CPU Benchmarks: PCMark And Sandra 2012
PCMark favors Intel hardware—perhaps unfairly. What puzzles us is that the A10-4600M seems to perform really close to (and sometimes better than) Intel’s Core i5-2450 in all of the individual metrics, and yet the aggregate score is much lower.
The Core i5-2450M takes a huge lead in Sandra’s Arithmetic module, and iSSE4.2 extensions don’t even help the A10-4600M all that much. The A8-3500M is far behind the competition.
Bear in mind that we don’t draw conclusions based on diagnostic tests like Sandra. Of course, we’re interested in evaluating potential performance. But our real-world results are what we use to make recommendations.
The addition of FMA3 isn’t enough to push the A10-4600M past Intel’s Core i5-2450M.
The Sandra Cryptography result is surprisingly close, likely a result of AES-NI support on both the Trinity- and Sandy Bridge-based parts. The A8-3500M isn’t in the running.
AMD’s Trinity design shows off in Sandra’s GPGPU/GPCPU Cryptography benchmark, beating out Llano and embarrassing Sandy Bridge. Both APUs benefit from native OpenCL support enabled through AMD’s driver. Sandy Bridge, meanwhile, can only emulate support on its x86 processing cores.
Sandra’s memory bandwidth result seems low for Trinity and Llano, though we’ve seen this diagnostic report back inaccurate results, particularly on just-released hardware.
BTW, Charlie @ SemiAccurate is not an AMD fanbois IME. He just calls it like it is. Reality bites sometimes be it Nvidia, AMD or Intel's problems. Denial never changes reality. It is what it is.
A10-4600M laptops will be int eh $600-$700 neighborhood, and we're still waiting for Ivy bridge Core i5 to arrive in this price range.
We go over this. We also talk about how we'll do a follow up as soon as an appropriate product is available.
You need to read for it to make sense.
In a related question, does Trinity's details and specs lead to any conclusions about what Piledriver desktop processors will be like?