[HN Gopher] Ubitium is developing 'universal' processor combinin...
       ___________________________________________________________________
        
       Ubitium is developing 'universal' processor combining CPU, GPU,
       DSP, and FPGA
        
       Author : LorenDB
       Score  : 25 points
       Date   : 2024-11-24 18:45 UTC (4 hours ago)
        
 (HTM) web link (www.tomshardware.com)
 (TXT) w3m dump (www.tomshardware.com)
        
       | mouse_ wrote:
       | that's a really long winded way of saying "SoC with FPGA".
        
         | jacoblambda wrote:
         | Specifically what it looks like they are pursuing is an SoC
         | built around an FPGA that is optimised for runtime
         | reconfiguration speed and presumably with an ISA extension to
         | request and then later release configurations.
        
         | westurner wrote:
         | From "Universal AI RISC-V processor does it all -- CPU, GPU,
         | DSP, FPGA" (2024) https://www.eenewseurope.com/en/universal-ai-
         | risc-v-processo... :
         | 
         | > _For over half a century, general-purpose processors have
         | been built on the Tomasulo algorithm, developed by IBM engineer
         | Robert Tomasulo in 1967. It's a $500B industry built on
         | specialised CPU, GPU and other chips for different computing
         | tasks. Hardware startup Ubitium has shattered this paradigm
         | with a breakthrough universal RISC-V processor that handles all
         | computing workloads on a single, efficient chip -- unlocking
         | simpler, smarter, and more cost-effective devices across
         | industries -- while revolutionizing a 57-year-old industry
         | standard._
         | 
         | Tomasulo's algorithm:
         | https://en.wikipedia.org/wiki/Tomasulo%27s_algorithm
         | 
         | Intel, AMD, ARM, X-Silicon's C-GPU RISC architecture, and
         | Cerebras' on-chip SRAM architecture and are all Tomasulo
         | algorithm OOO Out-of-Order execution processor architectures
         | FWIU
        
       | not_your_vase wrote:
       | Which makes me remember Tachyum, and their universal Prodigy CPU,
       | which is in a constant state of "we just need 5 more minutes, and
       | we are done"...
        
       | sillywalk wrote:
       | "Ubititum claims all of the transistors in its Universal
       | Processor can be reused for everything; no "specialized cores"
       | like those in CPUs and GPUs are required."
       | 
       | One has doubts, especially with only $3.7 million in funding so
       | far.
       | 
       | I recall that Sun's MAJC processor had functional/instruction
       | units that were generic - there weren't dedicated floating point
       | or integer or simd units, they could all operate on any
       | instruction.
        
         | written-beyond wrote:
         | Could you go into a little more depth about how what they're
         | building is anything different from an FPGA.
         | 
         | FPGA's are basically a matrix of interconnected MUXs and LUTs,
         | providing whatever functionality a designer may require, that
         | fits in it's die.
        
           | sillywalk wrote:
           | If you mean about the Ubitium, then no - other than what's in
           | the article.
           | 
           | If you mean more in depth about MAJC, then also no - I read
           | an Ars Technica article around about it (and Itanium) around
           | 25 years ago, when it came out and also the Wikipedia page.
           | 
           | I have no EE or CPU design background, I'd imagine most
           | people would know far more than me. I just remembered the
           | 'generic instruction unit' from MAJC and if this was
           | something superficially similar but at the processor 'core'
           | level.
        
           | cdumler wrote:
           | I have no specific knowledge, but another approach would be
           | to integrate more unusual very-long-instruction-word micro-
           | instructions, like large scale matrix functions, algorithm
           | encode/decode functions, and very long vector operations.
           | 
           | As I recall, Transmeta's CPU could accept x86 instructions
           | because the software translator, called Code Morphing
           | Software (like Rosetta), would decompose the x86 instruction
           | into a set of steps over a very-long-instruction-word. VLIW's
           | design is such that all of the instructions went into
           | separate, parallel pipelines. Each pipeline had specific set
           | of abilities. Think, the first three pipelines might be able
           | to do integer arithmetic, but 3 and 4 can do floats. Also,
           | the CPU implemented a commit/rollback concept which allowed
           | it cause "faults," like branch miss-predictions, interrupts,
           | and instruction faults. This allowed the Transmeta CPU to
           | emulate the x86 beyond just JIT compilations. In theory, it
           | could emulate any other CPU. They tried going after Intel
           | (and failed); but, I think they would have been better off
           | trying go after any one trying to jump start a new
           | architecture.
           | 
           | Part of the reason why CPUs aren't good at GPU activities is
           | because the instructions are expected to have pretty small,
           | definite set of inputs and outputs (registers), use a
           | reasonable number of CPU cycles, and must devote logic to
           | ensure a fault can be unwound (CPU doesn't crash). FPGs are
           | cool because you can essentially have wholly independent
           | units with their own internal state. The little units can be
           | wired any way desired. The problem with FPGs is all that
           | interconnect means a lot of capacitance in the lines, so much
           | slower clock speeds.
           | 
           | So, maybe they are trying to strike a balance. They have
           | targeted instructions are more FPG-like, like "perform
           | algorithm." The instruction receives a set of flags that
           | defines which algorithms to use and in what order (use vector
           | as 8-bit integers, mask with 0x80, compute 16bit checksum)
           | and a vector register. You can loading vectors and running
           | them then finally "read perform algorithm result" with flag
           | "get compute 16bit checksum." FPG-like and registers aren't
           | "polluted" with intermediate state.
        
           | imtringued wrote:
           | Actually, FPGAs are a mix of everything nowadays. They have
           | both programmable logic consisting of LUTs and flipflops in
           | CLBs with integrated carry chains, connection boxes and
           | routing switches, configurable SRAM blocks known as block RAM
           | or sometimes UltraRAM, DSP blocks providing configurable
           | arithmetic units, PLLs, conventional ARM cores, memory
           | controllers, high speed transceivers and finally also VLIW
           | cores for machine learning inference. Notice how a lot of the
           | silicon area is actually taken up by hard silicon that can be
           | connected to the programmable logic. The problem with the
           | largest FPGAs is that you will reach the point where you are
           | swimming in LUTs and the chip are is better spent on e.g.
           | more memory or other hard wired logic like a processor core.
        
       | wmf wrote:
       | The CTO Martin Vorbach published some research on reconfigurable
       | processors 20 years ago:
       | https://scholar.google.com/scholar?hl=en&as_sdt=0%2C44&q=Mar...
        
       ___________________________________________________________________
       (page generated 2024-11-24 23:01 UTC)