Descript.ion /cat/root
speed.exactly.c program for measuring actual memory throughput with the account of chipset and CPU latency
speed.exactly.make.bat CALL clock.make.bat speed.exactly.c
unroll.read.c program for investigation of the influence of the loop unrolling depth on the execution time of the memory-reading loop
unroll.read.make.bat CALL clock.make -release %1 unroll.read.c
unroll.write.c program for investigation of the loop unrolling depth on the execution time of the memory-writing loop
dependence.c program demonstrating the efficiency of processing independent data
dependence.make.bat CALL clock.make.bat -release %1 dependence.c
parallel.test.c program implementing the parallel memory reading algorithm that allows to "increase" memory throughput
parellel.test.make.bat CALL clock.make.bat -release %1 parallel.test.c
list.splint.c program determining optimal stragegy of list splitting
list.splint.make.bat CALL clock.make.bat -release list.splint.c
list.separated.c program demonstrating efficiency of tracing splinted lists
list.separated.make.bat CALL clock.make -release %1 list.separated.c
list.obj.c program demonstrating negative impact of memory paging
list.obj.make.bat CALL clock.make -release %1 list.obj.c
list.step.c program demonstrating dependce of the list tracing time
list.step.make.bat CALL clock.make -release %1 list.step.c
memory.way.make.bat CALL clock.make -release %1 memory.way.c
memory.way.c program demonstrating the dependence of the block processing time on the step size
memory.hit.miss.make.bat CALL clock.make -release %1 memory.hit.miss.c
memory.hit.miss.c program demonstrating memory hit, memory miss & memory organization
DRAM.wave.c program for detailed investigation of DRAM "ripples"
DRAM.wave.make.bat CALL clock.make.bat -release %1 DRAM.wave.c
bank.malloc.c program determining the bank numbers, from which memory blocks allocated by malloc start
bank.malloc.make.bat CALL clock.make.bat %1 bank.malloc.c
stream.virtual.c program demonstrating efficiency of flow virtualization depending on their number
stream.virtual.make.bat CALL clock.make -release %1 stream.virtual.c
DWORD.c program demonstrating the efficiency of processing double words
DWORD.make.bat CALL clock.make.bat -release %1 DWORD.c
align.make.bat CALL clock.make.bat -release %1 align.c
align.c program demonstrating the influence of address alignment on the speed of processing data blocks
align.memcpy.c program demonstrating the influence of address alignment of the speed of memory copying
align.memcpy.make.bat CALL clock.make.bat -release %1 align.memcpy.c
align.dwstream.c program demonstrating i n e f f i c i e n c y of aligning flows of int data
align.dwstream.make.bat CALL clock.make -release %1 align.dwstream.c
align.bstream.c Example of implementation of the function that alignes byte data flow
align.bstream.make.bat CALL clock.make -release %1 align.bstream.c
mem.mix.c program demonstrating efficiency of combining memory access with calculations
mem.mix.make.bat CALL clock.make -release %1 mem.mix.c
read.write.c program demonstrating the effect of read/write transaction overlapping on the performance
read.write.make.bat CALL clock.make -release %1 read.write.c
memcpy.optimize.c Optimized implementation of memcpy
memcpy.optimize.make.bat CALL clock.make -release %1 memcpy.optimize.c
memcmp.optimize.c Optimized implementation of memcmp
memcmp.optimize.make.bat CALL clock.make -release %1 memcmp.optimize.c
MFC.str.c program for comparing efficiency of MFC and C string functions
MFC.str.make.bat CALL clock.make.bat -release -LIB LIBCMT.LIB --cpp MFC.str.c
speculative.read.c program demonstrating efficiency of speculative data loading
speculative.read.make.bat CALL clock.make -release %1 speculative.read.c
sort.linear.c example of improved implementation of linear sort algortihm
sort.linear.make.bat CALL clock.make -release %1 sort.linear.c
unroll.write.make.bat CALL clock.make -release %1 unroll.write.c
