home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.sys.intel:2791 comp.arch:11802
- Path: sparky!uunet!spool.mu.edu!uwm.edu!cs.utexas.edu!sun-barr!news2me.EBay.Sun.COM!exodus.Eng.Sun.COM!brahmand.Eng.Sun.COM!grover
- From: grover@brahmand.Eng.Sun.COM (Vinod Grover)
- Newsgroups: comp.sys.intel,comp.arch
- Subject: Re: Superscalar vs. multiple CPUs ?
- Date: 20 Dec 1992 16:18:21 GMT
- Organization: Sun
- Lines: 34
- Message-ID: <lj976dINNg4d@exodus.Eng.Sun.COM>
- References: <PCG.92Dec9154602@aberdb.aber.ac.uk> <1992Dec12.152224.168173@zeus.calpoly.edu> <PCG.92Dec19165907@decb.aber.ac.uk>
- NNTP-Posting-Host: brahmand
-
- In article <PCG.92Dec19165907@decb.aber.ac.uk> pcg@aber.ac.uk (Piercarlo Grandi) writes:
- >As far as I have read and seen with my eyes, let me insist, most
- >"general purpose" codes have limited degrees of exploitable micro/macro
- >parallelism, say 2 to 4. The underlying reason is that most such codes
- >are about is serial tree/graph walking/updating.
-
- I suggest you read the Butler et. al. paper cited [1] earlier by someone
- in this thread. These authors claim that on an unrestricted data flow
- machine, *general purpose* codes like gcc, li, eqntott, (taken from
- SPEC89) have pretty high degree of parallelisms in them. Measured in
- terms of IPC:
-
- gcc - 38
- espresso - 179
- eqntott - 300
- li - 162
-
- Judging from these claims, the issue is not how much parallelism there
- is but how cost-effective is it to extract it. As CPU resources
- approach realistic values the sustainable issue rates on these codes
- fall dramatically, (2-4). These are limits imposed by the
- hardware/compilers.
-
-
- Vinod Grover
-
- -not speaking for Sun.
-
-
- [1] Butler, Yeh, Patt, Alsup, Scales, Shebanow, "Single Instruction
- Stream Parallelism is Greater than Two", Intnl. Symp. on Comp. Arch
- 1991.
-
-
-