Re: pdp11/84 PMI memory: What is the problem with Q bus?
> I actually have -B/-C boards, I should plug one in in QBUS mode, and get my > QSIC prototype working again (it somehow random failed during the last year, > and I've been too lazy to debug it), and write a little program to DMA blocks > in and out, and see what happens to the data. If I get really energetic I > could throw a 'scope on the bus and look at bus cycles and see if they look > OK. > > It would be interesting to have some more detail on the failure. > > Noel Noel, The experiments you describe above would be very interesting! In the accidental tests I did using -C boards in an 11/83, RSX booted ok and ran for a good bit but I think errors Started to accumulate due to bad DMA writes that either were written to the wrong logical block Or the data written was scrambled. When this happened on my BA23 11/83 I scratched my head Took the boards to a BA123 11/83 and repeated the mistake. Fortunately I use two SCSI2SD devices In each system and leave one identical unit unmounted except during disk to disk backups. With good memory boards I was able to do a disk to disk restore and recover everything up to My last backup. > And that might make sense: PMI memory responds to the Q bus just like > normal memory. So from a Q bus device perspective it's just boring old > memory and thus no speed improvement. What might speed up is if I did > memory to memory (VM0:) copies, but with only 2mb running at the moment > there's not a lot of time to check for performance differences. Chris, I think the way that you see the biggest performance improvements in PMI over Q22 memory Is when you have heavy asynchronous I/O happening at the same time the CPU is compute bound And the memory access is not well cached due to the type of programs being run. This is more Likely to happen in a busy multi-user environment. RSX has a tool IOX that was developed to load a RSX system and simulate multiple users. The CPU can get at memory via the PMI and not be delayed Waiting on the Q22 bus. This is particularly helpful with larger block mode Q22 transfers that don’t cause CPU memory access delays. Mark
Re: pdp11/84 PMI memory: What is the problem with Q bus?
Oh, right. Still, it sounds from reports here like regular DMA doesn't work in QBUS mode either - and technically that table entry might mean than since it doesn't work for the QBUS _at all_, that includes no block mode. Regular Q bus DMA seems to be working fine. I can see the performance difference pretty easily when looking at 1,2,4,8,16 word transfers, anything else I should be checking? I actually have -B/-C boards, I should plug one in in QBUS mode, and get my QSIC prototype working again (it somehow random failed during the last year, and I've been too lazy to debug it), and write a little program to DMA blocks in and out, and see what happens to the data. If I get really energetic I could throw a 'scope on the bus and look at bus cycles and see if they look OK. I can also bring up an RL02 with the RLV12 (also does DMA) and see how an authentic DEC appliance works with this memory card. But really I'm not seeing any speed increase of PMI memory vs. non-PMI memory with the exception that the initial memory check runs a good bit faster with PMI over without. And that might make sense: PMI memory responds to the Q bus just like normal memory. So from a Q bus device perspective it's just boring old memory and thus no speed improvement. What might speed up is if I did memory to memory (VM0:) copies, but with only 2mb running at the moment there's not a lot of time to check for performance differences. Maybe it can't properly handle things like 18 bit DMA cards like the RXV12. Let's find out: What's the worst that can happen?
Re: pdp11/84 PMI memory: What is the problem with Q bus?
> From: Jerry Weiss > Sorry about the uNOTE confusion.. No problem, it only took me about a minute to find the right one; my note was to warn other people who didn't know about the number duplication. > If you look at the Memory Comparison table in this OEM uNOTE, it only > lists Block Mode for "JD/JE ONLY". Oh, right. Still, it sounds from reports here like regular DMA doesn't work in QBUS mode either - and technically that table entry might mean than since it doesn't work for the QBUS _at all_, that includes no block mode. I actually have -B/-C boards, I should plug one in in QBUS mode, and get my QSIC prototype working again (it somehow random failed during the last year, and I've been too lazy to debug it), and write a little program to DMA blocks in and out, and see what happens to the data. If I get really energetic I could throw a 'scope on the bus and look at bus cycles and see if they look OK. It would be interesting to have some more detail on the failure. Noel
Re: pdp11/84 PMI memory: What is the problem with Q bus?
Sorry about the uNOTE confusion... I was focused and just used the reference from the OEM version. I was aware but had mentally excluded the older Microcomputer Products Group/Components Group version. If you look at the Memory Comparison table in this OEM uNOTE, it only lists Block Mode for "JD/JE ONLY". Hence my comment about it not being on the JB/JC. Jerry On 4/24/20 11:23 AM, Noel Chiappa via cctalk wrote: > From: Jerry Weiss > uNOTE # 028 indicates that MSV-11 JB/JC (M8637-B/C) doesn't do block > mode. I went and looked at uNOTE #28, after I found it (it's not in the initial set of uNOTEs, but in the second set - the so-called 'OEM uNOTEs"; note that the numbers were re-used between the two sets, so there are _two different_ uNOTE #28's). I couldn't find anything there about the JB/JC not doing block mode? All it says is they "can not be used in a Q-BUS system due to gate array incompatibilities". Noel
Re: pdp11/84 PMI memory: What is the problem with Q bus?
> From: Chris Zach > Just checked the configuration and block mode DMA *is* off. Interesting. So it's not bklock-mode on the QBUS which is screwed up, but normal QBUS transfers. That jibes with the comment abour "gate array incompatibilities" (which I take to mean "errors" :-). > was the 11/70's MASSBUS channels nothing more than RH11-C's attached to > the old FASTBUS on the 11/45 cpu core (which is what an 11/70 really > is, with cache) or did they port right to the memory box? RH70's are totally different from RH11's - a hex card, and a couple of quads - and the interface to the /70's memory system is totally different from the RH11's (which goes to the UNIBUS): https://gunkies.org/wiki/RH70_MASSBUS_controller It has interfaces to both the cache, and the memory bus (although the diagram in the 11/70 CPU handbook shows it as only connected to the cache). I didn't follow the "the old FASTBUS on the 11/45 cpu core (which is what an 11/70 really is, with cache)"; the 70's cache is what's connected to what used to be the FASTBUS, the memory bus connects to the cache, IIRC. Noel
Re: pdp11/84 PMI memory: What is the problem with Q bus?
> From: Jerry Weiss > uNOTE # 028 indicates that MSV-11 JB/JC (M8637-B/C) doesn't do block > mode. I went and looked at uNOTE #28, after I found it (it's not in the initial set of uNOTEs, but in the second set - the so-called 'OEM uNOTEs"; note that the numbers were re-used between the two sets, so there are _two different_ uNOTE #28's). I couldn't find anything there about the JB/JC not doing block mode? All it says is they "can not be used in a Q-BUS system due to gate array incompatibilities". Noel
Re: pdp11/84 PMI memory: What is the problem with Q bus?
Oh I'm using an MTI MQD13 card as my disk controller. It is a MCSP controller that can interface up to 4 ESDI drives to Q Bus. Pretty fast. Just checked the configuration and block mode DMA *is* off. Wonder what happens if I turn it on... It does have a lot of knobs to fiddle with, so maybe I can figure out what works and what does not for these memory boards. Experimentation! C DMA CHARACTERISTICS: DRIVE 2... ESDI BLOCKMODE OFFFIRST LOGICAL.. 002 BURST LENGTH (WORDS). 16SECOND LOGICAL. 006 THROTTLE. ON DRIVE 3... ESDI DWELL us. 1.6 FIRST LOGICAL.. 003 SECOND LOGICAL. 007 SEEK MODE OVERLAPPED SEEK OPTIMIZATION ELEVATOR COMMAND QUEUE.. 008 FAIRNESS VALUE... 016 On 4/23/2020 1:17 AM, Mark Matlock via cctech wrote: Date: Tue, 21 Apr 2020 16:17:07 -0400 From: Chris Zach To:cctalk@classiccmp.org Subject: Re: pdp11/84 PMI memory: What is the problem with Q bus? Message-ID:<27647f0e-19d4-b484-d288-e9f3bb715...@alembic.crystel.com> Content-Type: text/plain; charset=utf-8; format=flowed Thanks Mark! Actually this was just the boards from the 11/84 (no idea what happened to the chassis, drat) so it's an 11/84 CPU (18mhz, FPP chip installed), 2 PMI boards (one old 2mb, one new 1mb) a console board of some sort and the Unibus map. I popped this into my BA23 to speed things up a bit in place of my quad height 11/73 CPU with 2mb memory. So far it seems to work, and with the CA memory in the PMI slot managed to boot RSX11M 4.2 and compile up EMPIRE. Chris, I understand now. I also have a PDP-11/83 in a BA123 box and the CPU and PMI memory (M8637-E) can move from the Qbus box to the 11/84 box and work fine In either. I spent a good bit of time tinkering with the 11/84 power supply which did not Work until I put a M7556 minimum load module in it. Basically the ± 12 Volts needs a Load or you get a hung bus error. Also, with the Unibus you have to pay attention to The NPR/NPG grant jumpers. For disks on the QBus systems I used the UC07 and SCSI2SD. The UC07 can be can be configured for block mode transfers and I think it is doing it. I guess I’d need to hook up a logic analyzer to know for sure. The 11/84 uses a UniBone and when it is emulating a MSCP disk, it can do 150 I/Os a second (using IOX on RSX11M+) The 11/83 using the UC07 and a SCSI2SD Does about 60 I/Os per second. I think the UC07 could go faster but is limited by the SDcard interface. I need to put a fast real SCSI disk on it sometime and see what it can do.
Re: pdp11/84 PMI memory: What is the problem with Q bus?
Well I turned on block mode DMA on my MTI controller, booted RT11 5.5, did an init on VM0: and tried to copy a .dsk file of 2500 blocks in size with 2mb of PMI memory from an 11/84 (CA, bad memory for Q Bus). First time was not good: .copy dungeo.dsk vm: Files copied: ?PIP-F-Input error DK:DUNGEO.DSK .dir dungeo.dsk DUNGEO.DSK 2500P 1 Files, 2500 Blocks 34488 Free blocks Second time was better, took ~4 seconds. .copy dungeo.dsk vm: Files copied: DK:DUNGEO.DSK to VM:DUNGEO.DSK Switched off block mode and tried again: Takes 5 seconds. Changed burst length from 16 words to 2: Took 25 seconds. 4: 23 seconds 16: 5 seconds Turning off the throttle mode (which requires Block mode and 16 word transfers) and it took 4 seconds. No speed increase. Then I decided to try using 2mb of crummy Q bus memory: 16: 5 seconds 8: 15 seconds 2: 26 seconds Didn't do 4. So it looks like what really speeds things up is having a large burst of Q busy transfers, going from 2 word transfers to 16 speeds things up by a factor of five. Makes sense, controller is spending less time setting up the transfer. Somewhat interesting that PMI doesn't really help, I understand that the controller is talking to PMI at normal Q bus speeds, but I would expect something for the CPU to manage the VM: driver. Unless the CPU just says "Oh, VM:? Point your data right into memory and be done with it". Moral: PMI memory does not really speed up disk to memory performance. Good to know. Anyone know a good benchmark to see if PMI is worth anything in terms of performance? Maybe the unibus map interfacing directly to PMI speeds things up a lot by allowing full hog mode DMA (which in theory could mean that an 11/84 could run a RH11-C controller and keep up with disks like the RM02 and RM05) Thinking along those lines, was the 11/70's MASSBUS channels nothing more than RH11-C's attached to the old FASTBUS on the 11/45 cpu core (which is what an 11/70 really is, with cache) or did they port right to the memory box? C
Re: pdp11/84 PMI memory: What is the problem with Q bus?
> Date: Tue, 21 Apr 2020 16:17:07 -0400 > From: Chris Zach > To: cctalk@classiccmp.org > Subject: Re: pdp11/84 PMI memory: What is the problem with Q bus? > Message-ID: <27647f0e-19d4-b484-d288-e9f3bb715...@alembic.crystel.com> > Content-Type: text/plain; charset=utf-8; format=flowed > > Thanks Mark! Actually this was just the boards from the 11/84 (no idea > what happened to the chassis, drat) so it's an 11/84 CPU (18mhz, FPP > chip installed), 2 PMI boards (one old 2mb, one new 1mb) a console board > of some sort and the Unibus map. > > I popped this into my BA23 to speed things up a bit in place of my quad > height 11/73 CPU with 2mb memory. So far it seems to work, and with the > CA memory in the PMI slot managed to boot RSX11M 4.2 and compile up EMPIRE. Chris, I understand now. I also have a PDP-11/83 in a BA123 box and the CPU and PMI memory (M8637-E) can move from the Qbus box to the 11/84 box and work fine In either. I spent a good bit of time tinkering with the 11/84 power supply which did not Work until I put a M7556 minimum load module in it. Basically the +/- 12 Volts needs a Load or you get a hung bus error. Also, with the Unibus you have to pay attention to The NPR/NPG grant jumpers. For disks on the QBus systems I used the UC07 and SCSI2SD. The UC07 can be can be configured for block mode transfers and I think it is doing it. I guess I’d need to hook up a logic analyzer to know for sure. The 11/84 uses a UniBone and when it is emulating a MSCP disk, it can do 150 I/Os a second (using IOX on RSX11M+) The 11/83 using the UC07 and a SCSI2SD Does about 60 I/Os per second. I think the UC07 could go faster but is limited by the SDcard interface. I need to put a fast real SCSI disk on it sometime and see what it can do. > > My guess is the 11/84's Unibus talks directly to the PMI bus and > orchestrates the data transfers, but there is something wrong when the > PMI memory is accessed on the true Q bus. That would not happen on an > 11/84 (CPU and Map use PMI only) but when you have a Q bus DMA device it > probably manifests at random. It's possible the MTI card is throttling > the DMA to single mode instead of hog mode, wonder if I want to screw up > my disk to verify this…. What is the model # for your MTI disk controller? > > Drat. On the positive side it's chock full of 256k chips, which I could > pull off and put on the EA board to bring it up to 2mb memory. I have > air heat tools and a pre-heater so getting the chips off should be > pretty basic. Getting them on the new board though could be a pain since > all the holes are soldered over…. Moving the RAM chips sounds a bit tedious but would certainly be possible. > > No way to reprogram or fix it I assume? Are you asking about making the M8637-B or -C into the -D or -E? If so I’ve never seen any reference to doing that. I was very fortunate that the person Who sold me the M8637-C was willing to trade it for a -E. Mark
Re: pdp11/84 PMI memory: What is the problem with Q bus?
So whatever the fault is (perhaps the QBUS block transfer issue reported up-thread), it must _seem_ to work, but fail in actuality. It would be interesting to appply a logic analyzer, and see what the bus transaction looks like, if it looks OK on the bus (in which case it's an internal failure). One possibility is that it's not handling multiple DMA devices talking at the same time or calling to arbitrate the bus. Right now I have an RL02 controller and the MTI controller but the RL02's are powered down. I'll see if I can run it for a bit on RSX11M and get it to fault (and backup my disk first as it's nice to have it working again). C
re: pdp11/84 PMI memory: What is the problem with Q bus?
> From: Mark Matlock > Are you able to use a Qbus MTI controller in the 11/84's Qbus section > of the backplane? This is something I've often wondered about but never > tried. I looked into this in some detail, but I don't know: https://gunkies.org/wiki/KTJ11-B_UNIBUS_adapter#QBUS_slots Amswering it definitively would probably require looking at DMA and interrupt cycles with a logic analyzer on the bus, to see what the CPU does with them. And the KDJ11-B and KDJ11-E (the 11/94 uses the same bacplane with a different CPU card) might act differently. > For anyone who is curious about what Happens when a M8637-C version > board is used as PMI memory in an 11/83 I can speak From experience. > ... > After this the disk is corrupted and you will need to restore the > system disk from backups Ah, very informative; thanks for reporting. So whatever the fault is (perhaps the QBUS block transfer issue reported up-thread), it must _seem_ to work, but fail in actuality. It would be interesting to appply a logic analyzer, and see what the bus transaction looks like, if it looks OK on the bus (in which case it's an internal failure). Noel
re: pdp11/84 PMI memory: What is the problem with Q bus?
> From: Chris Zach > in place of my quad height 11/73 CPU with 2mb memory. Sorry, which exact quad-height CPU card? {As someone else has previously pointed out, the /73 and the /83 are basially the same machine (roughly the same CPU board - KDJ11-B, perhaps with different clock crystals), just with different memories - QBUS in the /73, PMI in the /83. The /84 is an /83 with i) a different backplane and ii) a KTJ11-B UNIBUS adapter.} > On the positive side it's chock full of 256k chips, which I could pull > off and put on the EA board to bring it up to 2mb memory. I have air > heat tools and a pre-heater so getting the chips off should be pretty > basic. I would advise against that. 256K chips are readily available on eBait, and for not much money. Pulling them may damage them, and may well also do some damage to the memory card, in addition to making it useless. > Getting them on the new board though could be a pain since all the > holes are soldered over A vacuum desoldering station will easily open them. Used Hakkos can be found on eBait for not too much money. Noel
Re: pdp11/84 PMI memory: What is the problem with Q bus?
Thanks Mark! Actually this was just the boards from the 11/84 (no idea what happened to the chassis, drat) so it's an 11/84 CPU (18mhz, FPP chip installed), 2 PMI boards (one old 2mb, one new 1mb) a console board of some sort and the Unibus map. I popped this into my BA23 to speed things up a bit in place of my quad height 11/73 CPU with 2mb memory. So far it seems to work, and with the CA memory in the PMI slot managed to boot RSX11M 4.2 and compile up EMPIRE. My guess is the 11/84's Unibus talks directly to the PMI bus and orchestrates the data transfers, but there is something wrong when the PMI memory is accessed on the true Q bus. That would not happen on an 11/84 (CPU and Map use PMI only) but when you have a Q bus DMA device it probably manifests at random. It's possible the MTI card is throttling the DMA to single mode instead of hog mode, wonder if I want to screw up my disk to verify this Drat. On the positive side it's chock full of 256k chips, which I could pull off and put on the EA board to bring it up to 2mb memory. I have air heat tools and a pre-heater so getting the chips off should be pretty basic. Getting them on the new board though could be a pain since all the holes are soldered over No way to reprogram or fix it I assume? C On 4/21/2020 11:48 AM, Mark Matlock via cctalk wrote: Date: Sun, 19 Apr 2020 15:29:44 -0400 From: Chris Zach To: CCTalk mailing list Subject: pdp11/84 PMI memory: What is the problem with Q bus? Message-ID: <3efa4105-3d3d-bb98-0358-8c46fca0f...@alembic.crystel.com> Content-Type: text/plain; charset=utf-8; format=flowed So I picked up an 11/84 CPU, 3mb of memory, and a 11/84 Unibus card on Ebay. Goal is to speed up my fastest 11 here For boot time, the diagnostics run in 13 seconds (from when it starts to prompt) on the 11/73 board I have and 13 seconds on the 11/84 board. This is with a camintonn 2mb half height memory board. Put in the first PMI module above the 11/84 CPU and tried it out. This is a CA rev board which apparently only works in a Unibus pdp11 and not a Q-bus one. Apparently it does work. So what exactly was the bug with the older PMI memory? Block mode DMA, I'm using an MTI ESDI controller which can do 16 word block DMA on Q Bus. Something else? Chris, Congrats on the PDP-11/84! I also have a PDP-11/84 that uses one of Joerg’s Hoppe’s UniBone devices to simultaneously emulate MSCP disks, RL02 disks (including the RL02 Load/Ready/WriteProtect/ and fault lights) and a DL11. I have a question about something you said above, that you are using a MTI ESDI disk controller and then you mention Qbus block mode DMA. Are you able to use a Qbus MTI controller in the 11/84’s Qbus section of the backplane? This is something I’ve often wondered about but never tried. Also, you mention putting the PMI memory above the 11/84 CPU. In the 11/83 Qbus backplane this is of course determines whether the M8637 memory is accessed via Q22 or PMI. In the 11/84 System Maintenance Guide Figure 2-8 shows the CPU card above the memory which if you were to do this in the 11/83 would mean that the memory will be accessed via Q22 and essentially become an 11/73. In my 11/83 I have run both configurations to understand and measure the benefit of PMI. As has been mentioned the 11/84 can use any of the M8637 memory boards but the 11/83 can only use the M8637-D or -E versions. For anyone who is curious about what Happens when a M8637-C version board is used as PMI memory in an 11/83 I can speak From experience. This was running RSX11M+ and it boots fine but after a few minutes if The system is active, the console starts to report that various installed tasks are corrupted And the system will XDT a bit later. After this the disk is corrupted and you will need to restore the system disk from backups after you get the correct PMI memory boards. I’m not completely sure how the write DMA operations put bad data through the disk controller (I was using an Emulex UC07 with a SCSI2SD) into the disks but that is what happens. Mark Matlock
pdp11/84 PMI memory: What is the problem with Q bus?
> > Date: Sun, 19 Apr 2020 15:29:44 -0400 > From: Chris Zach > To: CCTalk mailing list > Subject: pdp11/84 PMI memory: What is the problem with Q bus? > Message-ID: <3efa4105-3d3d-bb98-0358-8c46fca0f...@alembic.crystel.com> > Content-Type: text/plain; charset=utf-8; format=flowed > > So I picked up an 11/84 CPU, 3mb of memory, and a 11/84 Unibus card on > Ebay. Goal is to speed up my fastest 11 here > > For boot time, the diagnostics run in 13 seconds (from when it starts to > prompt) on the 11/73 board I have and 13 seconds on the 11/84 board. > This is with a camintonn 2mb half height memory board. > > Put in the first PMI module above the 11/84 CPU and tried it out. This > is a CA rev board which apparently only works in a Unibus pdp11 and not > a Q-bus one. Apparently it does work. > > So what exactly was the bug with the older PMI memory? Block mode DMA, > I'm using an MTI ESDI controller which can do 16 word block DMA on Q > Bus. Something else? Chris, Congrats on the PDP-11/84! I also have a PDP-11/84 that uses one of Joerg’s Hoppe’s UniBone devices to simultaneously emulate MSCP disks, RL02 disks (including the RL02 Load/Ready/WriteProtect/ and fault lights) and a DL11. I have a question about something you said above, that you are using a MTI ESDI disk controller and then you mention Qbus block mode DMA. Are you able to use a Qbus MTI controller in the 11/84’s Qbus section of the backplane? This is something I’ve often wondered about but never tried. Also, you mention putting the PMI memory above the 11/84 CPU. In the 11/83 Qbus backplane this is of course determines whether the M8637 memory is accessed via Q22 or PMI. In the 11/84 System Maintenance Guide Figure 2-8 shows the CPU card above the memory which if you were to do this in the 11/83 would mean that the memory will be accessed via Q22 and essentially become an 11/73. In my 11/83 I have run both configurations to understand and measure the benefit of PMI. As has been mentioned the 11/84 can use any of the M8637 memory boards but the 11/83 can only use the M8637-D or -E versions. For anyone who is curious about what Happens when a M8637-C version board is used as PMI memory in an 11/83 I can speak From experience. This was running RSX11M+ and it boots fine but after a few minutes if The system is active, the console starts to report that various installed tasks are corrupted And the system will XDT a bit later. After this the disk is corrupted and you will need to restore the system disk from backups after you get the correct PMI memory boards. I’m not completely sure how the write DMA operations put bad data through the disk controller (I was using an Emulex UC07 with a SCSI2SD) into the disks but that is what happens. Mark Matlock
RE: pdp11/84 PMI memory: What is the problem with Q bus?
> Date: Sun, 19 Apr 2020 15:29:44 -0400 > From: Chris Zach > To: CCTalk mailing list > Subject: pdp11/84 PMI memory: What is the problem with Q bus? > Message-ID: <3efa4105-3d3d-bb98-0358-8c46fca0f...@alembic.crystel.com> > Content-Type: text/plain; charset=utf-8; format=flowed > > So I picked up an 11/84 CPU, 3mb of memory, and a 11/84 Unibus card on > Ebay. Goal is to speed up my fastest 11 here > > For boot time, the diagnostics run in 13 seconds (from when it starts to > prompt) on the 11/73 board I have and 13 seconds on the 11/84 board. > This is with a camintonn 2mb half height memory board. > > Put in the first PMI module above the 11/84 CPU and tried it out. This > is a CA rev board which apparently only works in a Unibus pdp11 and not > a Q-bus one. Apparently it does work. > > So what exactly was the bug with the older PMI memory? Block mode DMA, > I'm using an MTI ESDI controller which can do 16 word block DMA on Q > Bus. Something else? Chris, Congrats on the PDP-11/84! I also have a PDP-11/84 that uses one of Joerg’s Hoppe’s UniBone devices to simultaneously emulate MSCP disks, RL02 disks (including the RL02 Load/Ready/WriteProtect/ and fault lights) and a DL11. I have a question about something you said above, that you are using a MTI ESDI disk controller and then you mention Qbus block mode DMA. Are you able to use a Qbus MTI controller in the 11/84’s Qbus section of the backplane? This is something I’ve often wondered about but never tried. Also, you mention putting the PMI memory above the 11/84 CPU. In the 11/83 Qbus backplane this is of course determines whether the M8637 memory is accessed via Q22 or PMI. In the 11/84 System Maintenance Guide Figure 2-8 shows the CPU card above the memory which if you were to do this in the 11/83 would mean that the memory will be accessed via Q22 and essentially become an 11/73. In my 11/83 I have run both configurations to understand and measure the benefit of PMI. As has been mentioned the 11/84 can use any of the M8637 memory boards but the 11/83 can only use the M8637-D or -E versions. For anyone who is curious about what Happens when a M8637-C version board is used as PMI memory in an 11/83 I can speak From experience. This was running RSX11M+ and it boots fine but after a few minutes if The system is active, the console starts to report that various installed tasks are corrupted And the system will XDT a bit later. After this the disk is corrupted and you will need to restore the system disk from backups after you get the correct PMI memory boards. I’m not completely sure how the write DMA operations put bad data through the disk controller (I was using an Emulex UC07 with a SCSI2SD) into the disks but that is what happens. Mark Matlock
Re: pdp11/84 PMI memory: What is the problem with Q bus?
On 4/19/20 2:29 PM, Chris Zach via cctalk wrote: So I picked up an 11/84 CPU, 3mb of memory, and a 11/84 Unibus card on Ebay. Goal is to speed up my fastest 11 here For boot time, the diagnostics run in 13 seconds (from when it starts to prompt) on the 11/73 board I have and 13 seconds on the 11/84 board. This is with a camintonn 2mb half height memory board. Put in the first PMI module above the 11/84 CPU and tried it out. This is a CA rev board which apparently only works in a Unibus pdp11 and not a Q-bus one. Apparently it does work. So what exactly was the bug with the older PMI memory? Block mode DMA, I'm using an MTI ESDI controller which can do 16 word block DMA on Q Bus. Something else EK-MSV1J-UG 001 documents the the versions that don't do Q-Bus Cycles. uNOTE # 028 indicates that MSV-11 JB/JC (M8637-B/C) doesn't do block mode. I suspect the MTI card falls back to single cycle DMA. Also RT11 simply may not challenge the configuration sufficiently to demonstrate the limitations of the -CA memory variant. I have not seen any document that describes this as a "bug", so it must be a "feature" /s Jerry
pdp11/84 PMI memory: What is the problem with Q bus?
So I picked up an 11/84 CPU, 3mb of memory, and a 11/84 Unibus card on Ebay. Goal is to speed up my fastest 11 here For boot time, the diagnostics run in 13 seconds (from when it starts to prompt) on the 11/73 board I have and 13 seconds on the 11/84 board. This is with a camintonn 2mb half height memory board. Put in the first PMI module above the 11/84 CPU and tried it out. This is a CA rev board which apparently only works in a Unibus pdp11 and not a Q-bus one. Apparently it does work. So what exactly was the bug with the older PMI memory? Block mode DMA, I'm using an MTI ESDI controller which can do 16 word block DMA on Q Bus. Something else? Here's the output from RT11. .show all RT-11FB (S) V05.05 Booted from DU6:RT11FB USR is set SWAP EXITis set SWAP KMONis set NOIND TT is set NOQUIET ERROR is set ERROR SL is set OFF EDITis set KED FORTRAN is set FORTRA KMON nesting depth is 3 Global .SCCA flag is disabled PDP 11/83 Processor 2048KB of memory Floating Point Accelerator Unit Extended Instruction Set (EIS) Memory Management Unit ECC Memory Cache Memory PMI Memory 60 Cycle System Clock Device I/O time-out support Error logging support Memory parity support System job support Global .SCCA support FPU support Extended unit support DeviceStatus CSR Vector(s) ---- --- - EL Not installed 00 000 LD Installed 00 000 BA Installed 00 000 DY Not installed 177170 264 VM Installed 177572 250 SP Installed 00 110 XL Not installed 176500 300 304 DL Installed 174400 160 MS Not installed 172522 224 DU Resident172150 154 LS Not installed 176510 310 314 NL Installed 00 000 TT (Resident) DU (Resident) DU6 = DK , SY MQ (Resident) LD DL VM SP BA NL 9 free slots Job Name Console Level StateLowHigh Impure --- --- - ---- -- 0 RESORC 0 0 Run 00 103232 105046 No multi-terminal support Address ModuleWords --- --- 16IOPAGE 4096. 132174DU 5570. 103274RMON 5856. 001000..BG..16990. LD0 is DU6:RTTST.DSK[6000.]