An interesting comment piece on The Register, from Timothy Prickett Morgan, about how the mothballing of "Larrabee" - the x86-based hybrid multi-core CPU and GPU - points to good HPC times for Nvidia: Intel Larrabee letdown leaves HPC to Nvidia's Fermi
He says Intel has never been particularly precise about what "Larrabee" chips were, so it is hard to know exactly what it is we will be missing. Or indeed what we can ever expect from when it finally markets discrete graphics chips that can also be used for number-crunching in servers and workstations...
He continues:
He says Intel has never been particularly precise about what "Larrabee" chips were, so it is hard to know exactly what it is we will be missing. Or indeed what we can ever expect from when it finally markets discrete graphics chips that can also be used for number-crunching in servers and workstations...
He continues:
At the SC09 supercomputing trade show in November, when Justin Rattner, Intel's chief technology officer, gave the keynote presentation and his finale was to demonstrate a Larrabee co-processor being overclocked so it could hit 1 teraflops of single-precision floating point performance, there was no hint that Larrabee was on the rocks - the demonstration was clearly meant to show quite the opposite. That made the abrupt change last week that turned Larrabee from a graphics chip that was expected some time next year to a "software development platform for internal and external use," as Intel's statement put it, all the more jarring.
Read the full article >>
For more on the Larrabee developments:
- Intel shelves consumer Larrabee (The Inquirer)
- Intel delays Larrabee indefinitely (Computerworld)
- Intel drops plans for Larrabee GPU in 2010 (ZDNet)
Leave a comment