Return to the
comp.compilers page.
Search the
comp.compilers archives again.
| Related articles |
|---|
| Register Files storm@binkley.cs.mcgill.ca (1992-10-05) |
| Re: Register Files preston@helena.cs.rice.edu (1992-10-05) |
| Re: Register Files ssimmons@convex.com (1992-10-06) |
| Re: Register Files cliffc@cs.rice.edu (1992-10-06) |
| Re: Register Files hobbs@steven.enet.dec.com (1992-10-06) |
| Re: Register Files kendall@centerline.com (1992-10-07) |
| Re: Register Files bart@cs.uoregon.edu (1992-10-07) |
| Re: Register Files henry@zoo.toronto.edu (1992-10-07) |
| Re: Register Files ali@LARK.WARP.CS.CMU.EDU (Ali-Reza Adl-Tabatabai) (1992-10-22) |
| [1 later articles] |
| Newsgroups: | comp.compilers |
| From: | ssimmons@convex.com (Steve Simmons) |
| Organization: | Engineering, CONVEX Computer Corp., Richardson, Tx., USA |
| Date: | Tue, 6 Oct 1992 12:35:51 GMT |
| Keywords: | registers |
>[why did DEC compiler writers care if Alpha has combined or separate
>integer and FP registers?]
This is not uncommon.... They were trying to separate the contention for
different functional units. Since the CPU can write (or read) to (or
from) only one register file on a cycle, having both floating point and
integers gprs in the same register file would prohibit simultaneous
execution of both floating point and integer operations.
Separating these two register files allows the CPU to execute floating pt
and integer instructions simultaneously. After all, the floating pointer
arithmetic unit and integer arithmetic unit are already different
functional units. Therefore, they can fetch, decode and execute both an
integer and a floating point instruction on the same cycles.
Be careful about some of the hype in the marketing literature. The Intel
i860 has been doing that for 4 years now.
Thank you.
Steve Simmons
--
Return to the
comp.compilers page.
Search the
comp.compilers archives again.