The State Of Debian & Fedora On The RISC-V Architecture

[tuxd3v]

I am glad to see people adopting risc-v, I'm hoping to replace my ARM devices with risc-v in the next few years. Level1Techs did a basic yet cool video on SiFive a few days ago. It's worth a watch to someone who wonders about the motivation behind companies like SiFive, the title was: "Building Your Own RISC-V CPU With SiFive".

Thanks for the video
RiscV,Open Risc, and now Mips32, are all good things,
OpenRisc is in a undefined state

I see mips32( which is now also open ), with a better option has a OS microprocessor..
Riscv will need lots of work, to reshape the market,( mips32 too ),
Its better positioned for micro-controllers space, like the GreenWaves GAP8, and SiFive lower parts, IOT and stuff, even WD made some statements about that some time ago, for hard-drives, Raid controllers, etc..

[Jabberwocky]

I am glad to see people adopting risc-v, I'm hoping to replace my ARM devices with risc-v in the next few years. Level1Techs did a basic yet cool video on SiFive a few days ago. It's worth a watch to someone who wonders about the motivation behind companies like SiFive, the title was: "Building Your Own RISC-V CPU With SiFive".

[tuxd3v]

No, only on Mhz/performance. No word on performance/power.

Less than 5 watts also on the clusters? Also on higher frequencies? Because power consumption increases when you do that. Do note that the reviewer talked of 2Ghz as the frequency required to be competitive with an ARM cortex a-15. 1.5GHz isn't going to do that.

From your very results, Cortex-A15 at 2ghz or above.

you had to pick sentences out of context as even your own sources don't state that.

They were talking in the Samples , and the Samples have a T1 on its case which means limited to 1.2Ghz( For evaluation purpose.. )..
The cores can go to 1.5Ghz( But that we have no public view, at least I haven't found any ).

Imagination and TSMC, said that cores can reach 2Ghz, but that I haven saw any statement from Baikal Electronics..

So the results are related with the Evaluation Version( T1 on case 1.2Ghz ).
Yes off course less than 5 Watts on the Cluster!

They have bigger CoreMark than Cortex A15, and as far has I have readed it is increasing as Compilers are aware of the ISA intruction Set..
Baikal Tests are using a very old Compiler toolchain, 4.9 or 5.3 something like that..
On 7.3 results are even better!

No Cortex A15 @2Ghz, area a power hog..
And its performance only is bigger in absolute terms, not in perf/Mhz/Whatt,
So you failed to give a LowPower Option to compete with BaikalT1

[starshipeleven]

Second,
The point 2) and 3) and independent Analyses, and they even show better results than Baikal do( maybe due to more recent compilers, probably )!
They have the best scores on relative performance/Mhz/Power.

No, only on Mhz/performance. No word on performance/power.

They tested samples,
Which are limited to 1.2Ghz or 1 Ghz.. Baikal can produce cluster of 4, 4+2, till 1.5Ghz..
To give you an ideia, Baikat T1, power consumption is less than 5 Watts..

Less than 5 watts also on the clusters? Also on higher frequencies? Because power consumption increases when you do that. Do note that the reviewer talked of 2Ghz as the frequency required to be competitive with an ARM cortex a-15. 1.5GHz isn't going to do that.

Tell me one that has better results than BaikalT1.

From your very results, Cortex-A15 at 2ghz or above.

You asked for facts and I showed you facts,

you had to pick sentences out of context as even your own sources don't state that.

[tuxd3v]

In first Place, you are wrong..
I am not Russian, but I am also European!

Second,
The point 2) and 3) and independent Analyses, and they even show better results than Baikal do( maybe due to more recent compilers, probably )!
They have the best scores on relative performance/Mhz/Power.

They tested samples,
Which are limited to 1.2Ghz or 1 Ghz.. Baikal can produce cluster of 4, 4+2, till 1.5Ghz..
To give you an ideia, Baikat T1, power consumption is less than 5 Watts..

So my Statement is accurate!
They have the best LowPower 32 bits CPU.

Tell me one that has better results than BaikalT1.
You asked for facts and I showed you facts,
Now show me a 32 bits processor with more performance, and less than 5 watts of power 32 bits?!
Can you do that?

[starshipeleven]

Some examples:
1) Directly from Baikal
2) I think more recent benchmarks: https://medium.com/@malafeev/first-i...d-bc7c1db12046
3) "Per-clock, the P5600 also scored ahead of the Cortex-A15, which I believe is the closest competitor in the category of the P5600. "
("Those g++7.3 results positioned the P5600 firmly between the AMD A8-7600 and the Intel Core2 Duo P8600 in the clock-normalized Mandelbrot performance charts...")

Baikal is the main manufacturer so I'm not going to believe them at face value.

The second source does still show ARM and quite old x86 hardware (Pentium 4 or Phenom II) beating it.

Your third source actually states the same in a part that isn't taken out of context like you did:

Per-clock, the P5600 also scored ahead of the Cortex-A15, which I believe is the closest competitor in the category of the P5600. Where the P5600, or perhaps its incarnation in the Baikal T1, fell short, was in absolute performance due to low clocks. Should that core reach clocks closer to 2GHz, we’d be seeing much more interesting absolute-performance results.

Using my limited micro-benchmark set as a basis, that uarchitecture does largely deliver on its promises of good gen-purposes IPC and good SIMD throughput per clock, and could be considered a direct competitor to the best of 32-bit ARM Cortex designs. That said, Baikal T1 could use higher clocks, which would position it in absolute-performance terms right in the group of the Core2 lineup by Intel and the Cortex-A12/15/17 lineup by ARM.

That's not really a statement of its superiority by any stretch of the imagination.
He says that per-clock it is superior but since it is run at low clock speed it's not better.

To be superior to ARM it would have to boost its power consumption quite a bit, as that's what happens when you boost clock speed. Then it's no more "low power".

I'm not saying it's bad, all things considered it is a very good result for a small company, but it's not really "the best 32bit low power CPU".

You probably won't accept this truth because it's russian and russian stuff is always best for russian people, but that's your own problem.

[tuxd3v]

[citation needed]

Some examples:
1) Directly from Baikal
2) I think more recent benchmarks: https://medium.com/@malafeev/first-i...d-bc7c1db12046
3) "Per-clock, the P5600 also scored ahead of the Cortex-A15, which I believe is the closest competitor in the category of the P5600. "
("Those g++7.3 results positioned the P5600 firmly between the AMD A8-7600 and the Intel Core2 Duo P8600 in the clock-normalized Mandelbrot performance charts...")

[starshipeleven]

Because mips owns the best lowpower 32 bits cpu out there,

[citation needed]

[tuxd3v]

risc-v is nice for been simpler and open..
But now with Open Mips32.. I don'tknow..

Because mips owns the best lowpower 32 bits cpu out there, and now its also open..

[LaeMing]

If risc-v ends up implementing support for posit number format in hardware and those linux distributions start supporting it, my bet is that risc-v can become the next big thing. See https://posithub.org/docs/RISC-V/RISC-V-for-posits.pdf for details.

Wow. THAT topic was a most interesting rabbit hole to fall down! Much thanks, pegasus !