* [libre-riscv-dev] [Bug 376] Assess 40/45 nm 2022 target and interfaces
From: bugzilla-daemon @ 2020-06-12 23:02 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-376-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=376
--- Comment #21 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Jacob Lifshay from comment #19)
> (In reply to Luke Kenneth Casson Leighton from comment #17)
> > (In reply to Jacob Lifshay from comment #12)
> > > Assuming we're building a higher than 2W version, I think we should double
> > > the int/fpmul to 8x32-bit per core or maybe even quadruple it to 16x32-bit
> > > and add more cores to 8 or 16 or more cores.
> >
> > at 2.0 ghz this would start to put out some serious numbers :)
>
> I got 1TFLOP/s for 16 fma/clock/core with 16 cores, that's more than half
> the PS4's performance.
those are deeply impressive numbers :) the cross-over post explains however
that the number of RSes - and the data cache line widths etc. - are starting
to get rather scary.
48 LD/ST Reservation Stations would mean 96 160-bit PortInterfaces,
which is 15,360 wires coming into a single block!
we would be much better off going to 128-bit SIMD, which would have the
unfortunate side-effect of cutting scalar performance by another factor
of 2 in speed if there were register usage that could not be scheduled
correctly.
> > > Also, it might be worthwhile to add one more
> > > core and disable one at manufacture time as a way to increase yield.
> >
> > that's a good idea. have to bear in mind that current leakage occurs
> > regardless of whether the silicon is in use or not.
>
> If we set up each core as a different power domain (which will also help
> with idle power), the disabled core could be powered-down.
(you still get current leakage even when powered down, is my point)
> We should probably also widen the instruction decoders to decode 3 or 4
> 32-bit instructions per cycle.
yes. this will almost certainly be necessary, because we would have far more
instructions to keep the monstrous number of RSes "fed".
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 376] Assess 40/45 nm 2022 target and interfaces
From: bugzilla-daemon @ 2020-06-12 23:11 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-376-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=376
--- Comment #22 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Jacob Lifshay from comment #18)
> (In reply to Luke Kenneth Casson Leighton from comment #14)
> > (In reply to Jacob Lifshay from comment #13)
> >
> > > > this for the video framebuffer and the video framebuffer only.
> > >
> > > That doesn't really work, since the GPU will need lots of memory bandwidth
> > > into the framebuffer since that's where it will be rendering to, potentially
> > > drawing over the same pixels several dozen times. To support that, the
> > > memory bandwidth of both the framebuffer and everything else needs to be
> > > spread across all available memory interfaces.
> >
> > ok let's think it through, internally. would we have:
> >
> > * two separate memory interfaces, each dedicated to different address ranges
> > * one L2 (L3?) cache, through which *both* memory interfaces have to go,
> > first
> > (note: the CPU/GPU as a Wishbone Slave, the RGBTTL HDL as a Master)
>
> I think what would work the best is for the RGBTTL HDL and every core to be
> a (extended) wishbone master to the L2 (L3?) cache,
no: really. the cores *have* to take a back seat. it seems odd that
they have such a highly important role but they are actually "slaves",
however the fact is that in a Shared Memory Architecture, I/O absolutely
cannot be given anything but absolute top priority.
this is just normal practice: I/O *has* to have guaranteed timing:
interrupts cannot go unserviced, buffers are extremely small, and
consequently I/O has to have absolute top priority.
look at the Shakti E-Class HDL, you'll see that the SMP Cores are given
AXI4 "slave" status on the internal bus architecture.
> where the cache logic is
> the arbiter and is designed to give the RGBTTL HDL highest priority and
> everything else round robin (or other) priority. Saving power on scan-out
> when the data is already in cache seems like a good idea, also, the memory
> interfaces would be the tightest bottleneck, why require more accesses to go
> through them when that can be avoided?
yes. ideally (following the scenario through) the RGB/TTL HDL Master would
have a completely separate memory bus entirely dedicated to it, reflecting
the fact that it has a completely separate DRAM chip.
however this only starts to be justified if there are say two or three
4k LCDs connected up, where the bandwidth of one 3200 Mbyte/sec interface
would pretty much be soaked up entirely by framebuffers.
> The memory interfaces would be organized into one larger super-interface
> where each memory interface would be responsible for odd or even
> cache-block-sized address blocks. The idea is that accessing something laid
> out contiguously in physical address space would approximate balancing
> evenly across both memory interfaces.
yes. if going the shared route, this seems eminently sensible.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 376] Assess 40/45 nm 2022 target and interfaces
From: bugzilla-daemon @ 2020-06-12 23:14 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-376-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=376
--- Comment #23 from Jacob Lifshay <programmerjake@gmail.com> ---
(In reply to Luke Kenneth Casson Leighton from comment #21)
> (In reply to Jacob Lifshay from comment #19)
> > > > Also, it might be worthwhile to add one more
> > > > core and disable one at manufacture time as a way to increase yield.
> > >
> > > that's a good idea. have to bear in mind that current leakage occurs
> > > regardless of whether the silicon is in use or not.
> >
> > If we set up each core as a different power domain (which will also help
> > with idle power), the disabled core could be powered-down.
>
> (you still get current leakage even when powered down, is my point)
I meant something like having a mosfet in the power line to the whole core, so
the entire power supply could be turned off. Assuming that mosfet wasn't
garbage, the power usage for the whole core could be reduced to the microwatt
level.
> > We should probably also widen the instruction decoders to decode 3 or 4
> > 32-bit instructions per cycle.
>
> yes. this will almost certainly be necessary, because we would have far more
> instructions to keep the monstrous number of RSes "fed".
We would also want to build a better branch predictor (TAGE?) since we would
have a higher power/area budget.
Both of those changes would potentially also drastically improve scalar
performance, approaching that of some modern desktop processors at equivalent
clock speeds.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* Re: [libre-riscv-dev] Fall 2022 Interfaces
From: Jacob Lifshay @ 2020-06-12 23:17 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <CAPweEDxi==E70SDBAh6aHHjyasH6YofX+13RzKAKT8qNe0yJcQ@mail.gmail.com>
On Fri, Jun 12, 2020 at 2:43 PM Luke Kenneth Casson Leighton
<lkcl@lkcl.net> wrote:
>
> ---
> crowd-funded eco-conscious hardware: https://www.crowdsupply.com/eoma68
>
> On Fri, Jun 12, 2020 at 8:34 PM Yehowshua <yimmanuel3@gatech.edu> wrote:
> >
> > >
> > > no it really is 25GHz.
> >
> > Just talked with an engineer who has used the OpenCAPI
> > SMC 100 from Microchip. It actually is 25GHz. 25.6 GHz to
> > be precise.
>
> makes sense, maps to 3200 gbytes/sec, which is the speeds you see for
> things like the latest NVMe
Wow! 3.2 hard drives per second! :P
(I'm assuming you meant 3.2GB/s not 3.2TB/s)
>
> l.
>
> _______________________________________________
> libre-riscv-dev mailing list
> libre-riscv-dev@lists.libre-riscv.org
> http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* Re: [libre-riscv-dev] daily kan-ban update 12jun2020
From: Jacob Lifshay @ 2020-06-12 23:20 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <96D745C1-889B-4E67-82B4-39F479E5E309@getmailspring.com>
today:
figuring out specs for 2022 GPU
working on div pipeline
Jacob
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* Re: [libre-riscv-dev] Fall 2022 Interfaces
From: Luke Kenneth Casson Leighton @ 2020-06-13 0:10 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <CAC2bXD629okgsgMp15LzC2CoovcJ4SiZ7fy07Px_zna1n8HbLA@mail.gmail.com>
On Saturday, June 13, 2020, Jacob Lifshay <programmerjake@gmail.com> wrote:
>
> > makes sense, maps to 3200 gbytes/sec, which is the speeds you see for
> > things like the latest NVMe
>
> Wow! 3.2 hard drives per second! :P
>
> (I'm assuming you meant 3.2GB/s not 3.2TB/s)
haha, yes :)
--
---
crowd-funded eco-conscious hardware: https://www.crowdsupply.com/eoma68
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 376] Assess 40/45 nm 2022 target and interfaces
From: bugzilla-daemon @ 2020-06-13 0:20 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-376-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=376
--- Comment #24 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Jacob Lifshay from comment #23)
> (In reply to Luke Kenneth Casson Leighton from comment #21)
> > (In reply to Jacob Lifshay from comment #19)
> > > > > Also, it might be worthwhile to add one more
> > > > > core and disable one at manufacture time as a way to increase yield.
> > > >
> > > > that's a good idea. have to bear in mind that current leakage occurs
> > > > regardless of whether the silicon is in use or not.
> > >
> > > If we set up each core as a different power domain (which will also help
> > > with idle power), the disabled core could be powered-down.
> >
> > (you still get current leakage even when powered down, is my point)
>
> I meant something like having a mosfet in the power line to the whole core,
> so the entire power supply could be turned off. Assuming that mosfet wasn't
> garbage, the power usage for the whole core could be reduced to the
> microwatt level.
apologies: you're still not getting it. even the *existence* of the gates,
even when fully powered down, with zero oower connected in any way, shape or
form, *still* causes not insignificant current leakage.
this shows up particularly badly in the design of GSM ASICs. thousands of
correlators are required to get an initial lock within "seconds" expected by
users... or... and then they are "powered down" exactly as you suggest.
unfortunately even their very existence, even powered down, causes current
leakage, adversely affecting power consumption and draining battery life.
the solution had to involve "A-GPS" where the LAT/LONG (or even just one of
those) was obtained from the bearest celltower. this reduced the correlator
search soace to the point where a decent DSP could handle the job instead.
> > > We should probably also widen the instruction decoders to decode 3 or 4
> > > 32-bit instructions per cycle.
> >
> > yes. this will almost certainly be necessary, because we would have far more
> > instructions to keep the monstrous number of RSes "fed".
>
> We would also want to build a better branch predictor (TAGE?) since we would
> have a higher power/area budget.
yes, agreed. cancelling 40 Reservation Stations on a regular basis is not an
amusing prospect.
> Both of those changes would potentially also drastically improve scalar
> performance, approaching that of some modern desktop processors at
> equivalent clock speeds.
one very nice thing about SimpleV is that the VL (Vector Length) can be thrown
into the branch tag XOR/hash/thing.
this would give a different prediction at the end of a loop, right just when
you need different decision-making about which way a branch is likely to go.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 376] Assess 40/45 nm 2022 target and interfaces
From: bugzilla-daemon @ 2020-06-13 3:37 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-376-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=376
--- Comment #25 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
i took a look at the OPENCAPI PDF on the proposed interfaces. IBM put OpenCAPI
2 was on top of 8x PCIe 4.0
the later slides, blacked out, show rhat POWER7 was in 40nm.
later, by the time they move to 25GBit/s, they are for POWER9 which is in 14nm.
this, in conjunction with the power requirements, basically tells us that there
is an unachievable mismatch between 25.6 Gbit/s SERDES and a 40/45nm target.
if we were instead to target 14nm or below, we could achieve a 25 GBit/s SERDES
PHY.
this however would require that, as our first major production chip, we seek a
minimum of USD 20 million funding.
if however we stick to PCIe @ 3200 mhz, this *is* achievable in 40/45nm. with
sufficient lanes it becomes possible to reach the bandwidth required, and to
not expect investors to take a huge risk on an unproven team.
alternatively, we stick with plain DDR3/4 because it is also achievable, but
expensive and timeconsuming (SymbioticEDA: 8 to 12 months fulltime work on a
PHY, USD 600,000).
alternatively, we use multiple HyperRAM interfaces and overclock the protocol,
connecting to a suitable FPGA that either has a DDR3/4 interface *or* suitable
SERDES sufficient to do OpenCAPI. the ECP5G springs to mind although its DRAM
interface is only capable of 200mhz (400mhz DDR).
the advantage of a 3200 mhz SERDES is that it is useful for a large number of
things that rely on a PCIe PHY. OpenCAPI, HMC, and PCIe itself.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] daily kan-ban update 13jul2020
From: Luke Kenneth Casson Leighton @ 2020-06-13 14:48 UTC (permalink / raw)
To: Libre-RISCV General Development
yesterday:
* investigated LDST memory byte order discrepancy.
* reviewed proposed 40/45nm ASIC and found its interfaces to be
unachievable (25GBit/s is not practical in 45nm)
the review occupied the entire day and consequently no code was written.
today:
continue investigating byte order particularly of simulator vs qemu in
order to be able to get it right for the hardware.
what i do not understand - what concerns me greatly - is that the simulator
appears to be storing data from the opposite (big) end of its 8 byte
granularity, computing shiftmasks based on subtracting from 8.
this would tend to suggest a hardcoded dependency on a 64 bit memory width
allocation.
however reviewing both microwatt and pearpc i find no evidence of that,
hence my concern.
l.
--
---
crowd-funded eco-conscious hardware: https://www.crowdsupply.com/eoma68
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 377] possible bug in Simulator Mem ld/st function
From: bugzilla-daemon @ 2020-06-13 15:53 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-377-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=377
--- Comment #2 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
hmmm i took a look at microwatt, and i'm likewise not seeing any evidence of
offset-reversal based on an 8-byte (64-bit) boundary.
i did however discover that qemu 8-byte memory-read returns data in big-endian
order, and had to read it in single-bytes then reconstruct a little-endian
debug/display value.
honestly i have no real idea what i am doing here and could really use some
help and discussion.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 377] possible bug in Simulator Mem ld/st function
From: bugzilla-daemon @ 2020-06-13 23:52 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-377-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=377
--- Comment #3 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
i think i got it.
nmigen memory write port, if you specify a granularity argument to cut the SRAM
into bytes, writes those bytes in *big* endian order.
however if you read the same interface with a single read-enable line, the
answer comes back in *little* endian order.
*face-palm*
i am however much preferring thinking in LE terms when it comes to memory
layouts and byte addressing.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] effects of powered-off chip sections on current leakage
From: Jacob Lifshay @ 2020-06-14 5:06 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <bug-376-13-VsIxQBkNqh@https.bugs.libre-soc.org/>
On Fri, Jun 12, 2020, 17:21 <bugzilla-daemon@libre-soc.org> wrote:
> https://bugs.libre-soc.org/show_bug.cgi?id=376
>
> --- Comment #24 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
> (In reply to Jacob Lifshay from comment #23)
> > (In reply to Luke Kenneth Casson Leighton from comment #21)
> > > (In reply to Jacob Lifshay from comment #19)
> > > > > > Also, it might be worthwhile to add one more
> > > > > > core and disable one at manufacture time as a way to increase
> yield.
> > > > >
> > > > > that's a good idea. have to bear in mind that current leakage
> occurs
> > > > > regardless of whether the silicon is in use or not.
> > > >
> > > > If we set up each core as a different power domain (which will also
> help
> > > > with idle power), the disabled core could be powered-down.
> > >
> > > (you still get current leakage even when powered down, is my point)
> >
> > I meant something like having a mosfet in the power line to the whole
> core,
> > so the entire power supply could be turned off. Assuming that mosfet
> wasn't
> > garbage, the power usage for the whole core could be reduced to the
> > microwatt level.
>
> apologies: you're still not getting it. even the *existence* of the gates,
> even when fully powered down, with zero oower connected in any way, shape
> or
> form, *still* causes not insignificant current leakage.
>
Please explain in more detail, perhaps with some supporting references --
it still makes close to zero sense to me how additional unused silicon area
could affect the rest of the chip, since that area itself couldn't be
drawing any power since all wires into it that are at 0V due to the power
rails and I/O signals being switched off.
> this shows up particularly badly in the design of GSM ASICs. thousands of
> correlators are required to get an initial lock within "seconds" expected
> by
> users... or... and then they are "powered down" exactly as you suggest.
>
> unfortunately even their very existence, even powered down, causes current
> leakage, adversely affecting power consumption and draining battery life.
>
> the solution had to involve "A-GPS" where the LAT/LONG (or even just one of
> those) was obtained from the bearest celltower. this reduced the
> correlator
> search soace to the point where a decent DSP could handle the job instead.
>
neat! didn't know about A-GPS before, though I assumed it was related to
GPS somehow.
>
Jacob
>
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* Re: [libre-riscv-dev] effects of powered-off chip sections on current leakage
From: Luke Kenneth Casson Leighton @ 2020-06-14 11:30 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <CAC2bXD64OBzL_-gaxipwyCR5NqgphuJmtmK1woTE9mWqpE1r8A@mail.gmail.com>
On Sun, Jun 14, 2020 at 6:06 AM Jacob Lifshay <programmerjake@gmail.com> wrote:
> Please explain in more detail, perhaps with some supporting references --
> it still makes close to zero sense to me how additional unused silicon area
> could affect the rest of the chip, since that area itself couldn't be
> drawing any power since all wires into it that are at 0V due to the power
> rails and I/O signals being switched off.
beyond the fact that it occurs, i do not know the details. i had a
mentor who explained it to me, and (in the case of the GPS
correlators) a second person confirmed it.
it is something to do with the fact that a transistor is not a perfect
isolator, and that it is both a resistor and a capacitor. the
resistance, when there is zero power applied to the Drain, is
extremely small but it is *not* zero, between the two planes that are
directly above and below the transistor (one VDD - +ve voltage, one
VSS - GND)
ok so if there's an actual MOSFET that cuts power to those planes,
there's nothing to "resist", so the idea that you came up with of
cutting power entirely has merit that needs a proper investigation.
> neat! didn't know about A-GPS before, though I assumed it was related to
> GPS somehow.
there was a company that "invented" the concept around 2006, it's a
logical progression. if you have a LAT/LON already to within a few
miles, the search space is clearly going to be far smaller.
l.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 377] possible bug in Simulator Mem ld/st function
From: bugzilla-daemon @ 2020-06-14 15:02 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-377-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=377
--- Comment #4 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
i tracked this down by adding memory dump/alteration to qemu and making
a comparison of memory in qemu and memory in the simulator.
it was a number of separate things:
* the hardware was not performing big-endian byte reversal
* the simulator was storing 8 bytes in a dictionary on 8-byte
address-aligned boundary where the data order of each 8-byte
group was byte-reversed (big-endian)
* to correct this, the shift-mask function subtracted the offset
from the *other* end (the 8-byte boundary of the underlying
simulated memory - 64 bit blocks)
what i did was:
* reverse the order of 8-byte groups being stored to be in
little-endian format in the simulator
* turned the shift round so that it is exactly the
LSB bits of the address (bits 0 to 2) where previously
it was (7-datalen-AddrLSBs)
* added a function which byte-reverses (big-endians) the load/store
*data* - not the entire simulator-stored 64-bit-granularity memory
* added a byte-reverse function into the hardware.
that byte-reverse function *should* now be possible to call on-demand
for LD/ST byte-reversal opcodes. i will give that a shot and see if
it works.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] daily kan-ban update 14jun2020
From: Luke Kenneth Casson Leighton @ 2020-06-14 17:12 UTC (permalink / raw)
To: Libre-RISCV General Development
yesterday:
* did more investigation of LD/ST. added memory dump to qemu sim
* had a really nice chat with Cole.
today:
* sorted out LD/ST by assuming qemu was correct, then correcting the
simulator to match it, then correcting the hardware to match *that*.
rest of today:
* add in LD/ST Comp Unit tests into simple/core.py and in to the "big"
unit test_core.py
tomorrow can consider adding in the InstructionQ (probably only 1
wide) and then add Minerva instruction "read" (I-Cache). have to
create some sort of nmigen-wishbone-to-Memory bridge to do that.
l.
---
crowd-funded eco-conscious hardware: https://www.crowdsupply.com/eoma68
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 376] Assess 40/45 nm 2022 target and interfaces
From: bugzilla-daemon @ 2020-06-14 17:27 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-376-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=376
--- Comment #26 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Jacob Lifshay from comment #23)
> I meant something like having a mosfet in the power line to the whole core,
> so the entire power supply could be turned off. Assuming that mosfet wasn't
> garbage, the power usage for the whole core could be reduced to the
> microwatt level.
yep, as you can see from the list reply, i've caught up now. with zero
power being applied between the VDD and VSS plane, the expectation would
be that there would be no current to actually leak.
this is the point at which my knowledge is lacking, and we'd have to ask
someone. *nominally*, my understanding is that even powered down there
is still leakage, although because i did not ask that specific question
of the people who advised me, i can't confirm it.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 382] New: nmigen wishbone Memory object needed
From: bugzilla-daemon @ 2020-06-14 17:32 UTC (permalink / raw)
To: libre-riscv-dev
https://bugs.libre-soc.org/show_bug.cgi?id=382
Bug ID: 382
Summary: nmigen wishbone Memory object needed
Product: Libre-SOC's first SoC
Version: unspecified
Hardware: PC
OS: Linux
Status: CONFIRMED
Severity: enhancement
Priority: ---
Component: Source Code
Assignee: lkcl@lkcl.net
Reporter: lkcl@lkcl.net
CC: libre-riscv-dev@lists.libre-riscv.org
NLnet milestone: ---
for testing purposes (and also because we will actually need an on-board SRAM
and maybe a ROM as well) we need a means to place a Memory object behind a
wishbone bus.
does anyone know of anything like this?
one of the simplest ways to achieve it is to hack the minerva L1 cache
code, removing the "tag" aspect and substituting direct memory read-write.
however it would be preferable not to spend the time doing that if someone
knows of a pre-existing block.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 383] New: Complete first functional POWER9 Core
From: bugzilla-daemon @ 2020-06-14 18:23 UTC (permalink / raw)
To: libre-riscv-dev
https://bugs.libre-soc.org/show_bug.cgi?id=383
Bug ID: 383
Summary: Complete first functional POWER9 Core
Product: Libre-SOC's first SoC
Version: unspecified
Hardware: Other
OS: Linux
Status: CONFIRMED
Severity: enhancement
Priority: ---
Component: Source Code
Assignee: lkcl@lkcl.net
Reporter: lkcl@lkcl.net
CC: libre-riscv-dev@lists.libre-riscv.org
NLnet milestone: ---
After the decision to implement POWER9 instead of RISC-V a full from-scratch
implementation of POWER9 was needed in nmigen. This to become the later basis
for adding Vectorisation, GPU and VPU instructions.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 383] Complete first functional POWER9 Core
From: bugzilla-daemon @ 2020-06-14 18:24 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-383-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=383
Luke Kenneth Casson Leighton <lkcl@lkcl.net> changed:
What |Removed |Added
----------------------------------------------------------------------------
parent task for| |175
budget allocation| |
Blocks| |175
total budget (EUR)|0 |8000
for completion of| |
task and all| |
subtasks| |
NLnet milestone|--- |NLNet.2019.10.Wishbone
Referenced Bugs:
https://bugs.libre-soc.org/show_bug.cgi?id=175
[Bug 175] NLNet 2019 Wishbone proposal 2019-10-043
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 384] New: Documentation for the POWER9 Core and internal architecture
From: bugzilla-daemon @ 2020-06-14 18:39 UTC (permalink / raw)
To: libre-riscv-dev
https://bugs.libre-soc.org/show_bug.cgi?id=384
Bug ID: 384
Summary: Documentation for the POWER9 Core and internal
architecture
Product: Libre-SOC's first SoC
Version: unspecified
Hardware: Other
OS: Linux
Status: CONFIRMED
Severity: enhancement
Priority: ---
Component: Documentation
Assignee: lkcl@lkcl.net
Reporter: lkcl@lkcl.net
CC: libre-riscv-dev@lists.libre-riscv.org
NLnet milestone: ---
The LibreSOC core is complex and comprehensive. Its internal architecture
needs to be documented in order to make its design both accessible and
maintainable.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 384] Documentation for the POWER9 Core and internal architecture
From: bugzilla-daemon @ 2020-06-14 18:40 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-384-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=384
Luke Kenneth Casson Leighton <lkcl@lkcl.net> changed:
What |Removed |Added
----------------------------------------------------------------------------
NLnet milestone|--- |NLNet.2019.10.Wishbone
total budget (EUR)|0 |6000
for completion of| |
task and all| |
subtasks| |
Blocks| |175
parent task for| |175
budget allocation| |
Referenced Bugs:
https://bugs.libre-soc.org/show_bug.cgi?id=175
[Bug 175] NLNet 2019 Wishbone proposal 2019-10-043
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 175] NLNet 2019 Wishbone proposal 2019-10-043
From: bugzilla-daemon @ 2020-06-14 18:42 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-175-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=175
Luke Kenneth Casson Leighton <lkcl@lkcl.net> changed:
What |Removed |Added
----------------------------------------------------------------------------
total budget (EUR)|36000 |50000
for completion of| |
task and all| |
subtasks| |
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 184] new mailing lists proposal for libre-soc.org
From: bugzilla-daemon @ 2020-06-14 18:57 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-184-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=184
--- Comment #22 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Cole Poirier from comment #21)
> (In reply to Luke Kenneth Casson Leighton from comment #20)
> > just checking by subscribing to libre-soc-misc, should they be
> > libre-soc-misc@lists.libre-soc.org
> > i kiiinda prefer the convention of a separate domain name
>
> I Agree. I prefer libre-soc-misc@libre-soc.org
turns out they are in fact at lists.libre-soc.org because exim4 can't easily be
configured to merge mailman on one vhost and email addresses on another.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 382] nmigen wishbone Memory object needed
From: bugzilla-daemon @ 2020-06-14 19:13 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-382-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=382
--- Comment #1 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
found one
https://codecov.io/gh/m-labs/nmigen-soc/pull/6/diff?src=pr&el=tree#diff-bm1pZ2VuX3NvYy93aXNoYm9uZS9zcmFtLnB5
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
* [libre-riscv-dev] [Bug 382] nmigen wishbone Memory object needed
From: bugzilla-daemon @ 2020-06-14 19:14 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-382-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=382
--- Comment #2 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
found one
https://codecov.io/gh/m-labs/nmigen-soc/pull/6/diff?src=pr&el=tree#diff-bm1pZ2VuX3NvYy93aXNoYm9uZS9zcmFtLnB5
https://github.com/m-labs/nmigen-soc/pull/6
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
^ permalink raw reply
page: next prev latest
Libre RISC-V Mailing list Archives (accessible via public-inbox)
Archives are clonable: git clone --mirror https://inbox.libre-soc.org/libre-riscv-dev
Example config snippet for mirrors
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git