7d693898ee
Add pseudo dependency to force a def&use operand to be scheduled last (unless
...
the distance between the def and another use is much longer). This is under
option control for now "-sched-lower-defnuse".
llvm-svn: 28201
2006-05-09 07:13:34 +00:00
2c74848af1
Debugging info
...
llvm-svn: 28200
2006-05-09 06:55:15 +00:00
ae45020720
PR 770 - permit coallescing of registers in subset register classes.
...
llvm-svn: 28197
2006-05-09 06:37:48 +00:00
4ebc6a2311
Implement MASM sections correctly, without a "has masm sections flag" and a bunch of special case code.
...
llvm-svn: 28194
2006-05-09 05:33:48 +00:00
8c2bfc0659
Oh yeah, there are two of these now, unify both.
...
llvm-svn: 28192
2006-05-09 05:24:50 +00:00
6341df8069
Setting SwitchToSectionDirective properly in the MASM backend permits a bunch
...
of code to be unified.
llvm-svn: 28191
2006-05-09 05:23:12 +00:00
d36cc2b610
Don't prefix section directives with a tab. Doing so causes blank lines to
...
be emitted to the .s file.
llvm-svn: 28189
2006-05-09 05:19:59 +00:00
e64f764d25
Make the masm codepath work like the normal code path.
...
llvm-svn: 28188
2006-05-09 05:15:58 +00:00
c0f0dfa56f
The MASM asmprinter has been fixed, these hacks are no longer needed.
...
llvm-svn: 28186
2006-05-09 05:13:34 +00:00
8488ba2e41
Split SwitchSection into SwitchTo{Text|Data}Section methods.
...
llvm-svn: 28184
2006-05-09 04:59:56 +00:00
446e1ef26a
Make the case I just checked in stronger. Now we compile this:
...
short test2(short X, short x) {
int Y = (short)(X+x);
return Y >> 1;
}
to:
_test2:
add r2, r3, r4
extsh r2, r2
srawi r3, r2, 1
blr
instead of:
_test2:
add r2, r3, r4
extsh r2, r2
srwi r2, r2, 1
extsh r3, r2
blr
llvm-svn: 28175
2006-05-08 21:18:59 +00:00
29062da0ac
Implement and_sext.ll:test3, generating:
...
_test4:
srawi r3, r3, 16
blr
instead of:
_test4:
srwi r2, r3, 16
extsh r3, r2
blr
for:
short test4(unsigned X) {
return (X >> 16);
}
llvm-svn: 28174
2006-05-08 20:59:41 +00:00
2935d8190c
Compile this:
...
short test4(unsigned X) {
return (X >> 16);
}
to:
_test4:
movl 4(%esp), %eax
sarl $16, %eax
ret
instead of:
_test4:
movl $-65536, %eax
andl 4(%esp), %eax
sarl $16, %eax
ret
llvm-svn: 28171
2006-05-08 20:51:54 +00:00
78da6792e7
Fold shifts with undef operands.
...
llvm-svn: 28167
2006-05-08 17:29:49 +00:00
d7a19102d1
Make emission of jump tables a bit less conservative; they are now required
...
to be only 31.25% dense, rather than 75% dense.
llvm-svn: 28165
2006-05-08 16:51:36 +00:00
e5ce5bb6da
Fix PR772
...
llvm-svn: 28161
2006-05-08 01:35:01 +00:00
7e7bcf3a54
Simplify some code, add a couple minor missed folds
...
llvm-svn: 28152
2006-05-06 23:06:26 +00:00
751817c54f
constant fold sign_extend_inreg
...
llvm-svn: 28151
2006-05-06 23:05:41 +00:00
2a4d7b845b
remove cases handled elsewhere
...
llvm-svn: 28150
2006-05-06 22:43:44 +00:00
ce9b9fe6eb
Fix some loose ends in MASM support.
...
llvm-svn: 28148
2006-05-06 21:27:14 +00:00
1ecb2a2dac
Use the new TargetLowering::ComputeNumSignBits method to eliminate
...
sign_extend_inreg operations. Though ComputeNumSignBits is still rudimentary,
this is enough to compile this:
short test(short X, short x) {
int Y = X+x;
return (Y >> 1);
}
short test2(short X, short x) {
int Y = (short)(X+x);
return Y >> 1;
}
into:
_test:
add r2, r3, r4
srawi r3, r2, 1
blr
_test2:
add r2, r3, r4
extsh r2, r2
srawi r3, r2, 1
blr
instead of:
_test:
add r2, r3, r4
srawi r2, r2, 1
extsh r3, r2
blr
_test2:
add r2, r3, r4
extsh r2, r2
srawi r2, r2, 1
extsh r3, r2
blr
llvm-svn: 28146
2006-05-06 09:30:03 +00:00
21cd99024a
When inserting casts, be careful of where we put them. We cannot insert
...
a cast immediately before a PHI node.
This fixes Regression/CodeGen/Generic/2006-05-06-GEP-Cast-Sink-Crash.ll
llvm-svn: 28143
2006-05-06 09:10:37 +00:00
907e392dba
Fold trunc(any_ext). This gives stuff like:
...
27,28c27
< movzwl %di, %edi
< movl %edi, %ebx
---
> movw %di, %bx
llvm-svn: 28137
2006-05-05 22:56:26 +00:00
57f8c5a387
Shrink shifts when possible.
...
llvm-svn: 28136
2006-05-05 22:53:17 +00:00
a633c31319
Indent multiline asm strings more nicely
...
llvm-svn: 28132
2006-05-05 21:47:05 +00:00
3d26577396
Fold (fpext (load x)) -> (extload x)
...
llvm-svn: 28130
2006-05-05 21:34:35 +00:00
3e3f2c63c3
More aggressively sink GEP offsets into loops. For example, before we
...
generated:
movl 8(%esp), %eax
movl %eax, %edx
addl $4316, %edx
cmpb $1, %cl
ja LBB1_2 #cond_false
LBB1_1: #cond_true
movl L_QuantizationTables720$non_lazy_ptr, %ecx
movl %ecx, (%edx)
movl L_QNOtoQuantTableShift720$non_lazy_ptr, %edx
movl %edx, 4460(%eax)
ret
...
Now we generate:
movl 8(%esp), %eax
cmpb $1, %cl
ja LBB1_2 #cond_false
LBB1_1: #cond_true
movl L_QuantizationTables720$non_lazy_ptr, %ecx
movl %ecx, 4316(%eax)
movl L_QNOtoQuantTableShift720$non_lazy_ptr, %ecx
movl %ecx, 4460(%eax)
ret
... which uses one fewer register.
llvm-svn: 28129
2006-05-05 21:17:49 +00:00
25a5283a86
Fold some common code.
...
llvm-svn: 28124
2006-05-05 06:32:04 +00:00
002ee91457
Implement:
...
// fold (and (sext x), (sext y)) -> (sext (and x, y))
// fold (or (sext x), (sext y)) -> (sext (or x, y))
// fold (xor (sext x), (sext y)) -> (sext (xor x, y))
// fold (and (aext x), (aext y)) -> (aext (and x, y))
// fold (or (aext x), (aext y)) -> (aext (or x, y))
// fold (xor (aext x), (aext y)) -> (aext (xor x, y))
llvm-svn: 28123
2006-05-05 06:31:05 +00:00
5ac4293606
Pull and through and/or/xor. This compiles some bitfield code to:
...
mov EAX, DWORD PTR [ESP + 4]
mov ECX, DWORD PTR [EAX]
mov EDX, ECX
add EDX, EDX
or EDX, ECX
and EDX, -2147483648
and ECX, 2147483647
or EDX, ECX
mov DWORD PTR [EAX], EDX
ret
instead of:
sub ESP, 4
mov DWORD PTR [ESP], ESI
mov EAX, DWORD PTR [ESP + 8]
mov ECX, DWORD PTR [EAX]
mov EDX, ECX
add EDX, EDX
mov ESI, ECX
and ESI, -2147483648
and EDX, -2147483648
or EDX, ESI
and ECX, 2147483647
or EDX, ECX
mov DWORD PTR [EAX], EDX
mov ESI, DWORD PTR [ESP]
add ESP, 4
ret
llvm-svn: 28122
2006-05-05 06:10:43 +00:00
812646aa0c
Implement a variety of simplifications for ANY_EXTEND.
...
llvm-svn: 28121
2006-05-05 05:58:59 +00:00
8d6fc20181
Factor some code, add these transformations:
...
// fold (and (trunc x), (trunc y)) -> (trunc (and x, y))
// fold (or (trunc x), (trunc y)) -> (trunc (or x, y))
// fold (xor (trunc x), (trunc y)) -> (trunc (xor x, y))
llvm-svn: 28120
2006-05-05 05:51:50 +00:00
78a7f0e05e
Fix VC++ compilation error.
...
llvm-svn: 28117
2006-05-05 01:47:05 +00:00
7a3ecf7993
Sink noop copies into the basic block that uses them. This reduces the number
...
of cross-block live ranges, and allows the bb-at-a-time selector to always
coallesce these away, at isel time.
This reduces the load on the coallescer and register allocator. For example
on a codec on X86, we went from:
1643 asm-printer - Number of machine instrs printed
419 liveintervals - Number of loads/stores folded into instructions
1144 liveintervals - Number of identity moves eliminated after coalescing
1022 liveintervals - Number of interval joins performed
282 liveintervals - Number of intervals after coalescing
1304 liveintervals - Number of original intervals
86 regalloc - Number of times we had to backtrack
1.90232 regalloc - Ratio of intervals processed over total intervals
40 spiller - Number of values reused
182 spiller - Number of loads added
121 spiller - Number of stores added
132 spiller - Number of register spills
6 twoaddressinstruction - Number of instructions commuted to coalesce
360 twoaddressinstruction - Number of two-address instructions
to:
1636 asm-printer - Number of machine instrs printed
403 liveintervals - Number of loads/stores folded into instructions
1155 liveintervals - Number of identity moves eliminated after coalescing
1033 liveintervals - Number of interval joins performed
279 liveintervals - Number of intervals after coalescing
1312 liveintervals - Number of original intervals
76 regalloc - Number of times we had to backtrack
1.88998 regalloc - Ratio of intervals processed over total intervals
1 spiller - Number of copies elided
41 spiller - Number of values reused
191 spiller - Number of loads added
114 spiller - Number of stores added
128 spiller - Number of register spills
4 twoaddressinstruction - Number of instructions commuted to coalesce
356 twoaddressinstruction - Number of two-address instructions
On this testcase, this change provides a modest reduction in spill code,
regalloc iterations, and total instructions emitted. It increases the number
of register coallesces.
llvm-svn: 28115
2006-05-05 01:04:50 +00:00
abdf4d569c
Final pass of minor cleanups for MachineInstr
...
llvm-svn: 28110
2006-05-04 19:36:09 +00:00
9add880566
Initial support for register pressure aware scheduling. The register reduction
...
scheduler can go into a "vertical mode" (i.e. traversing up the two-address
chain, etc.) when the register pressure is low.
This does seem to reduce the number of spills in the cases I've looked at. But
with x86, it's no guarantee the performance of the code improves.
It can be turned on with -sched-vertically option.
llvm-svn: 28108
2006-05-04 19:16:39 +00:00
53af9da363
Remove redundancy and a level of indirection when creating machine operands
...
llvm-svn: 28107
2006-05-04 19:14:44 +00:00
469647bf38
Remove and simplify some more machineinstr/machineoperand stuff.
...
llvm-svn: 28105
2006-05-04 18:16:01 +00:00
10b71c0d08
Rename MO_VirtualRegister -> MO_Register. Clean up immediate handling.
...
llvm-svn: 28104
2006-05-04 18:05:43 +00:00
10d6341618
Move some methods out of MachineInstr into MachineOperand
...
llvm-svn: 28102
2006-05-04 17:52:23 +00:00
fef7a2d0f5
There shalt be only one "immediate" operand type!
...
llvm-svn: 28099
2006-05-04 17:21:20 +00:00
15c52bda1d
Change "value" in MachineOperand to be a GlobalValue, as that is the only
...
thing that can be in it. Remove a dead method.
llvm-svn: 28098
2006-05-04 17:02:51 +00:00
ee64b6b40f
Remove a bunch more dead V9 specific stuff
...
llvm-svn: 28094
2006-05-04 01:26:39 +00:00
940cc978ef
Remove a bunch more SparcV9 specific stuff
...
llvm-svn: 28093
2006-05-04 01:15:02 +00:00
6e663f1c1e
Remove some more V9-specific stuff.
...
llvm-svn: 28092
2006-05-04 00:49:59 +00:00
9f6639b64d
Remove some more unused stuff from MachineInstr that was leftover from V9.
...
llvm-svn: 28091
2006-05-04 00:44:25 +00:00
1d8ee1fc80
Suck block address tracking out of targets into the JIT Emitter. This
...
simplifies the MachineCodeEmitter interface just a little bit and makes
BasicBlocks work like constant pools and jump tables.
llvm-svn: 28082
2006-05-03 17:10:41 +00:00
df4883971e
Finish up the initial jump table implementation by allowing jump tables to
...
not be 100% dense. Increase the minimum threshold for the number of cases
in a switch statement from 4 to 6 in order to create a jump table.
llvm-svn: 28079
2006-05-03 03:48:02 +00:00
ffef8b9412
Bottom up register pressure reduction work: clean up some hacks and enhanced
...
the heuristic to further reduce spills for several test cases. (Note, it may
not necessarily translate to runtime win!)
llvm-svn: 28076
2006-05-03 02:10:45 +00:00
20a631fde7
Refactor TargetMachine, pushing handling of TargetData into the target-specific subclasses. This has one caller-visible change: getTargetData() now returns a pointer instead of a reference.
...
This fixes PR 759.
llvm-svn: 28074
2006-05-03 01:29:57 +00:00
d8b192ba3b
Change the BasicBlockAddrs map to be a vector, indexed by MBB number.
...
llvm-svn: 28069
2006-05-03 00:32:55 +00:00
b8065a9a3a
Several related changes:
...
1. Change several methods in the MachineCodeEmitter class to be pure virtual.
2. Suck emitConstantPool/initJumpTableInfo into startFunction, removing them
from the MachineCodeEmitter interface, and reducing the amount of target-
specific code.
3. Change the JITEmitter so that it allocates constantpools and jump tables
*right* next to the functions that they belong to, instead of in a separate
pool of memory. This makes all memory for a function be contiguous, and
means the JITEmitter only tracks one block of memory now.
llvm-svn: 28065
2006-05-02 23:22:24 +00:00
23621fe8f4
Do not make the JIT memory manager manage the memory for globals. Instead
...
just have the JIT malloc them.
llvm-svn: 28062
2006-05-02 21:57:51 +00:00
c9aa3715e8
Refactor the machine code emitter interface to pull the pointers for the current
...
code emission location into the base class, instead of being in the derived classes.
This change means that low-level methods like emitByte/emitWord now are no longer
virtual (yaay for speed), and we now have a framework to support growable code
segments. This implements feature request #1 of PR469.
llvm-svn: 28059
2006-05-02 18:27:26 +00:00
4971ba5f41
Print function number instead of name
...
llvm-svn: 28057
2006-05-02 17:36:46 +00:00
67a3aa2aaa
Remove dead method
...
llvm-svn: 28055
2006-05-02 17:20:28 +00:00
bb1c345ec6
Remove the debug machine code emitter. The "FilePrinterEmitter" is more
...
useful for debugging.
llvm-svn: 28051
2006-05-02 16:59:24 +00:00
b9d4f8324d
Extend printBasicBlockLabel a bit so that it can be used to print all
...
basic block labels, consolidating the code to do so in one place for each
target.
llvm-svn: 28050
2006-05-02 05:37:32 +00:00
470f431f44
De-virtualize SwitchSection.
...
llvm-svn: 28047
2006-05-02 03:58:45 +00:00
f34ddb1e0d
De-virtualize EmitZeroes.
...
llvm-svn: 28046
2006-05-02 03:46:13 +00:00
24a62a9bc1
Make Intel syntax mode friendlier to Microsoft ML assembler (still needs more work).
...
llvm-svn: 28044
2006-05-02 01:16:28 +00:00
fd0a5478a1
Fix a latent bug that my spiller patch last week exposed: we were leaving
...
instructions in the virtregfolded map that were deleted. Because they
were deleted, newly allocated instructions could end up at the same address,
magically finding themselves in the map. The solution is to remove entries
from the map when we delete the instructions.
llvm-svn: 28041
2006-05-01 22:03:24 +00:00
ab7dbe0cc9
When promoting a load to a reg-reg copy, where the load was a previous
...
instruction folded with spill code, make sure the remove the load from
the virt reg folded map.
llvm-svn: 28040
2006-05-01 21:17:10 +00:00
4dee67c2cd
Remove previous patch, which wasn't quite right.
...
llvm-svn: 28039
2006-05-01 21:16:03 +00:00
0d084fb9ca
Dis-favor stores more
...
llvm-svn: 28035
2006-05-01 09:20:44 +00:00
24e795496d
Bottom up register-pressure reduction scheduler now pushes store operations
...
up the schedule. This helps code that looks like this:
loads ...
computations (first set) ...
stores (first set) ...
loads
computations (seccond set) ...
stores (seccond set) ...
Without this change, the stores and computations are more likely to
interleave:
loads ...
loads ...
computations (first set) ...
computations (second set) ...
computations (first set) ...
stores (first set) ...
computations (second set) ...
stores (stores set) ...
This can increase the number of spills if we are unlucky.
llvm-svn: 28033
2006-05-01 09:14:40 +00:00
10ff7b27ce
Didn't mean ScheduleDAGList.cpp to make the last checkin.
...
llvm-svn: 28030
2006-05-01 08:56:34 +00:00
a656242690
Remove temp. option -spiller-check-liveout, it didn't cause any failure nor performance regressions.
...
llvm-svn: 28029
2006-05-01 08:54:57 +00:00
25f55ae74a
Format #APP lines a bit nicer
...
llvm-svn: 28026
2006-05-01 04:11:03 +00:00
f71f0f2e0b
Local spiller kills a store if the folded restore is turned into a copy.
...
But this is incorrect if the spilled value live range extends beyond the
current BB.
It is currently controlled by a temporary option -spiller-check-liveout.
llvm-svn: 28024
2006-04-30 08:41:47 +00:00
2b48a94413
Remove a bogus transformation. This fixes SingleSource/UnitTests/2006-01-23-InitializedBitField.c
...
with some changes I have to the new CFE.
llvm-svn: 28022
2006-04-28 23:33:20 +00:00
c5e8ce8b8c
Remove the temporary option: -no-isel-fold-inflight
...
llvm-svn: 28012
2006-04-28 18:54:11 +00:00
d43c5c6046
TargetLowering::LowerArguments should return a VBIT_CONVERT of
...
FORMAL_ARGUMENTS SDOperand in the return result vector.
llvm-svn: 28009
2006-04-28 05:25:15 +00:00
79c50d96c9
Mapping of physregs can make it so that the designated and input physregs are
...
the same. In this case, don't emit a noop copy.
llvm-svn: 28008
2006-04-28 04:43:18 +00:00
51ab4498e7
Added a temporary option -no-isel-fold-inflight to control whether a "inflight"
...
node can be folded.
llvm-svn: 28003
2006-04-28 02:09:19 +00:00
84e95d00b5
When we have a two-address instruction where the input cannot be clobbered
...
and is already available, instead of falling back to emitting a load, fall
back to emitting a reg-reg copy. This generates significantly better code
for some SSE testcases, as SSE has lots of two-address instructions and
none of them are read/modify/write. As one example, this change does:
pshufd %XMM5, XMMWORD PTR [%ESP + 84], 255
xorps %XMM2, %XMM5
cmpltps %XMM1, %XMM0
- movaps XMMWORD PTR [%ESP + 52], %XMM0
- movapd %XMM6, XMMWORD PTR [%ESP + 52]
+ movaps %XMM6, %XMM0
cmpltps %XMM6, XMMWORD PTR [%ESP + 68]
movapd XMMWORD PTR [%ESP + 52], %XMM6
movaps %XMM6, %XMM0
cmpltps %XMM6, XMMWORD PTR [%ESP + 36]
cmpltps %XMM3, %XMM0
- movaps XMMWORD PTR [%ESP + 20], %XMM0
- movapd %XMM7, XMMWORD PTR [%ESP + 20]
+ movaps %XMM7, %XMM0
cmpltps %XMM7, XMMWORD PTR [%ESP + 4]
movapd XMMWORD PTR [%ESP + 20], %XMM7
cmpltps %XMM4, %XMM0
... which is far better than a store followed by a load!
llvm-svn: 28001
2006-04-28 01:46:50 +00:00
3784f3c57c
Insert a VBIT_CONVERT between a FORMAL_ARGUMENT node and its vector uses
...
(VAND, VADD, etc.). Legalizer will assert otherwise.
llvm-svn: 27991
2006-04-27 08:29:42 +00:00
393d96a56c
Fix Regression/CodeGen/Generic/2006-04-26-SetCCAnd.ll and
...
PR748.
llvm-svn: 27987
2006-04-27 05:01:07 +00:00
9618df1190
Don't forget return void.
...
llvm-svn: 27974
2006-04-25 23:03:35 +00:00
866b4b4d45
Fix the updating of the machine CFG when a PHI node was in a successor of
...
the jump table's range check block. This re-enables 100% dense jump tables
by default on PPC & x86
llvm-svn: 27952
2006-04-23 06:26:20 +00:00
3e04bb482b
Code cleanup associated with jump tables, thanks to Chris for noticing
...
these.
llvm-svn: 27950
2006-04-22 23:52:35 +00:00
ecb1dafd3d
Turn of jump tables for a bit, there are still some issues to work out with
...
updating the machine CFG.
llvm-svn: 27949
2006-04-22 23:51:56 +00:00
4ca2ea5b43
JumpTable support! What this represents is working asm and jit support for
...
x86 and ppc for 100% dense switch statements when relocations are non-PIC.
This support will be extended and enhanced in the coming days to support
PIC, and less dense forms of jump tables.
llvm-svn: 27947
2006-04-22 18:53:45 +00:00
b21d3bfd1f
The BFS scheduler is apparently nondeterminstic (causes many llvmgcc bootstrap
...
miscompares). Switch RISC targets to use the list-td scheduler, which isn't.
llvm-svn: 27933
2006-04-21 17:16:16 +00:00
662e940f73
Fix a couple more memory issues
...
llvm-svn: 27930
2006-04-21 15:32:26 +00:00
cc47ab3305
Fix a really subtle and obnoxious memory bug that caused issues with an
...
llvm-gcc4 boostrap. Whenever a node is deleted by the dag combiner, it
*must* be returned by the visit function, or the dag combiner will not
know that the node has been processed (and will, e.g., send it to the
target dag combine xforms).
llvm-svn: 27922
2006-04-20 23:55:59 +00:00
dcc1f995eb
This field no longer exists
...
llvm-svn: 27899
2006-04-20 18:32:41 +00:00
a38c3580bd
Remove some of the obvious V9-specific cruft
...
llvm-svn: 27893
2006-04-20 18:08:53 +00:00
a320abc494
Turn a VAND into a VECTOR_SHUFFLE is applicable.
...
DAG combiner can turn a VAND V, <-1, 0, -1, -1>, i.e. vector clear elements,
into a vector shuffle with a zero vector. It only does so when TLI tells it
the xform is profitable.
llvm-svn: 27874
2006-04-20 08:56:16 +00:00
bc1b262725
Implement folding of a bunch of binops with undef
...
llvm-svn: 27863
2006-04-20 05:39:12 +00:00
73eb58e1a2
Simplify some code
...
llvm-svn: 27846
2006-04-19 23:17:50 +00:00
916ae0775e
Fix handling of calls in functions that use vectors. This fixes a crash on
...
the code in GCC PR26546.
llvm-svn: 27780
2006-04-17 22:10:08 +00:00
bec79b4a59
Add a MachineInstr::eraseFromParent convenience method.
...
llvm-svn: 27775
2006-04-17 21:35:41 +00:00
326870b40b
Codegen insertelement with constant insertion points as scalar_to_vector
...
and a shuffle. For this:
void %test2(<4 x float>* %F, float %f) {
%tmp = load <4 x float>* %F ; <<4 x float>> [#uses=2]
%tmp3 = add <4 x float> %tmp, %tmp ; <<4 x float>> [#uses=1]
%tmp2 = insertelement <4 x float> %tmp3, float %f, uint 2 ; <<4 x float>> [#uses=2]
%tmp6 = add <4 x float> %tmp2, %tmp2 ; <<4 x float>> [#uses=1]
store <4 x float> %tmp6, <4 x float>* %F
ret void
}
we now get this on X86 (which will get better):
_test2:
movl 4(%esp), %eax
movaps (%eax), %xmm0
addps %xmm0, %xmm0
movaps %xmm0, %xmm1
shufps $3, %xmm1, %xmm1
movaps %xmm0, %xmm2
shufps $1, %xmm2, %xmm2
unpcklps %xmm1, %xmm2
movss 8(%esp), %xmm1
unpcklps %xmm1, %xmm0
unpcklps %xmm2, %xmm0
addps %xmm0, %xmm0
movaps %xmm0, (%eax)
ret
instead of:
_test2:
subl $28, %esp
movl 32(%esp), %eax
movaps (%eax), %xmm0
addps %xmm0, %xmm0
movaps %xmm0, (%esp)
movss 36(%esp), %xmm0
movss %xmm0, 8(%esp)
movaps (%esp), %xmm0
addps %xmm0, %xmm0
movaps %xmm0, (%eax)
addl $28, %esp
ret
llvm-svn: 27765
2006-04-17 19:21:01 +00:00
91226e5799
Add support for promoting stores from one legal type to another, allowing us
...
to write one pattern for vector stores instead of 4.
llvm-svn: 27730
2006-04-16 01:36:45 +00:00
7e7ad593cc
Make these predicates return true for bit_convert(buildvector)'s as well as
...
buildvectors.
llvm-svn: 27723
2006-04-15 23:38:00 +00:00
086e986e94
Make this assertion better
...
llvm-svn: 27695
2006-04-14 06:08:35 +00:00
709eaacb36
Expand some code with temporary variables to rid ourselves of the warning
...
about "dereferencing type-punned pointer will break strict-aliasing rules"
llvm-svn: 27671
2006-04-13 18:29:58 +00:00
119266ea92
Promote vector AND, OR, and XOR
...
llvm-svn: 27632
2006-04-12 21:20:24 +00:00
be8a8933e6
Vector type promotion for ISD::LOAD and ISD::SELECT
...
llvm-svn: 27606
2006-04-12 16:33:18 +00:00
Evan Cheng