Doing performance work with GPUs is harder than with CPUs because of the asynchronous and massively parallel architecture.
PIX - can do timing of Direct3D calls. Works reasonably well with Firefox.
NVIDIA PerfHUD - last I checked required a special build to be used.
AMD GPU ShaderAnalyzer - will compile a shader and show the machine code and give static pipeline estimations. Not that useful for Firefox because all of our shaders are pretty simple.