home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!ogicse!flop.ENGR.ORST.EDU!gaia.ucs.orst.edu!umn.edu!msus1.msus.edu!msus1.msus.edu!news
- From: lkoop@TIGGER.STCLOUD.MSUS.EDU (LaMonte Koop)
- Newsgroups: comp.sys.amiga.hardware
- Subject: Re: Chip RAM extremely slow with GVP A530
- Message-ID: <1993Jan27.010254.2209@msus1.msus.edu>
- Date: 26 Jan 93 19:02:54 GMT
- Article-I.D.: msus1.1993Jan27.010254.2209
- References: <93024.073149PATROL@ACI.CVUT.CS>
- Reply-To: lkoop@TIGGER.STCLOUD.MSUS.EDU
- Organization: SCS GP/Engineering Cluster
- Lines: 53
- Nntp-Posting-Host: tigger.stcloud.msus.edu
-
- In article <93024.073149PATROL@ACI.CVUT.CS>, Pavel Troller <PATROL@ACI.CVUT.CS> writes:
- >Hi netters,
- > I bought a new A530 Turbo Harddisk last week. Suddenly it is fitted
- >only with a 1Meg of 32bit RAM, because my local dealer hasn't expansion SIMMS
- >stock. Formerly I had GVP Series 2 Harddisk with 4Megs of expansion RAM, so
- >my system has relatively expensive memory requirements. First time I booted,
- >I tried SysInfo to show me the wonder, but I was surprised: 0.78 of standard
- >A500, 0.30 Chip vs A3000.
- > I wrote a short program in assembler, which simply counts to zero from
- >$1000000 and then returns. Its results are shown:
- > Memory Type Inst Cache Status Time to run
- > 32bit Enabled 3.5 s
- > Chip Enabled 3.5 s
- > 32bit Disabled 9 s
- > Chip Disabled 120 s :-(
- > With motherboard CPU:
- > Chip not available 49 s
- >
- > I know that with asynchronous bus operations there is a need to syn-
- >chronize bus cycles of 40Mhz '030 with 7Mhz of motherboard; but I didn't
- >supposed that it will be so drastic. It also means that without the basic
- >1Meg of 32bit RAM the system is unusable!
-
- Well, what you've run into is a charateristic of all the Motorola 680x0
- series processors from the 68020 on. The primary figure you are concerned
- with above (as it seems) is the timing you received from your test when you
- ran it with only CHIP memory available, with the 68030 instruction cache off.
- The results you see are fairly typical given that kind of setup. Here's why:
- The 68020, 68030, and 68040 always prefetch instructions using 32-bit read
- cycles. Since the A500 motherboard bus is a 16-bit port to the 68030 on your
- accelerator, essentially 2 memory read cycles must be accomplished for every
- instruction prefetch done. Right off the bat this gives you a 2x performance
- hit against a 68030 doing prefetches from a full 32-bit bus port. If you add
- to this the fact that, as you indicated, the reads are done asynchronously to
- a bus running a ~7.15 MHz, and the fact that you also have to deal with bus
- contention from the custom chip DMA on the CHIP RAM bus, you can easily see
- where performance drops into the ground in the case with the instruction
- cache disabled. Performance figures less than a system running the stock
- 68000 in this situation are not unexpected.
- When the instruction cache is enabled, it tends to somewhat buffer this
- effect and bring performance levels back up. Typically, do not expect better
- than a 1.5-2x performance enhancement over a stock A500 when only CHIP or
- 16-bit ported FAST RAM is available to the 68030 in this case. With a 32-bit
- ported RAM resource available to it, the 68030 is then not given the
- restrictions above, and this is the primary reason anyone with a 68020/030/040
- accelerator for an A500/600/2000 is well suited to acquire 32-bit ported memory
- expansion for it as well.
-
- ----------------------------------------
- LaMonte Koop -- SCSU Electrical/Computer Engineering
- Internet: lkoop@tigger.stcloud.msus.edu -OR- f00012@kanga.stcloud.msus.edu
- "You mean you want MORE lights on this thing???"
- ---------------------------------------------------------------------------
-