A processor chip is used for an application in which 30% of execution time is spent on floating-point addition. For the new model, the design team redesigns the floating-point adder to make it twice as fast. What is the maximum possible speed-up from this redesign?
Pick an option to check yourself, or open the answer below.
Show answer & explanation
Correct answer: C. 1.18
Explanation
By Amdahl's law, speed-up = 1 / (0.7 + 0.3/2) = 1/0.85 ≈ 1.18.More Computer System Architecture questions
- A 256 Mb DRAM is organised as a 32M × 8 memory externally and as a 16K × 16K square array internally. Each row must be refreshed at least o…
- The instruction LD ADR(X), equivalent to AC ← M[ADR + XR], is in:
- The instructions ADD R1, A, B ADD R2, C, D MUL X, R1, R2 evaluate X = (A + B) * (C + D) using which of the following?
- The Boolean expression for F(A, B, C) = Σm(0, 2, 6) with don't-cares d(A, B, C) = Σ(1, 3, 5) would be:
- A computer system has a cache access time of 100 ns, a main-memory access time of 1100 ns and a hit ratio of 0.9. The average access time w…
- Match List I (Boolean expression) with List II (dual of the Boolean expression)List I List II A. x·y + 0 I. (x̄ + 0)·(ȳ·z) B. x̄·1 + (ȳ + z…