530fe6ab30
implement Transforms/LoopStrengthReduce/dont-hoist-simple-loop-constants.ll.
...
We used to emit this code for it:
_test:
li r2, 1 ;; Value tying up a register for the whole loop
li r5, 0
LBB_test_1: ; no_exit.2
or r6, r5, r5
li r5, 0
stw r5, 0(r3)
addi r5, r6, 1
addi r3, r3, 4
add r7, r2, r5 ;; should be addi r7, r5, 1
cmpwi cr0, r7, 701
blt cr0, LBB_test_1 ; no_exit.2
LBB_test_2: ; loopexit.2.loopexit
addi r2, r6, 2
stw r2, 0(r4)
blr
now we emit this:
_test:
li r2, 0
LBB_test_1: ; no_exit.2
or r5, r2, r2
li r2, 0
stw r2, 0(r3)
addi r3, r3, 4
addi r2, r5, 1
addi r6, r5, 2 ;; whoa, fold those adds!
cmpwi cr0, r6, 701
blt cr0, LBB_test_1 ; no_exit.2
LBB_test_2: ; loopexit.2.loopexit
addi r2, r5, 2
stw r2, 0(r4)
blr
more improvement coming.
llvm-svn: 23306
2005-09-10 01:18:45 +00:00
ea7dfd53d6
Fix Transforms/LoopStrengthReduce/2005-08-17-OutOfLoopVariant.ll, a crash
...
on 177.mesa
llvm-svn: 22843
2005-08-17 21:22:41 +00:00
2bf7cb5213
Use a new helper to split critical edges, making the code simpler.
...
Do not claim to not change the CFG. We do change the cfg to split critical
edges. This isn't causing us a problem now, but could likely do so in the
future.
llvm-svn: 22824
2005-08-17 06:35:16 +00:00
5cf983ee0f
Fix a bad case in gzip where we put lots of things in registers across the
...
loop, because a IV-dependent value was used outside of the loop and didn't
have immediate-folding capability
llvm-svn: 22798
2005-08-16 00:38:11 +00:00
47d3ec3525
Ooops, don't forget to clear this. The real inner loop is now:
...
.LBB_foo_3: ; no_exit.1
lfd f2, 0(r9)
lfd f3, 8(r9)
fmul f4, f1, f2
fmadd f4, f0, f3, f4
stfd f4, 8(r9)
fmul f3, f1, f3
fmsub f2, f0, f2, f3
stfd f2, 0(r9)
addi r9, r9, 16
addi r8, r8, 1
cmpw cr0, r8, r4
ble .LBB_foo_3 ; no_exit.1
llvm-svn: 22782
2005-08-13 07:42:01 +00:00
5949d49032
Recursively scan scev expressions for common subexpressions. This allows us
...
to handle nested loops much better, for example, by being able to tell that
these two expressions:
{( 8 + ( 16 * ( 1 + %Tmp11 + %Tmp12)) + %c_),+,( 16 * %Tmp 12)}<loopentry.1>
{(( 16 * ( 1 + %Tmp11 + %Tmp12)) + %c_),+,( 16 * %Tmp12)}<loopentry.1>
Have the following common part that can be shared:
{(( 16 * ( 1 + %Tmp11 + %Tmp12)) + %c_),+,( 16 * %Tmp12)}<loopentry.1>
This allows us to codegen an important inner loop in 168.wupwise as:
.LBB_foo_4: ; no_exit.1
lfd f2, 16(r9)
fmul f3, f0, f2
fmul f2, f1, f2
fadd f4, f3, f2
stfd f4, 8(r9)
fsub f2, f3, f2
stfd f2, 16(r9)
addi r8, r8, 1
addi r9, r9, 16
cmpw cr0, r8, r4
ble .LBB_foo_4 ; no_exit.1
instead of:
.LBB_foo_3: ; no_exit.1
lfdx f2, r6, r9
add r10, r6, r9
lfd f3, 8(r10)
fmul f4, f1, f2
fmadd f4, f0, f3, f4
stfd f4, 8(r10)
fmul f3, f1, f3
fmsub f2, f0, f2, f3
stfdx f2, r6, r9
addi r9, r9, 16
addi r8, r8, 1
cmpw cr0, r8, r4
ble .LBB_foo_3 ; no_exit.1
llvm-svn: 22781
2005-08-13 07:27:18 +00:00
8447b49526
When splitting critical edges, make sure not to leave the new block in the
...
middle of the loop. This turns a critical loop in gzip into this:
.LBB_test_1: ; loopentry
or r27, r28, r28
add r28, r3, r27
lhz r28, 3(r28)
add r26, r4, r27
lhz r26, 3(r26)
cmpw cr0, r28, r26
bne .LBB_test_8 ; loopentry.loopexit_crit_edge
.LBB_test_2: ; shortcirc_next.0
add r28, r3, r27
lhz r28, 5(r28)
add r26, r4, r27
lhz r26, 5(r26)
cmpw cr0, r28, r26
bne .LBB_test_7 ; shortcirc_next.0.loopexit_crit_edge
.LBB_test_3: ; shortcirc_next.1
add r28, r3, r27
lhz r28, 7(r28)
add r26, r4, r27
lhz r26, 7(r26)
cmpw cr0, r28, r26
bne .LBB_test_6 ; shortcirc_next.1.loopexit_crit_edge
.LBB_test_4: ; shortcirc_next.2
add r28, r3, r27
lhz r26, 9(r28)
add r28, r4, r27
lhz r25, 9(r28)
addi r28, r27, 8
cmpw cr7, r26, r25
mfcr r26, 1
rlwinm r26, r26, 31, 31, 31
add r25, r8, r27
cmpw cr7, r25, r7
mfcr r25, 1
rlwinm r25, r25, 29, 31, 31
and. r26, r26, r25
bne .LBB_test_1 ; loopentry
instead of this:
.LBB_test_1: ; loopentry
or r27, r28, r28
add r28, r3, r27
lhz r28, 3(r28)
add r26, r4, r27
lhz r26, 3(r26)
cmpw cr0, r28, r26
beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2: ; loopentry.loopexit_crit_edge
add r2, r30, r27
add r8, r29, r27
b .LBB_test_9 ; loopexit
.LBB_test_3: ; shortcirc_next.0
add r28, r3, r27
lhz r28, 5(r28)
add r26, r4, r27
lhz r26, 5(r26)
cmpw cr0, r28, r26
beq .LBB_test_5 ; shortcirc_next.1
.LBB_test_4: ; shortcirc_next.0.loopexit_crit_edge
add r2, r11, r27
add r8, r12, r27
b .LBB_test_9 ; loopexit
.LBB_test_5: ; shortcirc_next.1
add r28, r3, r27
lhz r28, 7(r28)
add r26, r4, r27
lhz r26, 7(r26)
cmpw cr0, r28, r26
beq .LBB_test_7 ; shortcirc_next.2
.LBB_test_6: ; shortcirc_next.1.loopexit_crit_edge
add r2, r9, r27
add r8, r10, r27
b .LBB_test_9 ; loopexit
.LBB_test_7: ; shortcirc_next.2
add r28, r3, r27
lhz r26, 9(r28)
add r28, r4, r27
lhz r25, 9(r28)
addi r28, r27, 8
cmpw cr7, r26, r25
mfcr r26, 1
rlwinm r26, r26, 31, 31, 31
add r25, r8, r27
cmpw cr7, r25, r7
mfcr r25, 1
rlwinm r25, r25, 29, 31, 31
and. r26, r26, r25
bne .LBB_test_1 ; loopentry
Next up, improve the code for the loop.
llvm-svn: 22769
2005-08-12 22:22:17 +00:00
4fec86d348
Fix a FIXME: if we are inserting code for a PHI argument, split the critical
...
edge so that the code is not always executed for both operands. This
prevents LSR from inserting code into loops whose exit blocks contain
PHI uses of IV expressions (which are outside of loops). On gzip, for
example, we turn this ugly code:
.LBB_test_1: ; loopentry
add r27, r3, r28
lhz r27, 3(r27)
add r26, r4, r28
lhz r26, 3(r26)
add r25, r30, r28 ;; Only live if exiting the loop
add r24, r29, r28 ;; Only live if exiting the loop
cmpw cr0, r27, r26
bne .LBB_test_5 ; loopexit
into this:
.LBB_test_1: ; loopentry
or r27, r28, r28
add r28, r3, r27
lhz r28, 3(r28)
add r26, r4, r27
lhz r26, 3(r26)
cmpw cr0, r28, r26
beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2: ; loopentry.loopexit_crit_edge
add r2, r30, r27
add r8, r29, r27
b .LBB_test_9 ; loopexit
.LBB_test_2: ; shortcirc_next.0
...
blt .LBB_test_1
into this:
.LBB_test_1: ; loopentry
or r27, r28, r28
add r28, r3, r27
lhz r28, 3(r28)
add r26, r4, r27
lhz r26, 3(r26)
cmpw cr0, r28, r26
beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2: ; loopentry.loopexit_crit_edge
add r2, r30, r27
add r8, r29, r27
b .LBB_t_3: ; shortcirc_next.0
.LBB_test_3: ; shortcirc_next.0
...
blt .LBB_test_1
Next step: get the block out of the loop so that the loop is all
fall-throughs again.
llvm-svn: 22766
2005-08-12 22:06:11 +00:00
edff91a49a
Teach LSR to strength reduce IVs that have a loop-invariant but non-constant stride.
...
For code like this:
void foo(float *a, float *b, int n, int stride_a, int stride_b) {
int i;
for (i=0; i<n; i++)
a[i*stride_a] = b[i*stride_b];
}
we now emit:
.LBB_foo2_2: ; no_exit
lfs f0, 0(r4)
stfs f0, 0(r3)
addi r7, r7, 1
add r4, r2, r4
add r3, r6, r3
cmpw cr0, r7, r5
blt .LBB_foo2_2 ; no_exit
instead of:
.LBB_foo_2: ; no_exit
mullw r8, r2, r7 ;; multiply!
slwi r8, r8, 2
lfsx f0, r4, r8
mullw r8, r2, r6 ;; multiply!
slwi r8, r8, 2
stfsx f0, r3, r8
addi r2, r2, 1
cmpw cr0, r2, r5
blt .LBB_foo_2 ; no_exit
loops with variable strides occur pretty often. For example, in SPECFP2K
there are 317 variable strides in 177.mesa, 3 in 179.art, 14 in 188.ammp,
56 in 168.wupwise, 36 in 172.mgrid.
Now we can allow indvars to turn functions written like this:
void foo2(float *a, float *b, int n, int stride_a, int stride_b) {
int i, ai = 0, bi = 0;
for (i=0; i<n; i++)
{
a[ai] = b[bi];
ai += stride_a;
bi += stride_b;
}
}
into code like the above for better analysis. With this patch, they generate
identical code.
llvm-svn: 22740
2005-08-10 00:45:21 +00:00
dde7dc525e
Fix Regression/Transforms/LoopStrengthReduce/phi_node_update_multiple_preds.ll
...
by being more careful about updating PHI nodes
llvm-svn: 22739
2005-08-10 00:35:32 +00:00
c6c4d99a21
Fix some 80 column violations.
...
Once we compute the evolution for a GEP, tell SE about it. This allows users
of the GEP to know it, if the users are not direct. This allows us to compile
this testcase:
void fbSolidFillmmx(int w, unsigned char *d) {
while (w >= 64) {
*(unsigned long long *) (d + 0) = 0;
*(unsigned long long *) (d + 8) = 0;
*(unsigned long long *) (d + 16) = 0;
*(unsigned long long *) (d + 24) = 0;
*(unsigned long long *) (d + 32) = 0;
*(unsigned long long *) (d + 40) = 0;
*(unsigned long long *) (d + 48) = 0;
*(unsigned long long *) (d + 56) = 0;
w -= 64;
d += 64;
}
}
into:
.LBB_fbSolidFillmmx_2: ; no_exit
li r2, 0
stw r2, 0(r4)
stw r2, 4(r4)
stw r2, 8(r4)
stw r2, 12(r4)
stw r2, 16(r4)
stw r2, 20(r4)
stw r2, 24(r4)
stw r2, 28(r4)
stw r2, 32(r4)
stw r2, 36(r4)
stw r2, 40(r4)
stw r2, 44(r4)
stw r2, 48(r4)
stw r2, 52(r4)
stw r2, 56(r4)
stw r2, 60(r4)
addi r4, r4, 64
addi r3, r3, -64
cmpwi cr0, r3, 63
bgt .LBB_fbSolidFillmmx_2 ; no_exit
instead of:
.LBB_fbSolidFillmmx_2: ; no_exit
li r11, 0
stw r11, 0(r4)
stw r11, 4(r4)
stwx r11, r10, r4
add r12, r10, r4
stw r11, 4(r12)
stwx r11, r9, r4
add r12, r9, r4
stw r11, 4(r12)
stwx r11, r8, r4
add r12, r8, r4
stw r11, 4(r12)
stwx r11, r7, r4
add r12, r7, r4
stw r11, 4(r12)
stwx r11, r6, r4
add r12, r6, r4
stw r11, 4(r12)
stwx r11, r5, r4
add r12, r5, r4
stw r11, 4(r12)
stwx r11, r2, r4
add r12, r2, r4
stw r11, 4(r12)
addi r4, r4, 64
addi r3, r3, -64
cmpwi cr0, r3, 63
bgt .LBB_fbSolidFillmmx_2 ; no_exit
llvm-svn: 22737
2005-08-09 23:39:36 +00:00
02742710f3
SCEVAddExpr::get() of an empty list is invalid.
...
llvm-svn: 22724
2005-08-09 01:13:47 +00:00
a091ff1764
Implement: LoopStrengthReduce/share_ivs.ll
...
Two changes:
* Only insert one PHI node for each stride. Other values are live in
values. This cannot introduce higher register pressure than the
previous approach, and can take advantage of reg+reg addressing modes.
* Factor common base values out of uses before moving values from the
base to the immediate fields. This improves codegen by starting the
stride-specific PHI node out at a common place for each IV use.
As an example, we used to generate this for a loop in swim:
.LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_2: ; no_exit.7.i
lfd f0, 0(r8)
stfd f0, 0(r3)
lfd f0, 0(r6)
stfd f0, 0(r7)
lfd f0, 0(r2)
stfd f0, 0(r5)
addi r9, r9, 1
addi r2, r2, 8
addi r5, r5, 8
addi r6, r6, 8
addi r7, r7, 8
addi r8, r8, 8
addi r3, r3, 8
cmpw cr0, r9, r4
bgt .LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_1
now we emit:
.LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_2: ; no_exit.7.i
lfdx f0, r8, r2
stfdx f0, r9, r2
lfdx f0, r5, r2
stfdx f0, r7, r2
lfdx f0, r3, r2
stfdx f0, r6, r2
addi r10, r10, 1
addi r2, r2, 8
cmpw cr0, r10, r4
bgt .LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_1
As another more dramatic example, we used to emit this:
.LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_2: ; no_exit.1.i19
lfd f0, 8(r21)
lfd f4, 8(r3)
lfd f5, 8(r27)
lfd f6, 8(r22)
lfd f7, 8(r5)
lfd f8, 8(r6)
lfd f9, 8(r30)
lfd f10, 8(r11)
lfd f11, 8(r12)
fsub f10, f10, f11
fadd f5, f4, f5
fmul f5, f5, f1
fadd f6, f6, f7
fadd f6, f6, f8
fadd f6, f6, f9
fmadd f0, f5, f6, f0
fnmsub f0, f10, f2, f0
stfd f0, 8(r4)
lfd f0, 8(r25)
lfd f5, 8(r26)
lfd f6, 8(r23)
lfd f9, 8(r28)
lfd f10, 8(r10)
lfd f12, 8(r9)
lfd f13, 8(r29)
fsub f11, f13, f11
fadd f4, f4, f5
fmul f4, f4, f1
fadd f5, f6, f9
fadd f5, f5, f10
fadd f5, f5, f12
fnmsub f0, f4, f5, f0
fnmsub f0, f11, f3, f0
stfd f0, 8(r24)
lfd f0, 8(r8)
fsub f4, f7, f8
fsub f5, f12, f10
fnmsub f0, f5, f2, f0
fnmsub f0, f4, f3, f0
stfd f0, 8(r2)
addi r20, r20, 1
addi r2, r2, 8
addi r8, r8, 8
addi r10, r10, 8
addi r12, r12, 8
addi r6, r6, 8
addi r29, r29, 8
addi r28, r28, 8
addi r26, r26, 8
addi r25, r25, 8
addi r24, r24, 8
addi r5, r5, 8
addi r23, r23, 8
addi r22, r22, 8
addi r3, r3, 8
addi r9, r9, 8
addi r11, r11, 8
addi r30, r30, 8
addi r27, r27, 8
addi r21, r21, 8
addi r4, r4, 8
cmpw cr0, r20, r7
bgt .LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_1
we now emit:
.LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_2: ; no_exit.1.i19
lfdx f0, r21, r20
lfdx f4, r3, r20
lfdx f5, r27, r20
lfdx f6, r22, r20
lfdx f7, r5, r20
lfdx f8, r6, r20
lfdx f9, r30, r20
lfdx f10, r11, r20
lfdx f11, r12, r20
fsub f10, f10, f11
fadd f5, f4, f5
fmul f5, f5, f1
fadd f6, f6, f7
fadd f6, f6, f8
fadd f6, f6, f9
fmadd f0, f5, f6, f0
fnmsub f0, f10, f2, f0
stfdx f0, r4, r20
lfdx f0, r25, r20
lfdx f5, r26, r20
lfdx f6, r23, r20
lfdx f9, r28, r20
lfdx f10, r10, r20
lfdx f12, r9, r20
lfdx f13, r29, r20
fsub f11, f13, f11
fadd f4, f4, f5
fmul f4, f4, f1
fadd f5, f6, f9
fadd f5, f5, f10
fadd f5, f5, f12
fnmsub f0, f4, f5, f0
fnmsub f0, f11, f3, f0
stfdx f0, r24, r20
lfdx f0, r8, r20
fsub f4, f7, f8
fsub f5, f12, f10
fnmsub f0, f5, f2, f0
fnmsub f0, f4, f3, f0
stfdx f0, r2, r20
addi r19, r19, 1
addi r20, r20, 8
cmpw cr0, r19, r7
bgt .LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_1
llvm-svn: 22722
2005-08-09 00:18:09 +00:00
37c24cc98c
Suck the base value out of the UsersToProcess vector into the BasedUser
...
class to simplify the code. Fuse two loops.
llvm-svn: 22721
2005-08-08 22:56:21 +00:00
37ed895bf1
Split MoveLoopVariantsToImediateField out from MoveImmediateValues. The
...
first is a correctness thing, and the later is an optzn thing. This also
is needed to support a future change.
llvm-svn: 22720
2005-08-08 22:32:34 +00:00
14203e85b2
Not all constants are legal immediates in load/store instructions.
...
llvm-svn: 22704
2005-08-08 06:25:50 +00:00
c70bbc0c41
Implement LoopStrengthReduce/share_code_in_preheader.ll by having one
...
rewriter for all code inserted into the preheader, which is never flushed.
llvm-svn: 22702
2005-08-08 05:47:49 +00:00
9bfa6f8784
Implement a simple optimization for the termination condition of the loop.
...
The termination condition actually wants to use the post-incremented value
of the loop, not a new indvar with an unusual base.
On PPC, for example, this allows us to compile
LoopStrengthReduce/exit_compare_live_range.ll to:
_foo:
li r2, 0
.LBB_foo_1: ; no_exit
li r5, 0
stw r5, 0(r3)
addi r2, r2, 1
cmpw cr0, r2, r4
bne .LBB_foo_1 ; no_exit
blr
instead of:
_foo:
li r2, 1 ;; IV starts at 1, not 0
.LBB_foo_1: ; no_exit
li r5, 0
stw r5, 0(r3)
addi r5, r2, 1
cmpw cr0, r2, r4
or r2, r5, r5 ;; Reg-reg copy, extra live range
bne .LBB_foo_1 ; no_exit
blr
This implements LoopStrengthReduce/exit_compare_live_range.ll
llvm-svn: 22699
2005-08-08 05:28:22 +00:00
11e7a5eda7
Make sure to clean CastedPointers after casts are potentially deleted.
...
This fixes LSR crashes on 301.apsi, 191.fma3d, and 189.lucas
llvm-svn: 22673
2005-08-05 01:30:11 +00:00
45f8b6e7aa
Modify how immediates are removed from base expressions to deal with the fact
...
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
2005-08-04 22:34:05 +00:00
a6d7c355bc
* Refactor some code into a new BasedUser::RewriteInstructionToUseNewBase
...
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
2005-08-04 20:03:32 +00:00
0f7c0fa2a7
Fix a case that caused this to crash on 178.galgel
...
llvm-svn: 22653
2005-08-04 19:26:19 +00:00
acc42c4df1
Teach LSR about loop-variant expressions, such as loops like this:
...
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
2005-08-04 19:08:16 +00:00
456044b724
Remove some more dead code.
...
llvm-svn: 22650
2005-08-04 18:13:56 +00:00
eaf24725b2
Refactor this code substantially with the following improvements:
...
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
2005-08-04 17:40:30 +00:00
6f286b760f
refactor some code
...
llvm-svn: 22643
2005-08-04 01:19:13 +00:00
6510749050
invert to if's to make the logic simpler
...
llvm-svn: 22641
2005-08-04 00:40:47 +00:00
a0102fbc4f
When processing outer loops and we find uses of an IV in inner loops, make
...
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
2005-08-04 00:14:11 +00:00
fc62470466
Teach loop-reduce to see into nested loops, to pull out immediate values
...
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
2005-08-03 23:44:42 +00:00
bb78c97e24
improve debug output
...
llvm-svn: 22638
2005-08-03 23:30:08 +00:00
db23c74e5e
Move from Stage 0 to Stage 1.
...
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
2005-08-03 22:51:21 +00:00
430d0022df
Rename IVUse to IVUsersOfOneStride, use a struct instead of a pair to
...
unify some parallel vectors and get field names more descriptive than
"first" and "second". This isn't lisp afterall :)
llvm-svn: 22633
2005-08-03 22:21:05 +00:00
84e9baa925
Fix a nasty dangling pointer issue. The ScalarEvolution pass would keep a
...
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
2005-08-03 21:36:09 +00:00
351b891cbc
Like the comment says, do not insert cast instructions before phi nodes
...
llvm-svn: 22586
2005-08-02 03:31:14 +00:00
75a44e154e
add a comment, make a check more lenient
...
llvm-svn: 22581
2005-08-02 02:52:02 +00:00
dcce49e006
Simplify for loop, clear a per-loop map after processing each loop
...
llvm-svn: 22580
2005-08-02 02:44:31 +00:00
9ef1294210
Add a comment
...
Make LSR ignore GEP's that have loop variant base values, as we currently
cannot codegen them
llvm-svn: 22576
2005-08-02 01:32:29 +00:00
564900e5e5
Fix an iterator invalidation problem
...
llvm-svn: 22575
2005-08-02 00:41:11 +00:00
546fd5944e
Keep tabs and trailing spaces out.
...
llvm-svn: 22565
2005-07-30 18:33:25 +00:00
c500991055
Fix VC++ build problems.
...
llvm-svn: 22564
2005-07-30 18:22:27 +00:00
17a0e2afea
Ack, typo
...
llvm-svn: 22560
2005-07-30 00:21:31 +00:00
e68bcd1946
Commit a new LoopStrengthReduce pass that can use scalar evolutions and
...
target data to decide which loop induction variables to strength reduce
and how to do so. This work is mostly by Chris Lattner, with tweaks by
me to get it working on some of MultiSource.
llvm-svn: 22558
2005-07-30 00:15:07 +00:00
b1c9317bb4
Remove trailing whitespace
...
llvm-svn: 21427
2005-04-21 23:48:37 +00:00
8c79559443
fix a bug where we thought arguments were constants :(
...
llvm-svn: 20506
2005-03-06 22:52:29 +00:00
2ce303b406
Fix Regression/Transforms/LoopStrengthReduce/dont_insert_redundant_ops.ll,
...
hopefully not breaking too many other things.
llvm-svn: 20505
2005-03-06 22:36:12 +00:00
45403e5052
implement Transforms/LoopStrengthReduce/invariant_value_first_arg.ll
...
llvm-svn: 20501
2005-03-06 22:06:22 +00:00
d3874fad44
minor simplifications of the code.
...
llvm-svn: 20497
2005-03-06 21:58:22 +00:00
4abcea3a69
Reformat comments to fix 80 columns.
...
llvm-svn: 20467
2005-03-05 22:45:40 +00:00
be37fa07fd
Reuse induction variables created for strength-reduced GEPs by other similar GEPs.
...
llvm-svn: 20466
2005-03-05 22:40:34 +00:00
a2c59b7423
Add support for not strength reducing GEPs where the element size is a small
...
power of two. This emphatically includes the zeroeth power of two.
llvm-svn: 20429
2005-03-04 04:04:26 +00:00
8ea6f9e821
Fixed the following LSR bugs:
...
* Loop invariant code does not dominate the loop header, but rather
the end of the loop preheader.
* The base for a reduced GEP isn't a constant unless all of its
operands (preceding the induction variable) are constant.
* Allow induction variable elimination for the simple case after all.
Also made changes recommended by Chris for properly deleting
instructions.
llvm-svn: 20383
2005-03-01 03:46:11 +00:00
dcaa48b5c4
Fix crash in LSR due to attempt to remove original induction variable. However,
...
for reasons explained in the comments, I also deactivated this code as it needs
more thought.
llvm-svn: 20367
2005-02-28 00:08:56 +00:00
fd63d3af0d
PHI nodes were incorrectly placed when more than one GEP is reduced in a loop.
...
llvm-svn: 20360
2005-02-27 21:08:04 +00:00
39751c3b7c
First pass at improved Loop Strength Reduction. Still not yet ready for prime time.
...
llvm-svn: 20358
2005-02-27 19:37:07 +00:00
b18121e6a9
Initial implementation of the strength reduction for GEP instructions in
...
loops. This optimization is not turned on by default yet, but may be run
with the opt tool's -loop-reduce flag. There are many FIXMEs listed in the
code that will make it far more applicable to a wide range of code, but you
have to start somewhere :)
This limited version currently triggers on the following tests in the
MultiSource directory:
pcompress2: 7 times
cfrac: 5 times
anagram: 2 times
ks: 6 times
yacr2: 2 times
llvm-svn: 17134
2004-10-18 21:08:22 +00:00
Chris Lattner