As always, our good friends over at Kishonti managed to have the first GPU performance results for the new 4th generation iPad. Although the new iPad retains its 2048 x 1536 "retina" display, Apple claims a 2x improvement in GPU performance through the A6X SoC. The previous generation chip, the A5X, had two ARM Cortex A9 cores running at 1GHz paired with four PowerVR SGX 543 cores running at 250MHz. The entire SoC integrated 4 x 32-bit LPDDR2 memory controllers, giving the A5X the widest memory interface on a shipping mobile SoC in the market at the time of launch.

The A6X retains the 128-bit wide memory interface of the A5X (and it keeps the memory controller interface adjacent to the GPU cores and not the CPU cores as is the case in the A5/A6). It also integrates two of Apple's new Swift cores running at up to 1.4GHz (a slight increase from the 1.3GHz cores in the iPhone 5's A6). The big news today is what happens on the GPU side. A quick look at the GLBenchmark results for the new iPad 4 tells us all we need to know. The A6X moves to a newer GPU core: the PowerVR SGX 554.

Mobile SoC GPU Comparison
  PowerVR SGX 543 PowerVR SGX 543MP2 PowerVR SGX 543MP3 PowerVR SGX 543MP4 PowerVR SGX 554 PowerVR SGX 554MP2 PowerVR SGX 554MP4
Used In - iPad 2 iPhone 5 iPad 3 - - iPad 4
SIMD Name USSE2 USSE2 USSE2 USSE2 USSE2 USSE2 USSE2
# of SIMDs 4 8 12 16 8 16 32
MADs per SIMD 4 4 4 4 4 4 4
Total MADs 16 32 48 64 32 64 128
GFLOPS @ 300MHz 9.6 GFLOPS 19.2 GFLOPS 28.8 GFLOPS 38.4 GFLOPS 19.2 GFLOPS 38.4 GFLOPS 76.8 GFLOPS

As always, Imagination doesn't provide a ton of public information about the 554 but based on what I've seen internally it looks like the main difference between it and the 543 is a doubling of the ALU count per core (8 Vec4 ALUs per core vs. 4 Vec4). Chipworks' analysis of the GPU cores helps support this: "Each GPU core is sub-divided into 9 sub-cores (2 sets of 4 identical sub-cores plus a central core)."

I believe what we're looking at is the 8 Vec4 SIMDs (each one capable of executing 8+1 FLOPS). The 9th "core" is just the rest of the GPU including tiler front end and render backends. Based on the die shot and Apple's performance claims it looks like there are four PowerVR SGX554 cores on-die, resulting in peak theoretical performance greater than 77 GFLOPS.

There's no increase in TMU or ROP count per core, the main change between the 554 and 543 is the addition of more ALUs. There are some more low level tweaks which helps explain the different core layout from previous designs, but nothing major.

With that out of the way, let's get to the early performance results. We'll start with low level fill rate and triangle throughput numbers:

GLBenchmark 2.5 - Fill Test

Fill rate goes up by around 15% compared to the iPad, which isn't enough to indicate a huge increase in the number of texture units on the 554MP4 vs. the 543MP4. What we may be seeing here instead are benefits from higher clocked GPU cores rather than more texture units. If this is indeed the case it would indicate that the 554MP4 changes the texture to ALU ratio from what it was in the PowerVR SGX 543 (Update: this is confirmed). The data here points to a GPU clock at least 15% higher than the ~250MHz in the 3rd generation iPad.

GLBenchmark 2.5 - Fill Test (Offscreen 1080p)

GLBenchmark 2.5 - Triangle Texture Test

Triangle throughput goes up by a hefty 65%, these are huge gains over the previous generation iPad.

GLBenchmark 2.5 - Triangle Texture Test (Offscreen 1080p)

GLBenchmark 2.5 - Triangle Texture Test - Fragment Lit

The fragment lit triangle test starts showing us close to a doubling of performance at the iPad's native resolution.

GLBenchmark 2.5 - Triangle Texture Test - Fragment Lit (Offscreen 1080p)

GLBenchmark 2.5 - Triangle Texture Test - Vertex Lit

GLBenchmark 2.5 - Triangle Texture Test - Vertex Lit (Offscreen 1080p)

GLBenchmark 2.5 - Egypt HD

Throw in a more ALU heavy workload and we really start to see the advantage of the new GPU: almost double the performance in Egypt HD at 2048 x 1536. We also get performance that's well above 30 fps here on the iPad at native resolution for the first time.

GLBenchmark 2.5 - Egypt HD (Offscreen 1080p)

Normalize to the same resolution and we see that the new PowerVR graphics setup is 57% faster than even ARM's Mali-T604 in the Nexus 10. Once again we're seeing just about 2x the performance of the previous generation iPad.

GLBenchmark 2.5 - Egypt Classic

Vsync bound gaming performance obviously won't improve, but the offscreen classic test gives us an idea of how well the new SoC can handle lighter workloads:

GLBenchmark 2.5 - Egypt Classic (Offscreen 1080p)

For less compute bound workloads the new iPad still boasts a 53% performance boost over the previous generation.

Ultimately it looks like the A6X is the SoC that the iPad needed to really deliver good gaming performance at its native resolution. I would not be surprised to see more game developers default to 2048 x 1536 on the new iPad rather than picking a lower resolution and enabling anti-aliasing. The bar has been set for this generation and we've seen what ARM's latest GPU can do, now the question is whether or not NVIDIA will finally be able to challenge Imagination Technologies when it releases Wayne/Tegra 4 next year.

POST A COMMENT

113 Comments

View All Comments

  • CeriseCogburn - Tuesday, November 06, 2012 - link

    In this former review, when APPL claimed 4x the performance, it was noted the glbench gave APPL a large advantage, but the CPU tests gave nVidia just as large a win.

    So they ran a game (also reviewed here, with nVidia declared the winner).

    http://www.zdnet.com/blog/hardware/a5x-vs-tegra-3-...

    So this glbench is a way to skew real life performance toward APPL in that case, and I'd bet this one as well.

    Not like it's realistic, as the same thing before felled APPL down to "equal in real life", so skepticism instead of blind allegiance is required here.

    Enjoy the link that exposes the former lies and spin, likely directly related to this opening look.
    Reply
  • andsoitgoes - Saturday, November 10, 2012 - link

    "It's worth noting that neither Shadowgun nor Riptide has yet been optimized for the A5X chip, so it's possible that developers will be able to squeeze more power from the A5X in a later update."

    It's like running an Xbox game on an Xbox and an Xbox 360. This wasn't remotely a comparison that would show anything at all.

    The games were tested almost at launch of the retina iPad, win a processor and GPU that were just enough to push the screen without providing the same kind of gains that we get now. Now if we were to have that game optimized for the chipset it is running on, then we would see some real numbers.

    But as of now, like I said, you've got a game designed to support all manner of much older devices, hell the game probably runs great on the iPhone 4 or the iPad 2. That's the thing with the game developers, they are amazing at refining the game so it will run like butter across the platforms.

    It's interesting, Shadowgun was updated to support the bees knees of the chip in April. Take both of those systems and run the game then. Riptide was updated 11 days after that.

    Until that's done, it's a fartshoot.
    Reply
  • augiem - Friday, November 02, 2012 - link

    That's great from a manufacturing standpoint. They can use a smaller battery. Ultimately, that benefits the consumer by allowing the tablets to be lighter and somewhat cheaper. But it doesn't help those chasing the high-end of performance. And unfortunately, overall the Nexus 10's battery life isn't that competitive to iPad 4 even with more efficiency. (8.? hours vs 11.? I think it said) Reply
  • CeriseCogburn - Tuesday, November 06, 2012 - link

    That's pretty close actually, so what's the RECHARGE TIME differences ?

    Does the APPL take forever to recharge the giant battery in comparison ?

    LOL - very important - as downtime is critical.

    Might be wise to know that answer before declaring 11 big battery is better than 8 small battery.
    Reply
  • andsoitgoes - Saturday, November 10, 2012 - link

    But if your downtime is slightly longer while your run time is dramatically longer, it's 6 of one, a fart in a bucket in the other.

    The thing with the new iPad is the 12w power adapter. It takes 6 hours from dead, to give 11-12 hours of run time.

    Actually some other people have reported just a smidge over 5 hours.

    Is the nexus faster? What charger did it include with it? I can't find charge numbers for the 10 so...
    Reply
  • doobydoo - Saturday, November 03, 2012 - link

    'Nexus 10 uses a 22% smaller battery, and powers 33% more pixels, and yet it only has 6% lower battery life than the iPad. If you normalize those numbers, then the iPad's GPU is 50% more inefficient (or Mali T604 is 30% more efficient than iPad's GPU).'

    Um, no, because when the iPad is powering those 33% more pixels it's doing so at least 50% faster.
    Reply
  • andsoitgoes - Saturday, November 10, 2012 - link

    *slow clap of awesomeness*

    Thank you for being smarter than me and saying those awesome words.
    Reply
  • djgandy - Monday, November 05, 2012 - link

    Nexus 10 has a much dimmer display too. You missed that bit. Reply
  • BlendMe - Monday, November 05, 2012 - link

    Not only that. The Nexus has an AMOLED screen as opposed the the iPad's IPS panel. Reply
  • Aenean144 - Monday, November 05, 2012 - link

    All of the current Nexii has LCDs. The Nexus 4 and 7 have IPS displays while the Nexus 10 has a PLS display. They are all LCD technology, not AMOLED tech.

    Like everyone else, the display is the number one user of power in a tablet or phone. For 10 inch sizes, it's probably 70% to 80% of the power consumption.
    Reply

Log in

Don't have an account? Sign up now