Motorola starts to talk up PowerPC 7457

New G4 CPU nearing lift-off


Motorola's latest G4-class PowerPC processor, the MPC7457, will feature prominently at this week's Smart Networks Developer Conference (SNDF), being held at Disneyland Paris.

The 7457, codenamed 'Apollo 7', was announced last February, and began sampling in March. In February, Motorola said the part would ship in volume in Q4 2003.

The chip is essentially a die-shrink of the current 7455 (aka 'Apollo 6') as Motorola moves from a 0.18 micron to a 0.13 micron process. That has allowed the company to expand the chip's on-die L2 cache from the 7455's 256KB to 512KB.

That, says Motorola, brings the 1.3GHz 7457 a 40 per cent speed increase over the 1GHz 7455. The clock frequency hike provides just a 33 per cent performance boost - the rest comes from the chip's extra L2 cache.

The 7457 features a faster, 200MHz system bus, paving the way for 400MHz DDR SDRAM support. It can also cope with more backside L3 cache than its predecessor: 4MB compared to the 7455's 2MB.

According to Motorola documents seen by The Register, the 7457 is "footprint compatible" with the 7455, but the new chip has an extra pin for L3 cache addressing. The documentation implies that the equivalent pin on the 7455 isn't connected to anything, so provided Apple has designed its existing CPU daughtercards with the 7457 in mind, it should be able to add 7457s to its existing boards, assuming it's planning to use the chip at all. Our instinct is that it will, in its consumer computers, if only to maintain clear water between the iMac and the Power Mac lines.

Motorola is marketing the chip at the embedded market, but as we've seen, although the 7455 officially peaks at 1.067GHz, Motorola offers 1.25GHz and 1.4GHz parts too. The 7457's clock frequency range is 1-1.3GHz, but we'd bet that Motorola will offer desktop customers higher clocked versions. It's embedded G4s are given L and N codes to indicate "upper" and "lower" frequencies - and core voltages of 1.6V and 1.3V, respectively.

The chips Apple uses are coded P, and feature even higher clock speeds and core voltages of 1.85V. These chips are aimed at desktops and aren't pitched at embedded-chip buyers presumably because their power dissipation characteristics are less desirable for that market. Whatever, it's hard to imagine that Motorola will not offer P-class 7457s to Apple and others.

Extrapolating from Motorola's own figures, the 7457 should consume 30W as 1.4GHz and around 33W at 1.6GHz, based on a 1.6V core voltage. Running at 1.85V we'd estimate power dissipation will be much higher.

Full pricing for the chip has yet to be revealed but Motorola has said the 1GHz part will cost around $189 in batches of 10,000. That's a lot less than the $475 that the 1.25GHz 7455 is currently available through distributors for. Apple probably won't be paying that much, thanks to volume discounts, not least because it needs two per Power Mac.

IBM's PowerPC 970 has been rumoured to be being offered to Apple at around 25-35 per cent cheaper than competing Motorola parts. ®

Related Stories

Motorola adds dual-core G4 to PowerPC roadmap
Motorola to boost 0.13_ PowerPCs with low-k dielectrics
IBM preps 1GHz-plus PowerPC 750GX 'Gobi'


Other stories you might like

  • Will Lenovo ever think beyond hardware?
    Then again, why develop your own software à la HPE GreenLake when you can use someone else's?

    Analysis Lenovo fancies its TruScale anything-as-a-service (XaaS) platform as a more flexible competitor to HPE GreenLake or Dell Apex. Unlike its rivals, Lenovo doesn't believe it needs to mimic all aspects of the cloud to be successful.

    While subscription services are nothing new for Lenovo, the company only recently consolidated its offerings into a unified XaaS service called TruScale.

    On the surface TruScale ticks most of the XaaS boxes — cloud-like consumption model, subscription pricing — and it works just like you'd expect. Sign up for a certain amount of compute capacity and a short time later a rack full of pre-plumbed compute, storage, and network boxes are delivered to your place of choosing, whether that's a private datacenter, colo, or edge location.

    Continue reading
  • Intel is running rings around AMD and Arm at the edge
    What will it take to loosen the x86 giant's edge stranglehold?

    Analysis Supermicro launched a wave of edge appliances using Intel's newly refreshed Xeon-D processors last week. The launch itself was nothing to write home about, but a thought occurred: with all the hype surrounding the outer reaches of computing that we call the edge, you'd think there would be more competition from chipmakers in this arena.

    So where are all the AMD and Arm-based edge appliances?

    A glance through the catalogs of the major OEMs – Dell, HPE, Lenovo, Inspur, Supermicro – returned plenty of results for AMD servers, but few, if any, validated for edge deployments. In fact, Supermicro was the only one of the five vendors that even offered an AMD-based edge appliance – which used an ageing Epyc processor. Hardly a great showing from AMD. Meanwhile, just one appliance from Inspur used an Arm-based chip from Nvidia.

    Continue reading
  • NASA's Psyche mission: 2022 launch is off after software arrives late
    Launch window slides into 2023 or 2024 for asteroid-probing project

    Sadly for NASA's mission to take samples from the asteroid Psyche, software problems mean the spacecraft is going to miss its 2022 launch window.

    The US space agency made the announcement on Friday: "Due to the late delivery of the spacecraft's flight software and testing equipment, NASA does not have sufficient time to complete the testing needed ahead of its remaining launch period this year, which ends on October 11."

    While it appears the software and testbeds are now working, there just isn't enough time to get everything done before a SpaceX Falcon Heavy sends the spacecraft to study a metallic-rich asteroid of the same name.

    Continue reading

Biting the hand that feeds IT © 1998–2022