================
@@ -105,6 +106,161 @@ static void specializeForLoopForUnrolling(ForOp op) {
op.erase();
}
+/// Create a new for loop for the remaining iterations (partialIteration)
+/// after a for loop has been peeled. This is followed by correcting the
+/// loop bounds for both loops given the index (splitBound) where the
+/// iteration space is to be split up. Returns failure if the loop can not
+/// be split and no new partialIteration is created.
+static LogicalResult splitLoopHelper(RewriterBase &b, scf::ForOp forOp,
+ scf::ForOp &partialIteration,
+ Value splitBound) {
+ RewriterBase::InsertionGuard guard(b);
+ auto lbInt = getConstantIntValue(forOp.getLowerBound());
+ auto ubInt = getConstantIntValue(forOp.getUpperBound());
+ auto stepInt = getConstantIntValue(forOp.getStep());
+
+ // No specialization necessary if step already divides upper bound evenly.
+ if (lbInt && ubInt && stepInt && (*ubInt - *lbInt) % *stepInt == 0)
+ return failure();
+ // No specialization necessary if step size is 1.
+ if (stepInt == static_cast<int64_t>(1))
+ return failure();
+
+ // Create ForOp for partial iteration.
+ b.setInsertionPointAfter(forOp);
+ IRMapping map;
+ auto constStepOp =
+ b.create<arith::ConstantIndexOp>(forOp.getLoc(), *stepInt / 2);
+ // The new for loop for the remaining iterations has half the step size
+ // as continuous peeling requires the step size to diminish exponentially
+ // across subsequent loops.
+ map.map(forOp.getStep(), constStepOp);
----------------
matthias-springer wrote:
Generally speaking, for whatever modification you make to the loop body, you
have to be sure that the loop body is still computing the same thing as before.
Just blanket replacing all occurrences of the old step size (even if it's just
in `affine.min/max` ops) with the new step size may change the semantics of the
loop.
The only safe way of canonicalizing the loop body that we have at the moment is
`rewritePeeledMinMaxOp`. This function will look for `affine.min/max` ops and
select one of the provided options if it can prove that doing so would always
be correct in the peeled or partial loop.
https://github.com/llvm/llvm-project/pull/77328
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
