1
2
3
4
5
6
 
 

ULL trading firms go to a lot of trouble to get their servers and switches within the same buildings as the exchanges they trade with to reduce latency. Some firms don’t even use layer 1 switches to be competitive.

7
8
9
 
 

My kernels go 2x faster than MKL for matrices that fit in L2 cache, which makes them a work in progress, since the speedup works best for prompts having fewer than 1,000 tokens.

10
11
Trace Compass (eclipse.dev)
submitted 2 years ago by [M] to c/performance@programming.dev
12
13
14
eBPF Documentary (www.brendangregg.com)
submitted 2 years ago by [M] to c/performance@programming.dev
15
Perf is not enough (motherduck.com)
submitted 2 years ago by [M] to c/performance@programming.dev
16
17
UUID Benchmark War (ardentperf.com)
submitted 2 years ago by [M] to c/performance@programming.dev
18
19
20
21
22
23
Apache SkyWalking (skywalking.apache.org)
submitted 2 years ago by [M] to c/performance@programming.dev
24
25
view more: next ›