Or this problem you will calculate the accuracy and performance impacts of branch prediction techniques for a specific situation: consider our pipelined processor, assume branch outcome is determined in the reg stage, and assume branch prediction (and instruction cancelling, when appropriate) is used to resolve control hazards. also assume: branch instructions are 15% of the executed instructions in assembly language programs. the remainder are instructions that perform calculations (data instructions). data hazards affect both branch and data instruction performance. consider data instructions and branch instructions that do not have control hazard delays (correctly predicted branch instructions). assume these instructions have an average cpi of 1.25 (due to data hazards). control hazards also affect performance, but i'm not going to directly give you this number. instead, consider all instructions (including incorrectly predicted branches). assume overall average cpi for all instructions is 1.30. for this problem, don't worry about jump instructions. for control hazards, you will need to consider delays imposed by incorrectly predicted branches. (a) what is the accuracy of the branch predictor? hints: write the algebra formula for a weighted average using the information above. the number of cycles for branch instructions with failed predictions is: 1.2 + some stall penalties). you should have one unknown. (b) assume the branch predictor always predicted that branches are taken. for this situation, would it be better for the branch predictor to predict that branches are not taken? show the math that justifies your answer. (c) advanced: would performance improve if the branch predictor changed future predictions when it is wrong? (if it predicted 'not taken' but the branch was taken, it would predict 'taken' until it is wrong again.) either show the math that justifies your answer, or establish a sound argument for your answer.