We will compare the performance of a vector processor

Assignment Help Basic Computer Science

Reference no: EM13166933

In this problem, we will compare the performance of a vector processor with a hybrid system that contains a scalar processor and a GPU-based coprocessor. In the hybrid system, the host processor has superior scalar performance to the GPU, so in this case all scalar code is executed on the host processor while all vector code is executed on the GPU. We will refer to the first system as the vector computer and the second system as the hybrid computer. Assume that your target application contains a vector kernel with an arithmetic intensity of 0.5 FLOPs per DRAM byte accessed; however,

the application also has a scalar component which that must be performed before and after the kernel in order to prepare the input vectors and output vectors, respectively. For a sample dataset, the scalar portion of the code requires 400 ms of execution time on both the vector processor and the host processor in the hybrid system. The kernel reads input vectors consisting of 200 MB of data and has output data consisting of 100 MB of data. The vector processor has a peak memory bandwidth of 30 GB/sec and the GPU has a peak memory bandwidth of 150 GB/sec. The hybrid system has an additional overhead that requires all input vectors to be transferred between the host memory and GPU local memory before and after the kernel is invoked. The hybrid system has a direct memory access (DMA) bandwidth of 10 GB/sec and an average latency of 10 ms. Assume that both the vector processor and GPU are performance bound by memory bandwidth. Compute the execution time required by both computers for this application?

Reference no: EM13166933

Questions Cloud

Manual park button and the application accurately : As an application tester, I want to press the manual park button and the application accurately records the location of the intended vehicle. The ratio of successes to failures will be recorded to report to the development team.

C program to mips program : Convert the following C program to MIPS program. Assuming that i, j, k, f, are stored in registers $s0, $s1, $s2, $s3 already. The base address of arrays A and B are in registers $s4 and $s5, respectively. (30

Speedy spuds is a fast-food restaurant : Speedy Spuds is a fast-food restaurant offering all kinds of potatoes. The manager has a 30-second rule for serving customers. Servers at the counter say they could achieve that rule if the form they must fill out and give to the kitchen crew were si..

2n-1 comparisons are necessary in the worst case : Prove that 2n-1 comparisons are necessary in the worst case to merge two sorted lists containing n elements each.

We will compare the performance of a vector processor : In this problem, we will compare the performance of a vector processor with a hybrid system that contains a scalar processor and a GPU-based coprocessor.

One or more consecutive white spaces is a delimiter : Write a function which will determine how many words are in a given string. assume that one or more consecutive white spaces is a delimiter between words.

Pseudocode int an iterative one : Turn the following pseudocode int an iterative one, Assuming k is in T: if k is in T, Insert should change its associated item to x.

Design a circuit with 3 inputs : Design a circuit with 3 inputs (x,y,z) representing the bits in a binary number, and three outputs (a,b,c) also representing bits in a binary number. When the input is 1,2,3, the binary output should be one less than the inpu

Provide a recursive definition of sequence s : provide a recursive definition of sequence S of all Binary strings starting with 1. Include the base case, recursion and restriction.

User Account

All Pages