But the workloads when it is faster? I'm very impressed with AMD's offering.
Have code thats largely complex branch and loop conditions that bust the branch predictor's balls and isn't cache friendly and is largely integers? Bulldozer eats it for breakfast and asks for more.
Have code thats largely complex branch and loop conditions that bust the branch predictor's balls and isn't cache friendly and is largely integers? Bulldozer eats it for breakfast and asks for more.