C952 Computer Architecture PGKO Pre-Assessment Practice
What are two benefits of using virtual machines? Choose 2 answers. a) Software abstraction b) Hardware separation c) Disk failure rates lowered d) Memory hierarchy can be ignored * Use commas between letters: "a, b, c, ..."
a, b
Which three components or aspects specify the statement of a virtual machine? a) Page table b) Program counter c) Registers d) Secondary storage cache e) Translation-lookaside buffer (TLB) f) System call * Use commas between letters: "a, b, c, ..."
a, b, c
A company needs the ability to host a low-cost network of servers and thin clients that host different operating systems needed to support differing applications. Which solution will meet these needs? a) RAID b) Hypervisor c) RISC architecture d) Instruction-level parallelism
b
A program requires one billion instructions to execute on a processor running at 4 GHz. Exactly 50% of the instructions execute in three clock cycles, 30% execute in four clock cycles, and 20% execute in five clock cycles resulting in an execution time of 1.075 seconds. Which adjustment improves overall performance by 12%? a) 30% execute at three cycles and 70% at four cycles b) 70% execute at three cycles and 30% at four cycles c) 100% execute at three cycles d) 100% execute at four cycles
b
A program runs alone on a CPU. The CPU clock rate is 3e9 cycles per second, i.e., 3 GHz. It takes the CPU 15e9 clock cycles to complete the program. The CPU clock cycle time is 500e-12 second, i.e., 500 picoseconds. How many seconds is the CPU performance for the task? a) 1.5 b) 7.5 c) 15 d) 75
b
Given four sets of ARM instructions that take the same amount of time and processing power to execute. How much faster would the instructions complete if executed 1,000 times using a pipelining methodology? a) 2 times b) 4 times c) 8 times d) 16 times
b
The manufacturing process for producing a widget has 5 steps and each step in the process takes one day. What is the average number of days needed to manufacture each widget using a pipelined process to produce 10 widgets? a) 0.5 b) 1.4 c) 5 d) 14
b
What is an advantage of implementing cloud computing? a) It offers scheduled scaling. b) It provides automatic scaling. c) It provides local hosting by self-detection. d) It offers additional services by self-detection.
b
What is an advantage of using virtual memory technique? a) It increases the size of the primary memory available. b) It permits a program to exceed the size of primary memory. c) It shares a virtual address with the same physical address. d) It allows reading and writing to main memory in virtual machines.
b
What is meant by pipelining in computer architecture? a) It compensates for a serial portion of the program that would otherwise limit scalability. b) It employs an implementation technique where multiple instructions are overlapped in execution. c) It increases the size of the problem proportionally to the increase in the number of processors.
b
What is the final value in X10 when the following code completes, given that X6 contains 20, X7 contains 10, and X8 contains 20? SUB X9, X7, X6 CBZ X6, AAA ADD X9, XZR, #1 B ZZZ AAA SUB X9, X8, X6 CBNZ X6, ZZZ ADD X9, XZR, #2 ZZZ ADD X10, XZR, X9 a) 0 b) 1 c) 2 d) 3
b
Which computer architecture idea is analogous to the assembly line? a) Dependability via parallelism b) Performance via pipelining c) Performance via prediction d) Dependability via redundancy
b
Which feature of the IBM 360/91 was incorporated into the majority of microprocessors developed in the 21st century? a) Branch prediction allowed the processor to proceed with the next instruction. b) Algorithm innovations allowed the improved parallel execution of instructions. c) Pipeline innovations allowed for reservation stations and the commit unit. d) Pipeline innovations allowed for dynamically scheduled pipelined processors.
b
Which set-associative cache will improve overall performance? a) One-way b) Two-way c) Six-way d) Ten-way
b
Which instruction of the ARM architecture excludes a carry value after the arithmetic calculation? a) Reverse subtract b) Long multiplies c) No divide d) Conditional trap
a
Which key design element changed in 2005 to drive continued improvements in computing capability? a) Multiprocessor architecture b) Transistor architecture c) DRAM technology d) Frame buffering
a
Which memory type is built as an integrated circuit that provides the fastest access but less density? a) Static random access memory (SRAM) b) Dynamic random access memory (DRAM) c) Graphics-based d) Cache
a
Which optimized processor architecture solves operations with large amounts of data-level parallelism? a) Vector b) SISD c) Scalar d) Uniprocessor
a
Which type of processing is used if a program executes a process that takes turns waiting for user input? a) Parallel b) Sequential c) Distributed d) Symmetric
b
Which performance benefit do 128-bit wide registers in SSE2 streaming SIMD extensions enable? a) Parallel arithmetic computations b) Pipelined arithmetic computations c) Fine-grained multithreading d) Coarse-grained multithreading
a
Which register will be populated with the reason for an exception in LEGv8 architecture? a) ESR b) RAID c) FADDS d) FSUBS
a
Which statement about the operating system describes how virtual memory is allocated in ARM architecture? a) It loads the page table register to refer to the page table of the process. b) It uses a reference bit to refer to the page table of the process. c) It loads the entire page table to reference the process. d) It uses a limit register to refer to the page table of the process.
a
Which technique should be implemented to reduce cache miss rate? a) Blocking b) Pipelining c) Parallel processing d) Loop unrolling
a
Which technology improves the efficiency of processor utilization by ensuring all processors remain utilized, even when waiting for instruction sequences to complete? a) Multithreading b) Multiprocessing c) Multicore processors d) Multiple processes
a
Which term refers to the same instruction applied to multiple data streams? a) SIMD b) MIMD c) SPMD d) SISD
a
Which two elements are required to implement R-format arithmetic logic unit (ALU) operations? a) ALU and register file b) ALU and GPU c) GPU and register file d) Datapath and COD
a
A system designer wants to lower the cost of communicating at a high clock rate over the network. How can this goal be accomplished? a) Increase the network latency b) Extend the length of the wires c) Reduce the distance of each link d) Implement a fully connected network
c
Which component of a computer moderates the action of its other components? a) Control b) Datapath c) Memory d) Output
a
Which register holds the result for the instruction SUB X1, X2, X3? a) X1 b) X2 c) X3 d) X0
a
What does extending to 16 bits yield given -5 in 8-bit 2's complement 11111011? a) 11111100 11111011 b) 11111111 11111011 c) 01111111 11111011 d) 00111111 11111011
b
A cache has 16 one-word blocks. Memory blocks are mapped to fully associative caches. Memory block is 15. What is the cache position given the cache configuration and memory block? a) Block 7 b) Block 15 c) Any of the 15 cache blocks d) Any of the 16 cache blocks
d
Which factor in parallel processing is not bound by Amdahl's Law? a) Weak Scaling b) Strong Scaling c) Memory Hierarchy d) Application Hierarchy
a
A program has a CPI of 10 on a target platform. The processor pipeline is expanded and clock rate is increased by a factor of 5, but the CPI fails to decrease accordingly. Which factor is negatively affecting performance? a) Cache memory b) Virtual memory c) Hard disk drive d) Single processor
a
A storage solution for video editing is being planned. The requirements are: • Largest storage space • No redundancy • Fastest I/O speed Which RAID solution should be implemented? a) RAID 0 b) RAID 1 c) RAID 5 d) RAID 6
a
Given the following 8-bit integer binary variables: X1 = 11000110 X2 = 11110111 What is the value in X3 after the following command? ADD X3, X2, X1 a) Overflow b) 100111101 c) 11000110 d) 11110111
a
Given this set of ARM instructions, where b is at offset 0, e is at offset 8, and a is at offset 24: LDUR X1, [X0,#0] LDUR X2, [X0,#8] ADD X3, X1, X2 STUR X3, [X0,#24] What is the corresponding C language statement? a) a = b + e; b) a = a + e; c) a = b + a; d) a = e + a;
a
How can the CPU performance of a program be improved? a) By reducing the number of clock cycles b) By increasing the length of the clock cycle c) By reducing the throughput of the processor d) By increasing response time for disk access
a
In which type of multiprocessor is latency to any word in main memory the same regardless of which processor requests access? a) Uniform memory access b) Locking memory access c) Non-uniform memory access d) Synchronization memory access
a
Register M0 should contain the result of dividing register R1 by R2. R1 and R2 contain two unsigned 32-bit integers. Which ARM instruction is optimized for this arithmetic operation? a) UDIV M0, R1, R2 b) SDIV R1, R2, M0 c) Loop: CBZ R1, Exit SUB R1, R1, 1 SUB M0, M0, R2 B Loop Exit: d) Loop: CBZ R2, Exit SUB R1, R1, 1 SUB M0, M0, R1 B Loop Exit:
a
The value of b is stored in r1, c is stored in r2, and a is stored in r0. Which set of ARM instructions will accomplish a = b & c? a) AND r0, r1, r2 b) OR r0, r1, r2 c) EOR r0, r1, r2 d) ORR r0, r1, r2
a
The variables f and g are assigned to the registers X3 and X4, respectively in these ARM instructions. Loop: SUBS XZR, X3, X4 B.GE Exit LSL X3, X3, 1 B Loop Exit: What are the corresponding statements in the C language? a) while (f < g) { f = f << 1; } b) while (f > g) { f = f << 1; } c) while (f <= g) { f = f << 1; } d) while(f == g){f = f << 1; }
a
What does each bank of modern DRAMS consist of? a) Rows b) Disk c) Buffers d) Columns
a
What is an advantage of multiprocessor architecture? a) It increases throughput. b) It is easier to increase clock rate. c) It minimizes instruction bandwidth. d) It is easier to extend a scalar instruction set.
a
What is improved from all LEGv8 instructions having the same 32-bit length? a) Pipelining b) Caching c) Disk I/O d) Power consumption
a
What is the binary representation of instructions? a) Machine language b) Assembly language c) Operating system d) Systems software
a
What is used by virtual memory to increase performance? a) Translation-lookaside buffer b) Sparse memory c) Demand paging d) Page size
a
What maps virtual memory to real memory by using page tables? a) Each guest operating system manages virtual memory independently. b) The host operating system manages each virtual machine's virtual memory. c) The hypervisor software manages each virtual machine's virtual memory. d) Guest operating systems prohibit the use of virtual memory.
a
Which access does a register file rely on to properly function? a) Read and write access b) Write only access c) Read only access d) No access
a
Which benefit does pipelining a set of instructions provide? a) The throughput of the complete set of instructions is increased. b) The throughput of an individual instruction is increased. c) The execution time of an individual instruction is increased. d) The execution time for a complete set of instructions is increased.
a
Four processors (1, 2, 3, and 4) have clock frequencies of 200 Mhz, 300 Mhz, 500 Mhz, and 700 Mhz, respectively. Suppose: • Processor 1 can execute an instruction with an average of 5 steps. • Processor 2 can execute an instruction with an average of 3 steps. • Processor 3 can execute an instruction with an average of 3 steps. • Processor 4 can execute an instruction with an average of 5 steps. Which processor should be selected to improve performance for the execution of the same instruction? a) Processor 1 b) Processor 2 c) Processor 3 d) Processor 4
c
How many minutes does it take to wash, dry, and fold four loads of laundry using a pipelining approach, given the following information? • One washer takes 30 minutes • One dryer takes 40 minutes • One folder takes 20 minutes a) 90 b) 170 c) 210 d) 360
c
What is the bit width of an SIMD register with the suffix of 'D' when determining subword parallelism? a) 8-bit b) 32-bit c) 64-bit d) 128-bit
c
Which locality principle states that if a data location is referenced then it will tend to be referenced again soon? a) Spatial b) Residual c) Temporal d) Canonical
c
How is the integer 255 represented in memory? a) 0000 0000 0000 0000 0000 0000 0000 0111 b) 0000 0000 0000 0000 0000 0000 0000 1111 c) 0000 0000 0000 0000 0000 0000 0111 1111 d) 0000 0000 0000 0000 0000 0000 1111 1111
d
Registers X1, X2, X3 have corresponding data stored in each location: X1: A X2: B X3: C Which set of ARM instructions will accomplish A=B+C? a) ADD X3, X2, X1 b) ADD X1, X2 #X3 c) ADD X3 #X2, X1 d) ADD X1, X2, X3
d
What is superscalar as it relates to parallelization? a) A buffer within a functional unit that holds the operands and the operation b) The hardware support for reordering the order of instruction execution so as to avoid stalls c) A process in which an instruction is blocked from executing, and therefore it fails to cause the following instructions to wait d) A technique that enables the processor to execute more than one instruction per clock cycle by selecting them during execution
d
What is the approximate range of a 64-bit unsigned integer? a) −9,223,372,036,854,775,808 to 9,223,372,036,854,775,807 b) −2,147,483,648 to 2,147,483,647 c) 0 to 4,294,967,295 d) 0 to 18,446,744,073,709,551,615
d
What is the number of bits used in virtual memory with ARMv8? a) 12 b) 16 c) 24 d) 48
d
What makes vector-based code more efficient than conventional code? a) Usage of LEGv8 architecture code b) Usage of Multimedia extensions (MMX) c) Frequency of pipeline hazards is higher d) Frequency of pipeline hazards is lower
d
Why have recent CPU clock rates increased while power consumption has flattened out? a) Memory size requirements b) Chip sizes are too small c) Chip sizes are too large d) Cooling issues
d