带宽 · → daily
- 2026-06-21 ·
fact · 内存容量与内存带宽 · → daily
- 2026-05-05 ·
fact · 加速code相比优化基线x86-64速度提升 · → daily
- 2026-05-05 ·
fact · 加速code相比优化基线x86-64能效提升 · → daily
- 2026-05-05 ·
fact · 第一和第二种方法四MPI任务并行效率 · → daily
← 实体目录 · 系统日志