http://llvm.org/bugs/show_bug.cgi?id=17681
Bug ID: 17681
Summary: [Vectorizer] Recognize memory stride access
Product: libraries
Version: trunk
Hardware: PC
OS: Linux
Status: NEW
Severity: normal
Priority: P
Component: Loop Optimizer
Assignee: [email protected]
Reporter: [email protected]
CC: [email protected]
Classification: Unclassified
After implementing interleaved and non-interleaved non-unit stride access on
the vectorizer, make sure that cases where a pointer is used to access the
induction is mapped into a semantics we do understand.
Basically, making this:
for (i..N/3) {
a++ = b++ + K;
a++ = b++ + K;
a++ = b++ + K;
}
Look like this:
for (i..N/3) {
a[3*i] = b[3*i] + K;
a[3*i+1] = b[3*i+1] + K;
a[3*i+2] = b[3*i+2] + K;
}
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
LLVMbugs mailing list
[email protected]
http://lists.cs.uiuc.edu/mailman/listinfo/llvmbugs
