| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
| |
BasicBlock's removePredecessor routine. This requires shuffling around
the definition and implementation of hasContantValue from Utils.h,cpp into
Instructions.h,cpp
llvm-svn: 22664
|
| |
|
|
| |
llvm-svn: 22663
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
that the symbolic evaluator is not always able to use subtraction to remove
expressions. This makes the code faster, and fixes the last crash on 178.galgel.
Finally, add a statistic to see how many phi nodes are inserted.
On 178.galgel, we get the follow stats:
2562 loop-reduce - Number of PHIs inserted
3927 loop-reduce - Number of GEPs strength reduced
llvm-svn: 22662
|
| |
|
|
| |
llvm-svn: 22661
|
| |
|
|
|
|
| |
know what The Right Thing To Do is.
llvm-svn: 22660
|
| |
|
|
|
|
| |
and asm printer for PowerPC if one is not specified.
llvm-svn: 22659
|
| |
|
|
|
|
|
|
| |
method.
* Fix a crash on 178.galgel, where we would insert expressions before PHI
nodes instead of into the PHI node predecessor blocks.
llvm-svn: 22657
|
| |
|
|
| |
llvm-svn: 22656
|
| |
|
|
|
|
| |
not execution tests.
llvm-svn: 22655
|
| |
|
|
| |
llvm-svn: 22653
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
for (i = 0; i < N; ++i)
A[i][foo()] = 0;
here we still want to strength reduce the A[i] part, even though foo() is
l-v.
This also simplifies some of the 'CanReduce' logic.
This implements Transforms/LoopStrengthReduce/ops_after_indvar.ll
llvm-svn: 22652
|
| |
|
|
| |
llvm-svn: 22651
|
| |
|
|
| |
llvm-svn: 22650
|
| |
|
|
|
|
|
|
|
|
|
| |
1. We only analyze instructions once, guaranteed
2. AnalyzeGetElementPtrUsers has been ripped apart and replaced with
something much simpler.
The next step is to handle expressions that are not all indvar+loop-invariant
values (e.g. handling indvar+loopvariant).
llvm-svn: 22649
|
| |
|
|
| |
llvm-svn: 22648
|
| |
|
|
|
|
| |
* Add comments to #endif pragmas for readability
llvm-svn: 22647
|
| |
|
|
|
|
| |
* Comment #endif clauses for readability
llvm-svn: 22646
|
| |
|
|
| |
llvm-svn: 22644
|
| |
|
|
| |
llvm-svn: 22643
|
| |
|
|
| |
llvm-svn: 22642
|
| |
|
|
| |
llvm-svn: 22641
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
sure to handle the use, just don't recurse into it.
This permits us to generate this code for a simple nested loop case:
.LBB_foo_0: ; entry
stwu r1, -48(r1)
stw r29, 44(r1)
stw r30, 40(r1)
mflr r11
stw r11, 56(r1)
lis r2, ha16(L_A$non_lazy_ptr)
lwz r30, lo16(L_A$non_lazy_ptr)(r2)
li r29, 1
.LBB_foo_1: ; no_exit.0
bl L_bar$stub
li r2, 1
or r3, r30, r30
.LBB_foo_2: ; no_exit.1
lfd f0, 8(r3)
stfd f0, 0(r3)
addi r4, r2, 1
addi r3, r3, 8
cmpwi cr0, r2, 100
or r2, r4, r4
bne .LBB_foo_2 ; no_exit.1
.LBB_foo_3: ; loopexit.1
addi r30, r30, 800
addi r2, r29, 1
cmpwi cr0, r29, 100
or r29, r2, r2
bne .LBB_foo_1 ; no_exit.0
.LBB_foo_4: ; return
lwz r11, 56(r1)
mtlr r11
lwz r30, 40(r1)
lwz r29, 44(r1)
lwz r1, 0(r1)
blr
instead of this:
_foo:
.LBB_foo_0: ; entry
stwu r1, -48(r1)
stw r28, 44(r1) ;; uses an extra register.
stw r29, 40(r1)
stw r30, 36(r1)
mflr r11
stw r11, 56(r1)
li r30, 1
li r29, 0
or r28, r29, r29
.LBB_foo_1: ; no_exit.0
bl L_bar$stub
mulli r2, r28, 800 ;; unstrength-reduced multiply
lis r3, ha16(L_A$non_lazy_ptr) ;; loop invariant address computation
lwz r3, lo16(L_A$non_lazy_ptr)(r3)
add r2, r2, r3
mulli r4, r29, 800 ;; unstrength-reduced multiply
addi r3, r3, 8
add r3, r4, r3
li r4, 1
.LBB_foo_2: ; no_exit.1
lfd f0, 0(r3)
stfd f0, 0(r2)
addi r5, r4, 1
addi r2, r2, 8 ;; multiple stride 8 IV's
addi r3, r3, 8
cmpwi cr0, r4, 100
or r4, r5, r5
bne .LBB_foo_2 ; no_exit.1
.LBB_foo_3: ; loopexit.1
addi r28, r28, 1 ;;; Many IV's with stride 1
addi r29, r29, 1
addi r2, r30, 1
cmpwi cr0, r30, 100
or r30, r2, r2
bne .LBB_foo_1 ; no_exit.0
.LBB_foo_4: ; return
lwz r11, 56(r1)
mtlr r11
lwz r30, 36(r1)
lwz r29, 40(r1)
lwz r28, 44(r1)
lwz r1, 0(r1)
blr
llvm-svn: 22640
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
pushed down by SCEV.
In a nested loop case, this allows us to emit this:
lis r3, ha16(L_A$non_lazy_ptr)
lwz r3, lo16(L_A$non_lazy_ptr)(r3)
add r2, r2, r3
li r3, 1
.LBB_foo_2: ; no_exit.1
lfd f0, 8(r2) ;; Uses offset of 8 instead of 0
stfd f0, 0(r2)
addi r4, r3, 1
addi r2, r2, 8
cmpwi cr0, r3, 100
or r3, r4, r4
bne .LBB_foo_2 ; no_exit.1
instead of this:
lis r3, ha16(L_A$non_lazy_ptr)
lwz r3, lo16(L_A$non_lazy_ptr)(r3)
add r2, r2, r3
addi r3, r3, 8
li r4, 1
.LBB_foo_2: ; no_exit.1
lfd f0, 0(r3)
stfd f0, 0(r2)
addi r5, r4, 1
addi r2, r2, 8
addi r3, r3, 8
cmpwi cr0, r4, 100
or r4, r5, r5
bne .LBB_foo_2 ; no_exit.1
llvm-svn: 22639
|
| |
|
|
| |
llvm-svn: 22638
|
| |
|
|
|
|
|
| |
Scalar SSE: a < b ? c : 0.0 -> cmpss, andps
Scalar SSE: float -> i16 needs to be promoted
llvm-svn: 22637
|
| |
|
|
| |
llvm-svn: 22636
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Only emit one PHI node for IV uses with identical bases and strides (after
moving foldable immediates to the load/store instruction).
This implements LoopStrengthReduce/dont_insert_redundant_ops.ll, allowing
us to generate this PPC code for test1:
or r30, r3, r3
.LBB_test1_1: ; Loop
li r2, 0
stw r2, 0(r30)
stw r2, 4(r30)
bl L_pred$stub
addi r30, r30, 8
cmplwi cr0, r3, 0
bne .LBB_test1_1 ; Loop
instead of this code:
or r30, r3, r3
or r29, r3, r3
.LBB_test1_1: ; Loop
li r2, 0
stw r2, 0(r29)
stw r2, 4(r30)
bl L_pred$stub
addi r30, r30, 8 ;; Two iv's with step of 8
addi r29, r29, 8
cmplwi cr0, r3, 0
bne .LBB_test1_1 ; Loop
llvm-svn: 22635
|
| |
|
|
|
|
| |
will too
llvm-svn: 22634
|
| |
|
|
|
|
|
| |
unify some parallel vectors and get field names more descriptive than
"first" and "second". This isn't lisp afterall :)
llvm-svn: 22633
|
| |
|
|
|
|
|
|
|
| |
map from instruction* to SCEVHandles. When we delete instructions, we have
to tell it about it. We would run into nasty cases where new instructions
were reallocated at old instruction addresses and get the old map values.
Bad bad bad :(
llvm-svn: 22632
|
| |
|
|
| |
llvm-svn: 22631
|
| |
|
|
|
|
|
|
| |
SingleSource/UnitTests/2005-05-12-Int64ToFP
last night.
llvm-svn: 22630
|
| |
|
|
|
|
| |
the sequence used for integer ops
llvm-svn: 22629
|
| |
|
|
|
|
| |
Transforms/LowerInvoke/2005-08-03-InvokeWithPHIUse.ll
llvm-svn: 22628
|
| |
|
|
| |
llvm-svn: 22627
|
| |
|
|
|
|
| |
fixes PR612 and Transforms/LowerInvoke/2005-08-03-InvokeWithPHI.ll
llvm-svn: 22626
|
| |
|
|
| |
llvm-svn: 22625
|
| |
|
|
| |
llvm-svn: 22624
|
| |
|
|
| |
llvm-svn: 22623
|
| |
|
|
| |
llvm-svn: 22622
|
| |
|
|
|
|
| |
occurred while bugpointing another testcase
llvm-svn: 22621
|
| |
|
|
| |
llvm-svn: 22620
|
| |
|
|
| |
llvm-svn: 22619
|
| |
|
|
|
|
| |
non-ppc GCC 4.0 machines. Patch by Jim Laskey!
llvm-svn: 22618
|
| |
|
|
| |
llvm-svn: 22617
|
| |
|
|
| |
llvm-svn: 22616
|
| |
|
|
|
|
|
|
| |
Transforms/SimplifyCFG/2005-08-01-PHIUpdateFail.ll
the right way
llvm-svn: 22615
|
| |
|
|
| |
llvm-svn: 22614
|
| |
|
|
| |
llvm-svn: 22613
|
| |
|
|
|
|
| |
function with no side-effects
llvm-svn: 22612
|