Slashdot Mirror
ARM Offers First Clockless Processor Core
Sam Haine '95 writes "EETimes is reporting that ARM Holdings have developed an asynchronous processor based on the ARM9 core. The ARM996HS is thought to be the world's first commercial clockless processor. ARM announced they were developing the processor back in October 2004, along with an unnamed lead customer, which it appears could be Philips. The processor is especially suitable for automotive, medical and deeply embedded control applications. Although reduced power consumption, due to the lack of clock circuitry, is one benefit the clockless design also produces a low electromagnetic signature because of the diffuse nature of digital transitions within the chip. Because clockless processors consume zero dynamic power when there is no activity, they can significantly extend battery life compared with clocked equivalents."
Sun exhorts people to make clockless chips
This is my sig.
Is there a chance these things will cook themselves?
Current processors are clocked at whatever speed they can safely run at and many of them automatically underclock themselves if they overheat.
Without a clock, what keeps the speed at a safe level?
ARM and Intel are operating in very different market areas these days (sad actually as ARM processors fly). ARM are targetting the embedded and PDA type market (Alot Pocket PC's use StrongARM) and given all their embedded processors stuck in cars, washing machines etc I'd imagine in their target market space they've got more than 50% market share.
Can people please remember the computer industry does not start and stop with the latest bit of kit for playing DOOM3 or surfing the ruddy internet....
--- Users are like bacteria -> Each one causing a thousand tiny crises until the host finally gives up and dies.
There's no easy answer. On a traditional clocked processor, each instruction takes a certain number of clock cycles. In the async case, everything just takes however long it takes. In fact, some arithmetic operations might take variable amounts of time depending on the value of the operands.
Given an equivalent process, layout technology, and number of transistors, an async design will be at least somewhat faster and vastly more power-efficient than a clocked design.
But none of those things are going to be equivalent in the real world - except possibly the process that ARM designs to. So comparisons will be difficult.
Not faster - sooner. The closer they are the sooner they see the clock pulse.
so the processor doesn't run perfectly synchronously.
The processor does indeed run perfectly synchronously. The individual logic gates just produce results at different relative times. This has always been the case, but as clock speeds increase, the relative size of these delays becomes a bigger issue as the inputs to and outputs of logic gates clocked at different relative times have to be combined. Momemtary unexpected results (glitches) can occur if these effects are not controlled.