The real gains to be had are to be seen with Kaveri APU and beyond. Why else would this article be more about AMD's involvement in optimizing LibreOffice for APUs than general improvements for all platforms, were it not for the extra performance gains - above all competition - that will be happening on AMD products on LibreOffice through HSA and hUMA. Heck, it's made pretty clear in the below quote:
"Bringing the parallelism and performance of our technology to traditional, mainstream business software users will be a welcome innovation for heavy duty spreadsheet users, particularly when combined with the compute capabilities of the upcoming generation of AMD Heterogeneous System Architecture (HSA) based products."
This venture is just an example of a revolution in computing at its beginning. HSA and hUMA will bring performance wonder by enabling what is beyond OpenCL performance addition possible through new options enabled by the memory coherency, and the relatively easy coding (compared to any traditional GPU language). If an A10-6800k on a program with traditional OpenCL implementation will outperform a 3960x at stock, a Kaveri A10 on a program with HSA implementation will go even further than that.
The first of these code changes will show up in LibreOffice 4.1 in about a month, but it will take about six months to get substantial benefits to users.
I reckon that this line is actually referring to the Kaveri APU release, which we're about 6 months away from. While the whole program is slated to be more efficient, there's definitely going to be a particular advantage with HSA and hUMA to make AMD the point of this article and Document Foundation's original press release.