performance - Reducing the execution time of the code using ICC compiler -


i working on dsp based algorithms involve massive computation. have used gcc library options (-o3, -ftreevectorize...). execution time of whole code 43 ms. run same code using icc compiler there no significant reduction in execution time of code. how can reduce code execution time in icc without modifying existing code? (without using simd/s , asm)

if requirements floating-point math not stringent, easiest optimization come icc -fast file.c

however, turn on -no-prec-div well, might not want. in case, try passing icc -03 -axsse4.1 -ipo file.c

if willing put bit more time compiling, may able substantial speed benefits profiling. icc -03 -axsse4.1 -ipo -prof_gen file.c set generate profile. run code few times, exercising common use case, , recompile using icc -03 -axsse4.1 -ipo -prof_use file.c


Comments

Popular posts from this blog

python - Scipy curvefit RuntimeError:Optimal parameters not found: Number of calls to function has reached maxfev = 1000 -

c# - How to add a new treeview at the selected node? -

java - netbeans "Please wait - classpath scanning in progress..." -