Eelco de Groot wrote: ↑Sun Sep 11, 2022 5:13 pm
As far as I know, the processors they used for the Space Shuttle, computationally were far more ancient than the 68000. Basically it is IBM 360 hardware.
[..]
Haha, thx, core memory, transistor-transistor-logic - indeed, ancient

but probably reliable, according to your link 0.48 MIPS on average, 68k@8Mhz made ~1 MIPS, so it gets close, or alike...
https://www.sifive.com/document-file/x280-datasheet
The SiFive Intelligence Extensions enable the X280
processor to achieve a best-in-class 4.5 TFLOPs
(bfloat16 MatMul) or 9.2 TOPS (INT8 MatMul)
supporting the broadest range of ML workloads and
AI computation needs. The SiFive Intelligence
acceleration gives a 6x improvement over that
achievable with a vector processor running RISC-V
Vector ISA 1.0.
https://www.sifive.com/blog/introductio ... gence-x280
Key Features include:
64-bit RISC-V ISA
SiFive Intelligence Extensions, which are custom instructions that accelerate AI/ML performance critical operations
Multi-core, multi-cluster processor configuration options, with up to 8 cores
Loosely coupled vector computation pipeline and ALU implementing RISC-V Vector extension version 1.0
Support for multiple data types
512-bit vector register length
256-bit Vector ALU and Load/Store architecture
Decoupled scalar and vector pipelines for optimum parallel execution of scalar and vector computation
Virtual memory support, with up to 48-bit addressing
High performance, flexible connectivity to SoC peripherals
--
Srdja