Looking at the long term future of the market, Broadcom's move isn't surprising at all. Broadcom (and Qualcomm for that matter) is feeling a lot of pressure from Intel and NVidia, both of whom have a lot of new stuff that are scaring competitors (which is fucking great for us). They're scared not from just a technological or capital/market perspective, but also from a community exposure one. They're both firing on all cylinders right now improving their technology and trying to get as many engineers to use it as possible. While firmware engineers tend to be older, there is a constant cycle and the industry is starting to see the importance of open source, especially as die complexity grows and more and more testing is required for each silicon design.
Intel: 2.5W TDP quad core Atoms with Intel's x86 instruction pipeline and memory management unit have been released as well as a low cost SDR that should be able to dynamically switch between unlicensed, GSM, CDMA, and LTE spectrum. Intel's graphics work is also quickly catching up and will soon start trickling into their low power embedded chips. Intel has also made clear moves with Galileo to open up their technology to the hobbyist engineers.
NVIDIA: The Tegra K1 is out to NVIDIA's partners (supposedly it beats VideoCore and even low end integrated desktop graphics) and they are currently being worked into tablets. NVIDIA also has recently released the i500, their own software defined radio to compete with Intel, and both companies have the resources to end the lock-in that Qualcomm and Broadcom have had in their respective baseband markets. If you're already buying radios from them, it makes sense to get your processor from them too and Broadcom may be trying to hedge against that.
NVIDIA (and maybe Intel) aren't known to be pioneers of open source but they're better than most other Silicon companies and everyone else is really starting to feel the pressure. The problem of supporting many different device configurations is an old one on desktop systems and that problem is only magnified 10x for embedded engineers because of the opacity. With Intel and NVIDIAs expertise on the desktop as they're running full steam ahead into embedded (and kicking ass along the way), they're scary to the old guard.