NVIDIA Challenges Apple's iPad Benchmarks

MojoKid writes "At the iPad unveiling last week, Apple flashed up a slide claiming that the iPad 2 was 2x as fast as Nvidia's Tegra 3, while the new iPad would be 4x more powerful than Team Green's best tablet. NVIDIA's response boils down to: 'it's flattering to be compared to you, but how about a little data on which tests you ran and how you crunched the numbers?' NVIDIA is right to call Apple out on the meaningless nature of such a comparison, and the company is likely feeling a bit dogpiled given that TI was waving unverified webpage benchmarks around less than two weeks ago. That said, the Imagination Technologies (PowerVR) GPUs built into the iPad 2 and the new iPad both utilize tile-based rendering. In some ways, 2012 is a repeat of 2001 — memory bandwidth is at an absolute premium because adding more bandwidth has a direct impact on power consumption. The GPU inside NVIDIA's Tegra 2 and Tegra 3 is a traditional chip, which means it's subject to significant overdraw, especially at higher resolutions. Apple's comparisons may be bogus, but Tegra 3's bandwidth issue they indirectly point to aren't. It will be interesting to see NVIDIA's next move and what their rumored Tegra 3+ chip might bring."

Comments

Re:Don't worry, Nvidia!

[TheRaven64]

Just ask Intel about Apple's benchmarking strategy: For years, the finest in graphic design publicly asserted that PPC was so bitchin' that it was pretty much just letting Intel and x86 live because killing your inferiors is bad taste. Then, one design win, and x86 is suddenly eleventy-billion percent faster than that old-and-busted PPC legacy crap.

This wasn't totally misleading. The G4 was slightly faster than equivalent Intel chips when it was launched and AltiVec was a lot better than SSE for a lot of things. More importantly, AltiVec was actually used, while a lot of x86 code was still compiled using scalar x87 floating point stuff. Things like video editing - which Apple benchmarked - were a lot faster on PowerPC because of this. It didn't matter that hand-optimised code for x86 could often beat hand-optimised code for PowerPC, it mattered that code people were actually running was faster on PowerPC. After about 800MHz, the G4 didn't get much by way of improvements and the G5, while a nice chip, was expensive and used too much power for portables. The Pentium M was starting to push ahead of the PowerPC chips Apple was using in portables (which got a tiny speed bump but nothing amazing) and the Core widened the gap. By the Core 2, the gap was huge.

It wasn't just one design win, it was that the PowerPC chips for mobile were designs that competed well with the P2 and P3, but were never improved beyond that. The last few speedbumps were so starved for memory bandwidth that they came with almost no performance increase. Between the P3 and the Core 2, Intel had two complete microarchitecture designs and one partial redesign. Freescale had none and IBM wasn't interested in chips for laptops.

Re:This is funny.

[ozmanjusri]

This is a Tegra 3 to A5 benchmark:

http://hardware.slashdot.org/story/11/12/01/1518244/nvidias-tegra-3-outruns-apples-a5-in-first-benchmarks.

Note that in the Apple infographic, they're claiming a 2X speed advanatge over the Tegra 3 with the iPad2's A5. That doesn't appear to be true, though the A5 has some advantages.

Whether the A5X has picked up enough ground to quadruple the Tegra's performance remains to be seen, and given Apple's debunked claims about the A5, seems unlikely.