- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
How many cycles do the new instructions require
and can they be paired with other intructions?
aesimc
aeskeygenassist
aesenc
aesenclast
aesdec
aesdeclast
pclmulqdq
and can they be paired with other intructions?
aesimc
aeskeygenassist
aesenc
aesenclast
aesdec
aesdeclast
pclmulqdq
Link Copied
2 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The AES-NI white paper has some performance results from which you could estimate the instruction latencies: http://software.intel.com/en-us/articles/intel-advanced-encryption-standard-aes-instructions-set/. It explicitly mentions that they are pipelined too.
You can expect pclmulqdq to perform the same as other vector multiplications.
You can expect pclmulqdq to perform the same as other vector multiplications.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
it changes by impl, you can take your aes kernel(s) and run it through the CodenAnalyzer to understand tput, latency, etc
http://software.intel.com/en-us/articles/intel-architecture-code-analyzer/
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page