and handle it like constant stride vars. This fixes some bad codegen in
variable stride cases. For example, it compiles this:
void foo(int k, int i) {
for (k=i+i; k <= 8192; k+=i)
flags2[k] = 0;
}
to:
LBB1_1: #bb.preheader
movl %eax, %ecx
addl %ecx, %ecx
movl L_flags2$non_lazy_ptr, %edx
LBB1_2: #bb
movb $0, (%edx,%ecx)
addl %eax, %ecx
cmpl $8192, %ecx
jle LBB1_2 #bb
LBB1_5: #return
ret
or (if the array is local and we are in dynamic-nonpic or static mode):
LBB3_2: #bb
movb $0, _flags2(%ecx)
addl %eax, %ecx
cmpl $8192, %ecx
jle LBB3_2 #bb
and:
lis r2, ha16(L_flags2$non_lazy_ptr)
lwz r2, lo16(L_flags2$non_lazy_ptr)(r2)
slwi r3, r4, 1
LBB1_2: ;bb
li r5, 0
add r6, r4, r3
stbx r5, r2, r3
cmpwi cr0, r6, 8192
bgt cr0, LBB1_5 ;return
instead of:
leal (%eax,%eax,2), %ecx
movl %eax, %edx
addl %edx, %edx
addl L_flags2$non_lazy_ptr, %edx
xorl %esi, %esi
LBB1_2: #bb
movb $0, (%edx,%esi)
movl %eax, %edi
addl %esi, %edi
addl %ecx, %esi
cmpl $8192, %esi
jg LBB1_5 #return
and:
lis r2, ha16(L_flags2$non_lazy_ptr)
lwz r2, lo16(L_flags2$non_lazy_ptr)(r2)
mulli r3, r4, 3
slwi r5, r4, 1
li r6, 0
add r2, r2, r5
LBB1_2: ;bb
li r5, 0
add r7, r3, r6
stbx r5, r2, r6
add r6, r4, r6
cmpwi cr0, r7, 8192
ble cr0, LBB1_2 ;bb
This speeds up Benchmarks/Shootout/sieve from 8.533s to 6.464s and
implements LoopStrengthReduce/var_stride_used_by_compare.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@31809
91177308-0d34-0410-b5e6-
96231b3b80d8
}
if (!CondUse) return; // setcc doesn't use the IV.
- // setcc stride is complex, don't mess with users.
- // FIXME: Evaluate whether this is a good idea or not.
- if (!isa<SCEVConstant>(*CondStride)) return;
-
// It's possible for the setcc instruction to be anywhere in the loop, and
// possible for it to have multiple users. If it is not immediately before
// the latch block branch, move it.