in Toronto this month: International Symposium on Code Generation and Optimization

[D. Hugh Redelmeier]

| From: Lennart Sorensen <lsorense-1wCw9BSqJbv44Nm34jS7GywD8/FfD2ys at public.gmane.org>

| > EPIC (think: itanium) may eventually turn out to be important.  The 
| > workshop looks interesting.
| 
| How so?  Microsoft has just announced there won't be any future windows
| versions for it.  About 2/3 of itanium boxes run HP-UX or other HP unix,
| and about 1/3 run linux.  Less than 5% run windows, and hence counts as
| nearly none given the total number of itanium boxes out there.  I just
| don't see how it could ever become important.

As I read it, this is not just about iTanium.  "Eighth Workshop on
Explicitly Parallel Instruction Computing Architectures and Compiler
Technology (EPIC-8)".  Note the plural "Architectures".

I don't know how they define EPIC.  Some say it is a synonym for
Itanium, but then again, other architectures claim to be EPIC too (eg.
recent Elbrus architectures).

To me it is VLIW (quite interesting) plus a bunch of additional
features to try to make this practical.

I don't deeply understand the Itanium's problems.  I've heard or made
up many plausible explanations but they may not be right.

- Intel spent all its energy on x86, its bread and butter (see
  Christensen's "The Innovator's Dilemma" for an explanation of why
  this is to be expected)

- static scheduling is really hard when cached memory systems are
  very effective but each reference's time is very hard to predict.
  Some workloads could be tractable (eg. linear algebra).

- memory bandwidth is the main barrier; perhaps the organization of the
  processor is not that important.

- I think that VLIW has poor code-density.  Not just because of the
  size of instructions but also VLIW optimization techniques such as
  trace scheduling.

- VLIW seems a poor match for the kind of code I usually write: short
  basic blocks and lots of them.

I think that the case against VLIW and EPIC is not yet proven.
--
The Toronto Linux Users Group.      Meetings: http://gtalug.org/
TLUG requests: Linux topics, No HTML, wrap text below 80 columns
How to UNSUBSCRIBE: http://gtalug.org/wiki/Mailing_lists