Consider a simple in-order processor with the following characteristics: Consists of a pipeline where one instruction is issued each cycle if possible. • An instruction can issue once all of its dependencies are satisfied. • There is no limit to the number of functional units. • Do not assume all operands are read prior to any being written in a given cycle. Given the following sequential list of instructions and instruction latencies: A. 1dw $r5 = 12[$r8] B. stw 8[$r2] = $r7 c. 1dw $r2 = 4[$r4] D. stw 12[$r8] = $r2 Instruction Latency add sub 1dw stw mpy 2 2 5 7 1. What is the CPI for sequential execution of the code with no data speculation? 2. Create a new schedule to maximize instruction level parallelism (ILP) using instruction scheduling and data speculation, but without register renaming. o Please maintain the original ordering of the instructions. Make sure you include appropriate latencies in the provided schedule. o Calculate the new CPI, assuming no data speculation overhead and that the two locations did not collide

Consider a simple in-order processor with the following characteristics: Consists of a pipeline where one instruction is issued each cycle if possible. • An instruction can issue once all of its dependencies are satisfied. • There is no limit to the number of functional units. • Do not assume all operands are read prior to any being written in a given cycle. Given the following sequential list of instructions and instruction latencies: A. 1dw $r5 = 12[$r8] B. stw 8[$r2] = $r7 c. 1dw $r2 = 4[$r4] D. stw 12[$r8] = $r2 Instruction Latency add sub 1dw stw mpy 2 2 5 7 1. What is the CPI for sequential execution of the code with no data speculation? 2. Create a new schedule to maximize instruction level parallelism (ILP) using instruction scheduling and data speculation, but without register renaming. o Please maintain the original ordering of the instructions. Make sure you include appropriate latencies in the provided schedule. o Calculate the new CPI, assuming no data speculation overhead and that the two locations did not collide

C++ for Engineers and Scientists

4th Edition

ISBN:9781133187844

Author:Bronson, Gary J.

Publisher:Bronson, Gary J.

Chapter2: Problem Solving Using C++using

Section2.3: Data Types

Problem 9E: (Practice) Although the total number of bytes varies from computer to computer, memory sizes of...

See similar textbooks

Similar questions

5-Consider a computer running a program that requires 400 s, with 80 s spent executing FP instructions, 40 s executed L/S instructions, and 40 s spent execut- ing branch instructions. • By how much is the total time reduced if the time for FP operations is reduced by 5%? • By how much is the time for INT operations reduced if the total time is reduced by 5%? • Can the total time can be reduced by 10% by reducing only the time for branch instructions?
Multicycle execution is better than single cycle execution since it is: a. Every operation is completely carried out within a single clock cycle b. Break up operation so that each stage is executed in 1 clock cycle and allow skipping of unused stages. c. The maximum clock frequency is determined by the slowest instruction in the instruction set. d. A form of parallelism since more than one instruction is executed by the processor in any given cla
A program is profiled on a CPU: 20% of all instructions are arithmetic, 40% are load, 20% are store, 20% are conditional branches. On this CPU, loads take 4 cycles, stores 1 cycle, ALU instructions 2 cycle, and branches 3 cycles. Compute the CPI for each instruction and the average CPI for that program on that CPU: Compute the CPI for each instruction (GIVE ANSWERS WITH 2 DECIMAL DIGITS: CPI for loads is CPI for stores is CPI for ALU is CPI for branches is Average CPI is
Question Q: For a basic computer that is currently running in its timing TO of execution for an instruction that is located in memory location 366. The content of AC is (212) and the content of memory locations are as follow: [memory location: content]: [365:9473], [366:7010], [367:5431], [368:4620], [431:1A23], [620:C80D]. Answer the following questions that examine the contents of PC, AR, AC, DR and IR after the end of execution for the next instruction. (Note: all numbers are in Hexadecimal.) p 4:33 The content of AC after the end of * :execution for the next instruction is 700 O 620 320 O None of the choices O 4:35 /
1. Consider a machine running a program with four classes of instructions: A/B/C/D. The program requires 360 seconds, with the number of seconds executing each class as shown in the table below: Instruction Class A B C Time (sec) 100 80 120 60 1.1. By how much is the total execution time changed if the time for class D is reduced by 20% and the time for class C is increased by 10% (assuming no other changes)? 1.2. If we want to reduce the total execution time by 20% by optimizing class A only, what is the target execution time of class A instructions in order to achieve the reduction (assuming all other instructions are not changed)? 1.3. Can the total time be reduced by 25% if we only optimize class B? Use calculation to justify your answer.
Single instruction computer (SIC) has only one instruction that for all operations our MIPS does. The instruction has the following format. sbn a, b, c # Mems[a]=Mem[a]- Mem[b]; if (Mem[a]<0) go to PC+c For example, here is the program to copy a number from location a to location b: Start: sbn temp, temp, 1 sbn temp, a, 1 sbn b, b, 1 sbn b, temp, 1 So build SIC program to add a and b, leaving the result in a and leaving b unmodified.
Q1. Compute the effective CPI for an implementation of a RISC-V CPU using The Figurel. Assume we have made the following measurements of average CPI for instruction types: Instruction All ALU operations Loads Stores Branches Jumps Program astar bzip gec gobmk h264ref hmmer libquantum mcf omnetpp perlbench sjeng xalancbmk Loads 28% 20% 17% 21% 33% 28% 16% 35% 23% 25% 19% 30% Stores 6% 7% 23% 12% 14% 9% 6% 11% 15% 14% 7% 8% Clock cycles 1.1 4.2 3.3 2.8 3.0 Branches 18% 11% 20% 14% 5% 17% 29% 24% 17% 15% 15% 27% Jumps 2% 1% 4% 2% 2% 0% 0% 1% 7% 7% 3% 3% ALU operations 46% 54% 36% 50% 45% 46% 48% 29% 31% 39% 56% 31% Average the instruction frequencies of astar and perlbench to obtain the instruction mix.
Consider a hypothetical computer having instruction length 32 bit and Byte addressable memory. You need to run a program P having 10 Q.4 CO4 instructions 11,12,13...10. All the instructions are stored in consecutive memory locations started from 1000. To run an instruction li, you have to complete four operations: Fetch, Decode, Execute, and Store. The content of Program Counter will be after the completion of fetch operation of instruction 12. There are no jump or branch instruction in program P
A given processor has 32 registers, uses 16-bit immediate numbers and has 142 instructions in its ISA. In a given program:• 20 % of the instructions take 1 input register and have 1 output register,• 30 % have 2 input registers and 1 output register,• 25 % have 1 input register, 1 output register and take an immediate input as well,• and the remaining 25 % have one immediate input and 1 output register.a) For each of the 4 types of instructions, how many bits are required? Assume that the ISA requires that allinstructions be a multiple of 8 bits in length.b) How much less memory does the program take up if variable-length instruction set encoding is used asopposed to fixed-length encoding?
one Mil Q#1: Consider the instruction: add $2, $1, $3 What registers will be written and what registers will be read to execute this instruction? Registers to be written Registers to be read Q#2: Since we only support the add instruction, we don't care much for opcodes and funct codes and shamts. Therefore, suppose our programs are given to the processor as three inputs RD, RS, and RT. Each instruction executes within 1 clock periods Translate the following program to the RW, RS, RT inputs (in binary). clock period RD RS 1 2 3 4 RS RT Program add $2, $1, $3 add $0, $0, $1 add $1, $2, $2 add $1, $1, $1 Q#3: Design the single-cycle cessor datapath (only ID, EX and WB stages) using the mong different components. following datapath components.rly s the number of bits to be transferred in each data line and data bus connectio RD cik Registers RA RB RW BusA RegWrite Bus8 Bus W ALU zero ALU result overflow RT ALUOP
H.W.: Consider a hypothetical machine with two steps instruction cycle: fetch cycle and execute cycle. The characteristics of the machine is given in Figure 8 with the following explanation: The processor contains a single data register, called an accumulator (AC). • Both instructions and data are 8 bits long. • The memory is organized using 8-bit words. • The instruction format provides 2 bits for the opcode, and up to 26 = 64 words of memory can be directly addressed. Opcode Address (a) Instruction format Magnitude (b) Integer format Program counter (PC)= Address of instruction Instruction register (IR)- Instruction being executed Accumulator (AC) Temporary storage (c) Internal CPU registers -Load AC from memory Store AC to memory - Add to AC from memory (d) Partial list of opcodes Figure 8 Characteristics of a Hypothetical Machine Figure 9 illustrates a partial program execution, showing the relevant portions of memory and processor registers after the first instruction, 64H has…
3. Consider a pipeline in a processor that has 5 stages: (1) instruction fetch – 120 ns, (2) instruction decode – 30 ns (3) memory read – 80 ns (4) instruction execution – 30 ns and (5) register write – 80 ns. The times required in each stage are shown above following the name of the stage. For example, the instruction fetch requires 120 ns to complete. Assume that every instruction in the instruction set requires the use of all stages of the pipeline. Also assume that the stages of the pipeline are clocked with a common clock. This means that all information moves synchronously through the pipeline from one stage to the next based on a single clock signal dictating when information advances from one stage to the next. (0) Identify the execution time of a 5000-instruction program without pipelining. What can you infer on the latency of an instruction flowing through the pipeline? (Remember that you have a common clock) Since all stages of the pipeline are clocked with a single clock,…