Displaying 2 results from an estimated 2 matches for "ptr6".
Did you mean:
ptr
2012 Jul 30
0
[LLVMdev] IR optimization pass ideas for backend porting before ISel
...EP adopts a rule as N(n) = arr + n * ElementSize, and may
produce several instructions to compute the address.
Here's IR codes (bubbleSort-O3.ll) generated by Clang -O3:
for.body4:
%j.018 = phi i32 [ 0, %for.body4.lr.ph ], [ %add.ptr.sum, %for.inc ]
%add.ptr.sum = add i32 %j.018, 1
%add.ptr6 = getelementptr inbounds i32* %arr, i32 %add.ptr.sum
%1 = load i32* %add.ptr6, align 4, !tbaa !0
and thus generated assembly codes (bubbleSort-mcore-O3.s) by llc
-march=mcore as following:
mov r13,r6
lsli r13, 2
mov r14,r2
addu r14,r13
ldw r13, (r14, 4)
in which r6 stands for %j.018, r2 stand...
2013 Feb 14
1
[LLVMdev] LiveIntervals analysis problem
..., 69
br label %while.cond45
while.end54: ; preds = %while.cond45
store i8 0, i8* %s.2, align 1, !tbaa !1
br label %while.cond56
while.cond56: ; preds = %if.then28, %while.end54, %while.body63
%p.0 = phi i8* [ %incdec.ptr64, %while.body63 ], [ %arraydecay20, %while.end54 ], [ %arraydecay20, %if.then28 ]
%394 = load i8* %p.0, align 1, !tbaa !1
switch i8 %394, label %while.cond67 [
i8 32, label %while.body63
i8 45, label %while.body63
]
while.body63: ; preds = %while.c...