(Solved): Assume a processor with instruction frequencies and costs (number of clock cycles): - Integer ALU: ...

Assume a processor with instruction frequencies and costs (number of clock cycles): - Integer ALU: 50\%, 1 cycle - Load: $20\%,5$ cycle - Store: $10\%,1$ cycle - Branch: 20\%, 2 cycle Assume the clock period remains the same, which change would improve performance more? (1) Branch prediction to reduce branch cost to 1 cycle (2) A bigger data cache to reduce load cost to 3 cycles.