Displaying 2 results from an estimated 2 matches for "loop1dv1".
Did you mean:
loop1d
2015 May 02
5
[LLVMdev] Modifying LoopUnrollingPass
Hi Zhoulai,
I am trying to modify "LoopUnrollPass" in llvm which produces multiple
copies of loop equal to the loop unroll factor.Currently, using multicore
architecture, say 3 for example and the execution goes like:
for 3 cores if there are 9 iterations of loop
core instruction
1 0,3,6
2 1,4,7
3 2,5,8
But I want to to
2015 May 04
2
[LLVMdev] Modifying LoopUnrollingPass
...yaduveer-Inspiron-3542:~/RP$ clang -S -emit-llvm loop1d.c
> yaduveer at yaduveer-Inspiron-3542:~/RP$ clang -c -emit-llvm loop1d.c
> yaduveer at yaduveer-Inspiron-3542:~/RP$ opt -loop-vectorize
> -force-vector-width=4 -mem2reg -loop-rotate -indvars -debug -stats
> loop1d.ll | llvm-dis -o loop1dv1.ll
>
> we found the following message on the terminal:(Attached is the details
> found on terminal and the 2 .ll files)
>
> LV: Checking a loop in "main" from loop1d.ll
> LV: Loop hints: force=? width=4 unroll=0
> LV: Not vectorizing: Cannot prove legality.
>
>...