Shop OBEX P1 Docs P2 Docs Learn Events
HUB RAM interface question - Page 6 — Parallax Forums

HUB RAM interface question

1234689

Comments

  • @evanh said:

    @TonyB_ said:
    Evan, I think that is sysclk/3 for longs and burst = 3. The line with 1966xx is consistent and applies to sysclk/1.5 for longs.

    Oh, I see that data, 589824, is actually missing in newest runs. It has existed in previous runs of same config. I'm not yet sure how best to trigger worst case conditions.

    Do your tests have an initial random slice difference between streamer and fast block addresses? If so, I think it would be best to do eight tests with known slices differences of 0-7. Some slow times might occur for certain differences only.

  • TonyB_TonyB_ Posts: 2,178
    edited 2022-02-20 23:11

    @evanh said:

    @TonyB_ said:

    < Rev0 >< Rev1 >< Rev2 >< Rev3 >< Rev4 >< Rev5 >< Rev6 >< Rev7 >< Rev8 >    egg beater Revolutions
    012345670123456701234567012345670123456701234567012345670123456701234567    hub RAM slices
    ........................................................WWWWWWWW........    fast block Write
    .I........I........I........I........I........I........I........I.......    FIFO In
    O........O........O........O........O........O........O........O........    FIFO Out
    
    877777777877777777877777777877777777877777777877777777877777777877777777    FIFO unfilled longs
    < Rev0 >< Rev1 >< Rev2 >< Rev3 >< Rev4 >< Rev5 >< Rev6 >< Rev7 >< Rev8 >    egg beater Revolutions
    012345670123456701234567012345670123456701234567012345670123456701234567    hub RAM slices
    

    Ah, cool, hubRAM fetches spaced same 9 tick interval as streamer cycles. EDIT: Okay, not cool outcome, knocks the cog back every time.

    What is wrong with this? I'm not saying it's correct.

  • evanhevanh Posts: 15,915
    edited 2022-02-20 23:18

    @TonyB_ said:

    Oh, I see that data, 589824, is actually missing in newest runs. It has existed in previous runs of same config. I'm not yet sure how best to trigger worst case conditions.

    Do your tests have an initial random slice difference between streamer and fast block addresses? If so, I think it would be best to do eight tests with known slices differences of 0-7. Some slow times might occur for certain differences only.

    Doh! Of course, that was back with the streamer mode set wrong. It wasn't doing RFLONGs at all then. Okay, so worst case doesn't happen with LONG and divider index #3.

    Yeah, I used to have radomised FIFO start address and various pauses to shake up the timing. In the end an ordered change in FIFO start address was just as good and also repeatable.

  • evanhevanh Posts: 15,915

    @TonyB_ said:

    @evanh said:
    Ah, cool, hubRAM fetches spaced same 9 tick interval as streamer cycles. EDIT: Okay, not cool outcome, knocks the cog back every time.

    What is wrong with this? I'm not saying it's correct.

    Lol, I meant it shows the horror of how the FIFO doing that puts the cog in a pickle. That's not cool.

  • evanhevanh Posts: 15,915
    edited 2022-02-21 00:02

    Huh, I'm down to just index numbers of 3, 6, 9 and 18 as having that extreme worst case. I thought it was more ... I must have been counting the poor cases too. The earlier threshold checks in the extra final column was picking all the poor cases up too.

    Well, those few streamer dividers are easy enough avoided when used for stuff like comms. VGA auto calculated dividers might occasionally trip it though.

  • TonyB_TonyB_ Posts: 2,178
    edited 2024-01-08 18:01

    This is sysclk/9 for longs with burst = 6 and so FIFO reloads as soon as it can after it has six empty longs, which is how the P2 behaves when FIFO is operating correctly. Note that two cycles, marked as xx below, are wasted every burst because it is not eight.

    There is a repeating pattern every 27 revolutions. Of the 27 * 8 = 216 cycles, 216 / 9 = 24 are used to refill FIFO in 24 / 6 = 4 bursts with 4 * 2 = 8 cycles wasted, leaving 216 - 24 - 8 = 184 cycles for the fast move, which takes time T = (216 / 184) * N = 27N / 23 = 1.1739N cycles in total. For N = 65536, theoretical T = 76934 and actual measured T = 76936.

    < Rev0 >< Rev1 >< Rev2 >< Rev3 >< Rev4 >< Rev5 >< Rev6 >< Rev7 >< Rev8 >< Rev9 >< Rev10>< Rev11>< Rev12>< Rev13>< Rev14>< Rev15>< Rev16>< Rev17>< Rev18>< Rev19>< Rev20>< Rev21>< Rev22>< Rev23>< Rev24>< Rev25>< Rev26>    egg beater Revolutions
    012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567    hub RAM slices
    ..WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........  fast block Write
    xx..............................................IIIIIIxx..............................................IIIIIIxx..............................................IIIIIIxx..............................................IIIIIIxx  FIFO In
    O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O.  FIFO Out
    
    11111111122222222233333333344444444455555555566654321011111111122222222233333333344444444445555555556654321011111111122222222233333333344444444455555555566654321011111111122222222233333333344444444455555555566654321011  FIFO unfilled longs
    
  • Yeah nice packing density of hub access slots but we really want to see the case with the bad outcome. If the "O" position offset slides along relative to the burst write up to 9 slot positions, and the current address required by the FIFO does vary as well, perhaps we will hit the bad pattern somehow..., or do you think to make it happen will the FIFO need to not perform 6 transfers?

  • evanhevanh Posts: 15,915
    edited 2022-02-21 00:23

    Nice drawing Tony! The amount of space for the cog looks pleasing. Yeah, that's the fix Chip needs to do in a silicon re-spin - forcing FIFO hubRAM bursts to a minimum of 6.

  • evanhevanh Posts: 15,915
    edited 2022-02-21 01:09

    @rogloh said:
    ... or do you think to make it happen will the FIFO need to not perform 6 transfers?

    That's my take on it. If the refill burst is prevented from dropping below 6 then it'll naturally avoid the worst case.

    EDIT: It'll clean up the #5 cases too, even the BYTE line is poor there - https://forums.parallax.com/discussion/comment/1535820/#Comment_1535820

    Lbb = 8 / (10 * (1 - 65536 / 81920)) = 4
    Lbs = 8 / (5 * (1 - 65536 / 81920)) = 8
    Lbl = 8 / (2.5 * (1 - 65536 / 218448)) = 4.57
    
    Lbs = 8 / (5 * (1 - 65536 / 109224)) = 4
    Lbs = 8 / (5 * (1 - 65536 / 126040)) = 3.333
    

    There's lots more of other poor cases with bursts of 4 and 5.

  • evanhevanh Posts: 15,915
    edited 2022-02-21 06:17

    Uh-oh, umm, FIFO writes to hubRAM are not looking friendly at all. My guess is delayed writes aren't happening. I presume they're allowed but don't happen in practice. Measurements for BYTE lines are twice as bad as SHORT lines, which are in turn twice as bad as LONG lines. We're reaching up to 2 million ticks to SETQ2+WRLONG block write 64 kLW while streamer is also writing - for index 16 of all! That's 32 ticks per longword for the block write.

    PS: No change if the block write is changed to a block read with SETQ2+RDLONG.

  • Is there as much sensitivity to divisor this time with the FIFO writes vs reads?

  • evanhevanh Posts: 15,915
    edited 2022-02-21 06:23

    @rogloh said:
    Is there as much sensitivity to divisor this time with the FIFO writes vs reads?

    No, consistently Smile. Worse than the worst FIFO reads.
    EDIT: Well, after index 16 17, the effect also smoothly fades with higher dividers.

  • @evanh said:

    @rogloh said:
    Is there as much sensitivity to divisor this time with the FIFO writes vs reads?

    No, consistently Smile. Worse than the worst FIFO reads.
    EDIT: Well, after index 16 17, the effect also smoothly fades with higher dividers.

    Ok. We are kind of lucky then that the video driver uses the FIFO the other direction (out to pins), leaving us a lot of burst transfer bandwidth in parallel with streaming video pixel data.

  • TonyB_TonyB_ Posts: 2,178
    edited 2022-02-21 10:50

    @rogloh said:
    Yeah nice packing density of hub access slots but we really want to see the case with the bad outcome. If the "O" position offset slides along relative to the burst write up to 9 slot positions, and the current address required by the FIFO does vary as well, perhaps we will hit the bad pattern somehow..., or do you think to make it happen will the FIFO need to not perform 6 transfers?

    I showed the bad sysclk/9 for longs with T = 9N earlier with burst = 1, but this version by Evan is probably more likely:
    https://forums.parallax.com/discussion/comment/1535874/#Comment_1535874

    Note that in my good version,
    https://forums.parallax.com/discussion/comment/1535882/#Comment_1535882
    FIFO Input and Output have fixed phase difference, which is how it should be. The question mark is over fast block and FIFO address difference in bits [2:0].

  • TonyB_TonyB_ Posts: 2,178
    edited 2022-02-21 11:10

    @evanh said:
    Nice drawing Tony! The amount of space for the cog looks pleasing. Yeah, that's the fix Chip needs to do in a silicon re-spin - forcing FIFO hubRAM bursts to a minimum of 6.

    Burst = 6 minimum is how it works now, until it goes wrong. At higher streamer speeds there is at least one output during the input burst and so burst length increases. A fixed Burst = 8 would give best performance as there are no wasted cycles, but I haven't tested that on paper yet at very high speeds.

  • @evanh said:
    Uh-oh, umm, FIFO writes to hubRAM are not looking friendly at all. My guess is delayed writes aren't happening. I presume they're allowed but don't happen in practice. Measurements for BYTE lines are twice as bad as SHORT lines, which are in turn twice as bad as LONG lines. We're reaching up to 2 million ticks to SETQ2+WRLONG block write 64 kLW while streamer is also writing - for index 16 of all! That's 32 ticks per longword for the block write.

    PS: No change if the block write is changed to a block read with SETQ2+RDLONG.

    Conceptually, from the hub RAM's viewpoint, is there any difference between fast block read and FIFO read? If the answer is yes, why is fast block read worse than FIFO read? If no, why is FIFO write worse than fast block write?

  • evanhevanh Posts: 15,915

    @TonyB_ said:
    Conceptually, from the hub RAM's viewpoint, is there any difference between fast block read and FIFO read? If the answer is yes, why is fast block read worse than FIFO read? If no, why is FIFO write worse than fast block write?

    The biggie is priority. FIFO always gets the hubRAM access when it wants. Block read/write just has to fit around the FIFO.

  • @evanh said:

    @TonyB_ said:
    Conceptually, from the hub RAM's viewpoint, is there any difference between fast block read and FIFO read? If the answer is yes, why is fast block read worse than FIFO read? If no, why is FIFO write worse than fast block write?

    The biggie is priority. FIFO always gets the hubRAM access when it wants. Block read/write just has to fit around the FIFO.

    But the hub RAM doesn't know and doesn't care about priority.

  • evanhevanh Posts: 15,915
    edited 2022-02-21 12:06

    @TonyB_ said:
    Burst = 6 minimum is how it works now, until it goes wrong.

    Sort of. The "up to" and "potentially filling" in the silicon doc gives an out on that. And evidence is <6 does happen.

    QUOTE:
    The FIFO contains (cogs+11) stages. When in read mode, the FIFO loads continuously whenever less than (cogs+7) stages are filled, after which point, up to 5 more longs may stream in, potentially filling all (cogs+11) stages.

    @TonyB_ said:
    At higher streamer speeds there is at least one output during the input burst and so burst length increases.

    That's why it's good that -6 is the chosen low level. Gives greater coverage of cases that won't then unnecessarily spill beyond a burst of 8. Just has to also use 6 as the minimum burst length on top of being the low level.

    The distinction between low-level and minimum burst is where it diverges at the moment.

    PS: And FIFO writing to hubRAM also should get same features.

  • evanhevanh Posts: 15,915
    edited 2022-02-21 12:10

    @TonyB_ said:
    But the hub RAM doesn't know and doesn't care about priority.

    The FIFO and Streamer both are part of the Cog. Single shared bus to hubRAM for all. Priority is a cog level function.

  • TonyB_TonyB_ Posts: 2,178
    edited 2022-02-21 13:14

    @evanh said:
    Oh, reading the silicon doc:

    The FIFO contains (cogs+11) stages. When in read mode, the FIFO loads continuously whenever less than (cogs+7) stages are filled, after which point, up to 5 more longs may stream in, potentially filling all (cogs+11) stages. These metrics ensure that the FIFO never underflows, under all potential reading scenarios.

    If I'm reading that right, it is actually saying at least 6 longwords at a time. And maybe more if the flow rate is high. That's a nice improvement on the single longs I was thinking it might be.

    Reading this again, FIFO refilling can start when 14 stages are filled and 5 more longs can stream in filling all 19 stages. This is saying burst is 5 but mathematically we know it should be 6. However, there is no contradiction if an input and output happen at the same time. Here is a modified sysclk/9 for longs:

    < Rev0 >< Rev1 >< Rev2 >< Rev3 >< Rev4 >< Rev5 >< Rev6 >< Rev7 >< Rev8 >< Rev9 >< Rev10>< Rev11>< Rev12>< Rev13>< Rev14>< Rev15>< Rev16>< Rev17>< Rev18>< Rev19>< Rev20>< Rev21>< Rev22>< Rev23>< Rev24>< Rev25>< Rev26>    egg beater Revolutions
    012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567    hub RAM slices
    WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWW    fast block Write
    ........................................IIIIIIxx..............................................IIIIIIxx..............................................IIIIIIxx..............................................IIIIIIxx......    FIFO In
    O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........O........    FIFO Out
    
    111111111222222222333333333444444444555543210000000000111111111222222222333333333444444444455543210000000000111111111222222222333333333444444444555543210000000000111111111222222222333333333444444444555543210000000000    FIFO unfilled longs
    
  • evanhevanh Posts: 15,915
    edited 2022-02-21 13:14

    Of course, but there's also nothing requiring a minimum burst. I was being too hopeful when I wrote that right back at the start. Only figure stated is the -6 low-level mark.

  • @evanh said:
    Only figure stated is the -6 low-level mark.

    Where?

  • evanhevanh Posts: 15,915

    @TonyB_ said:
    ... This is saying burst is 5 ...

    It says up to five more. That's in addition to the minimum of one. Making potentially for six in total. But we know it can be even more, so even that doc isn't covering all cases.

    I vaguely remember Chip saying something about the egg-beater having a lot of buffering. HubRAM accesses must be queued up. This will be a factor in how the FIFO behaves I imagine.

  • evanhevanh Posts: 15,915
    edited 2022-02-21 13:32

    @TonyB_ said:

    @evanh said:
    Only figure stated is the -6 low-level mark.

    Where?

    The "less than cogs+7" is cogs+11-6. EDIT: Hmm, that's only -5. I wonder if the docs are in error. We know that 6 is a very common refill even for slow average rates.

  • TonyB_TonyB_ Posts: 2,178
    edited 2022-02-21 15:38

    @evanh said:
    The "less than cogs+7" is cogs+11-6. EDIT: Hmm, that's only -5. I wonder if the docs are in error. We know that 6 is a very common refill even for slow average rates.

    My earlier post today showed how there can be burst of 6 when starting off with only 5 empty longs. I've looked at the extreme case of sysclk/1.5 for longs and that works, with burst length ending up as 16.

    < Rev0 >< Rev1 >< Rev2 >    egg beater Revolutions
    012345670123456701234567    hub RAM slices
    WWWWWWWW................    fast block Write
    ........IIIIIIIIIIIIIIII    FIFO In
    .OO.OO.OO.OO.OO.OO.OO.OO    FIFO Out
    
    012234455444333222111000    FIFO unfilled longs
    
    < Rev0 >< Rev1 >< Rev2 >    egg beater Revolutions
    012345670123456701234567    hub RAM slices
    WWWWWWWW................    fast block Write
    ........IIIIIIIIIIIIIIII    FIFO In
    O.OO.OO.OO.OO.OO.OO.OO.O    FIFO Out
    
    112334555544433322211100    FIFO unfilled longs
    

    Hub RAM slices can be rotated 0-7 positions.

  • evanhevanh Posts: 15,915

    Six wouldn't then work if the average rate is really low.

  • TonyB_TonyB_ Posts: 2,178
    edited 2022-02-21 15:38

    @evanh said:
    Six wouldn't then work if the average rate is really low.

    Six does work mathematically, though.

  • evanhevanh Posts: 15,915
    edited 2022-02-21 14:22

    It wouldn't be able to fit within the five empty documented FIFO buffer stages. A burst of six needs six buffer stages. When at a low average rate there won't be any extra space freed up to fit all six longwords.

    So, I'm saying there actually is space for a burst of six, ie: the low-level is actually "less than cogs+6". And the docs are wrong.

  • @evanh said:
    So, I'm saying there actually is space for a burst of six, ie: the low-level is actually "less than cogs+6".

    I agree, the FIFO starts filling when there are six empty longs, not five.

    Looking at sysclk/8 for longs, you'd think every 8th rev would be a FIFO rev but that is not the case. Instead, there is a repeating pattern every 48 revs with 7 FIFO revs, six with burst = 7, one with burst = 6 and 8 wasted cycles altogether. Fast write time = 48/41 * N = 1.17N, matching the measured value and only 2.5% more than if one stall every eight revs.

    < Rev0 >< Rev1 >< Rev2 >< Rev3 >< Rev4 >< Rev5 >< Rev6 >< Rev7 >< Rev8 >< Rev9 >< Rev10>< Rev11>< Rev12>< Rev13>< Rev14>< Rev15>< Rev16>< Rev17>< Rev18>< Rev19>< Rev20>< Rev21>< Rev22>< Rev23>< Rev24>< Rev25>< Rev26>< Rev27>< Rev28>< Rev29>< Rev30>< Rev31>< Rev32>< Rev33>< Rev34>< Rev35>< Rev36>< Rev37>< Rev38>< Rev39>< Rev40>< Rev41>< Rev42>< Rev43>< Rev44>< Rev45>< Rev46>< Rev47>    egg beater Revolutions
    012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567012345670123456701234567    hub RAM slices
    ..WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW........  fast block Write
    xx..............................................IIIIIIIx...............................................IIIIIIIx...............................................IIIIIIIx...............................................IIIIIIIx...............................................IIIIIIIx...............................................IIIIIIIx...............................................IIIIIIxx  FIFO In
    O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.......O.  FIFO Out
    
    111111112222222233333333444444445555555566666666654321001111111122222222333333334444444455555555666666655432100011111111222222223333333344444444555555556666665443210000111111112222222233333333444444445555555566666543321000001111111122222222333333334444444455555555666654322100000011111111222222223333333344444444555555556665432110000000111111222222223333333344444444555555556666543210    FIFO unfilled longs
    
Sign In or Register to comment.