Conversation

Notices

Embed this notice
Arne Babenhauserheide (arnebab@rollenspiel.social)'s status on Wednesday, 22-Jan-2025 16:02:15 JST Arne Babenhauserheide
- DCoder 🇱🇹❤🇺🇦
@dcoderlt missing here: how did *latency* of hardware improve?
I’m asking because latency — not throughput — is what we feel when we interact with a computer, and negating the latency improvements is far easier than negating the throughput improvements.
See for example access memory times not getting much faster:
https://en.wikipedia.org/wiki/CAS_latency#Memory_timing_examples
(though L1 cache did, but you’re fare away of that if you have to react to keyboard input)
In conversation about a month ago from rollenspiel.social permalink
Attachments
1. No result found on File_thumbnail lookup.
  
  CAS latency
  
  Column address strobe latency, also called CAS latency or CL, is the delay in clock cycles between the READ command and the moment data is available. In asynchronous DRAM, the interval is specified in nanoseconds (absolute time). In synchronous DRAM, the interval is specified in clock cycles. Because the latency is dependent upon a number of clock ticks instead of absolute time, the actual time for an SDRAM module to respond to a CAS event might vary between uses of the same module if the clock rate differs. RAM operation background Dynamic RAM is arranged in a rectangular array. Each row is selected by a horizontal word line. Sending a logical high signal along a given row enables the MOSFETs present in that row, connecting each storage capacitor to its corresponding vertical bit line. Each bit line is connected to a sense amplifier that amplifies the small voltage change produced by the storage capacitor. This amplified signal is then output from the DRAM chip as well as driven back up the bit line to refresh the row. When no word line is active, the array is...
- Embed this notice
  Arne Babenhauserheide (arnebab@rollenspiel.social)'s status on Wednesday, 22-Jan-2025 18:34:32 JST Arne Babenhauserheide
  in reply to
  - DCoder 🇱🇹❤🇺🇦
  @dcoderlt Yes, it does.
  Similar to the network getting ever faster but websites getting slower. Because internet latency is lightspeed bound. And physics does not budge. So websites must take that as hard constraint — but most seem to not do it.
  
  In conversation about a month ago permalink
- Embed this notice
  DCoder 🇱🇹❤🇺🇦 (dcoderlt@ohai.social)'s status on Wednesday, 22-Jan-2025 18:34:33 JST DCoder 🇱🇹❤🇺🇦
  in reply to
  
  @ArneBab
  That’s a good point, but the overall situation — hardware is beating its chest about more and more performance, and interacting with software is unapologetically getting slower and slower — still sucks.
  
  In conversation about a month ago permalink

Public

Conversation

Notices

Feeds