(A) In this exercise we look at memory locality properties of matrix computation. The following code iswritten in C, where elements within the same row are stored contiguously. Assume each word is a 64-bitinteger.for (I-0; I<8; I++)for (J-0; J<8000; J++)A[I] [J]-B [I] [0] +A[J] [I];1. How many 64-bit integers can be stored in a 16-byte cache block?2. Which variable references exhibit temporal locality?3. Which variable references exhibit spatial locality?(B) Locality is affected by both the reference order and data layout. The same computation can also bewritten below in Matlab, which differs from C in that it stores matrix elements within the same columncontiguously in memory.1. How many 64-bit integers can be stored in a 16-byte cache block?2. Which variable references exhibit temporal locality?3. Which variable references exhibit spatial locality?4. How many 16-byte cache blocks are needed to store all 64-bit matrix elements being referenced usingMatlab's matrix storage? How many using C's matrix storage? (Assume cach row contains more thanone element.)

*As per the guideline in case of multiple question only 1 question can be answered* Please find the…

(A) In this exercise we look at memory locality properties of matrix computation. The following code is written in C, where elements within the same row are stored contiguously. Assume each word is a 64-bit integer. for (I-0; I<8; I++) for (J-0; J<8000; J++) A [I] [J]-B [I] [0] +A[J] [I]; 1. How many 64-bit integers can be stored in a 16-byte cache block? 2. Which variable references exhibit temporal locality? 3. Which variable references exhibit spatial locality?

(A) In this exercise we look at memory locality properties of matrix computation. The following code is written in C, where elements within the same row are stored contiguously. Assume each word is a 64-bit integer. for (I-0; I<8; I++) for (J-0; J<8000; J++) A [I] [J]-B [I] [0] +A[J] [I]; 1. How many 64-bit integers can be stored in a 16-byte cache block? 2. Which variable references exhibit temporal locality? 3. Which variable references exhibit spatial locality?

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Similar questions

4. The figure below shows an 8-way interleaved, byte-addressable memory. The total size of the memory is 4 KB. The elements A[i]G) of a 2-dimensional array A are 4-bytes (one-word) in length and can be stored in the memory as shown, where 0 < ij <7. The width of the bus between CPU and memory is 32 bits, that is, it can carry only one word at a time. Bank 1 Bank 7 Bank 0 31 7 A[7][0] A[I][0] A[0]|0] 32 A[7]1] 64 A[7]|2] A[I][2] A[0||2] RANKO 255 224 AI기기 A[I][7] A[0||7) RANKN ...... Since the address space of the memory is 4 KB, 12 bits are needed to uniquely identify each memory location, i.e., Addr[11:0]. Find out and explain which bits of the address will be used for: • Byte on bus: Addr […... :...] Bank index bits within a bank: Addr [.... .] • Chip select address bits within a rank: Addr […... .] • Rank bits: Addr […... :....]
What is the address of (int) m[i][j] in terms of the base address and COLS? What are potential problems with <code>strcpy()</code> and <code>strcat</code> Why does <code>scanf()</code> take a pointer?
Write the compiled MIPS code of the following C code: While (vector[j] != M) j += 1; Variables į in $3, M in Ss5, base address of Array vector in $s6
in c++ In a 2D integer array TD, assume that the row indices range from -3 to 7 and column indices range from 6 to 14. An element TD [-3, 6] stored at address 3220. Find out the dimension of TD and address of an element TD [2, 10], if TD stores the elements in column major order.
Exercise 1: Write the compiled MIPS code of the following C code: While (vector[j] != M) j+= 1; Variables j in $s3, M in $s5, base address of Array vector in $s6
MPI Programming: Write a MPI program in C/C++ to multiply two n-by-n matrices using p processors organized ina ring network with 1 ≤ p ≤ 12. Use the algorithm laid out here: P0 will generate and send ith row-band of Aand ith row-band of BT (the transpose of matrix B) to Pi, 1 ≤ i ≤ p − 1 (thus, space allocated should only be toaccommodate row-bands of A, BT and C). To compute their row-bands of product matrix C, the processors willuse p steps of computation (multiplying row-bands of A and BT producing a block of row-band of C) and (p-1)steps of communication (sending the row-band of BT to the right neighbor and receiving from the left neighbor).You must only use send/receive primitives. P0 finally receives the ith row-bands of product matrix C from Pi,1 ≤ i ≤ p − 1, and prints it out.
Please help me Translate the following C code to MIPS. Assume A is an array of 32-bit integers, the address of A is in $s0, i is in $s1, and d is in $s2. A[i] = A[i-1] + A[i-2] - d;
Write the compiled MIPS code of the following C code: While (vector[j] < M) j =j+M; Variables j in $s3, M in $s5, base address of Array vector in $s6
For a two-dimensional array in C as follows (Each long double-type element occupies 10 bytes of memory). long double A[N][M]; If the base address of A in memory is SO, what is the memory address of A[i][j](just write the formula)?
UAA: [109, 105, 114, 122, 97, 98, 101]Use C++ if programmed <-- not required to. Using your UAA, apply the Lomuto’s Partioning Algorithm. Write the initial array and trace the content of the array and the positions of the indices (s, i) for each iteration in i, and for the final swap.
Consider two integer arrays B and D of 100 elements. Let X2 and X3 contain the base address of array "B" and "D", respectively, and the index į is in X0, h is in X10. Write LEGV8 code to perform the following operations: (a) Get B[15] from memory and put it in register X5. (b) Put the value 132 in D[6]. (c) Translate the following C code into LEGv8 instructions int j = 50, h; do { D[2*j] = (B[j] + B[j+2])*9 - h; j^j -2; while {j >0}; DO NOT use multiply instruction in your code, use shift instruction for multiplication instead! (d)How many instructions are executed during the running of the code in (c), and how many memory data references are made during executio'n?
Assume that the arrays uses a row-major if it is an even dimension and uses column-major if it is odd dimension way of accessing the elements. If the array has multiple dimensions all the dimensions should be either odd or even. Write the SDT's to generate 3-address code for such an array and use it to generate three address code for the following: x = a[i]li] + b(i]ljl %3D