| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1. Fix an illegal argument to getClassB when deciding whether or not to
sign extend a byte load.
2. Initial addition of isLoad and isStore flags to the instruction .td file
for eventual use in a scheduler.
3. Rewrite of how constants are handled in emitSimpleBinaryOperation so
that we can emit the PowerPC shifted immediate instructions far more
often. This allows us to emit the following code:
int foo(int x) { return x | 0x00F0000; }
_foo:
.LBB_foo_0: ; entry
; IMPLICIT_DEF
oris r3, r3, 15
blr
llvm-svn: 16826
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
loading a 32bit constant into a register whose low halfword is all zeroes.
We now omit the ori after the lis for the following C code:
int bar(int y) { return y * 0x00F0000; }
_bar:
.LBB_bar_0: ; entry
; IMPLICIT_DEF
lis r2, 15
mullw r3, r3, r2
blr
llvm-svn: 16825
|
| |
|
|
| |
llvm-svn: 16824
|
| |
|
|
| |
llvm-svn: 16770
|
| |
|
|
|
|
| |
the JIT had last night.
llvm-svn: 16766
|
| |
|
|
| |
llvm-svn: 16765
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
instruction.
Now, rather than emitting the following loop out of bisect:
.LBB_main_19: ; no_exit.0.i
rlwinm r3, r2, 3, 0, 28
lfdx f1, r3, r27
addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
lfd f2, lo16(.CPI_main_1-"L00000$pb")(r3)
fsub f2, f2, f1
addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
lfd f4, lo16(.CPI_main_1-"L00000$pb")(r3)
fcmpu cr0, f1, f4
bge .LBB_main_64 ; no_exit.0.i
.LBB_main_63: ; no_exit.0.i
b .LBB_main_65 ; no_exit.0.i
.LBB_main_64: ; no_exit.0.i
fmr f2, f1
.LBB_main_65: ; no_exit.0.i
addi r3, r2, 1
rlwinm r3, r3, 3, 0, 28
lfdx f1, r3, r27
addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
lfd f4, lo16(.CPI_main_1-"L00000$pb")(r3)
fsub f4, f4, f1
addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
lfd f5, lo16(.CPI_main_1-"L00000$pb")(r3)
fcmpu cr0, f1, f5
bge .LBB_main_67 ; no_exit.0.i
.LBB_main_66: ; no_exit.0.i
b .LBB_main_68 ; no_exit.0.i
.LBB_main_67: ; no_exit.0.i
fmr f4, f1
.LBB_main_68: ; no_exit.0.i
fadd f1, f2, f4
addis r3, r30, ha16(.CPI_main_2-"L00000$pb")
lfd f2, lo16(.CPI_main_2-"L00000$pb")(r3)
fmul f1, f1, f2
rlwinm r3, r2, 3, 0, 28
lfdx f2, r3, r28
fadd f4, f2, f1
fcmpu cr0, f4, f0
bgt .LBB_main_70 ; no_exit.0.i
.LBB_main_69: ; no_exit.0.i
b .LBB_main_71 ; no_exit.0.i
.LBB_main_70: ; no_exit.0.i
fmr f0, f4
.LBB_main_71: ; no_exit.0.i
fsub f1, f2, f1
addi r2, r2, -1
fcmpu cr0, f1, f3
blt .LBB_main_73 ; no_exit.0.i
.LBB_main_72: ; no_exit.0.i
b .LBB_main_74 ; no_exit.0.i
.LBB_main_73: ; no_exit.0.i
fmr f3, f1
.LBB_main_74: ; no_exit.0.i
cmpwi cr0, r2, -1
fmr f16, f0
fmr f17, f3
bgt .LBB_main_19 ; no_exit.0.i
We emit this instead:
.LBB_main_19: ; no_exit.0.i
rlwinm r3, r2, 3, 0, 28
lfdx f1, r3, r27
addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
lfd f2, lo16(.CPI_main_1-"L00000$pb")(r3)
fsub f2, f2, f1
fsel f1, f1, f1, f2
addi r3, r2, 1
rlwinm r3, r3, 3, 0, 28
lfdx f2, r3, r27
addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
lfd f4, lo16(.CPI_main_1-"L00000$pb")(r3)
fsub f4, f4, f2
fsel f2, f2, f2, f4
fadd f1, f1, f2
addis r3, r30, ha16(.CPI_main_2-"L00000$pb")
lfd f2, lo16(.CPI_main_2-"L00000$pb")(r3)
fmul f1, f1, f2
rlwinm r3, r2, 3, 0, 28
lfdx f2, r3, r28
fadd f4, f2, f1
fsub f5, f0, f4
fsel f0, f5, f0, f4
fsub f1, f2, f1
addi r2, r2, -1
fsub f2, f1, f3
fsel f3, f2, f3, f1
cmpwi cr0, r2, -1
fmr f16, f0
fmr f17, f3
bgt .LBB_main_19 ; no_exit.0.i
llvm-svn: 16764
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
t:
mov %EDX, DWORD PTR [%ESP + 4]
mov %ECX, 2
mov %EAX, %EDX
sar %EDX, 31
idiv %ECX
mov %EAX, %EDX
ret
Generate:
t:
mov %ECX, DWORD PTR [%ESP + 4]
*** mov %EAX, %ECX
cdq
and %ECX, 1
xor %ECX, %EDX
sub %ECX, %EDX
*** mov %EAX, %ECX
ret
Note that the two marked moves are redundant, and should be eliminated by the
register allocator, but aren't.
Compare this to GCC, which generates:
t:
mov %eax, DWORD PTR [%esp+4]
mov %edx, %eax
shr %edx, 31
lea %ecx, [%edx+%eax]
and %ecx, -2
sub %eax, %ecx
ret
or ICC 8.0, which generates:
t:
movl 4(%esp), %ecx #3.5
movl $-2147483647, %eax #3.25
imull %ecx #3.25
movl %ecx, %eax #3.25
sarl $31, %eax #3.25
addl %ecx, %edx #3.25
subl %edx, %eax #3.25
addl %eax, %eax #3.25
negl %eax #3.25
subl %eax, %ecx #3.25
movl %ecx, %eax #3.25
ret #3.25
We would be in great shape if not for the moves.
llvm-svn: 16763
|
| |
|
|
|
|
| |
Thanks to Jeff Cohen for pointing out my goof.
llvm-svn: 16762
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
s: ;; X / 4
mov %EAX, DWORD PTR [%ESP + 4]
mov %ECX, %EAX
sar %ECX, 1
shr %ECX, 30
mov %EDX, %EAX
add %EDX, %ECX
sar %EAX, 2
ret
When we really meant:
s:
mov %EAX, DWORD PTR [%ESP + 4]
mov %ECX, %EAX
sar %ECX, 1
shr %ECX, 30
add %EAX, %ECX
sar %EAX, 2
ret
Hey, this also reduces register pressure too :)
llvm-svn: 16761
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
instead of:
s: ;; X / 2
movl 4(%esp), %eax
movl %eax, %ecx
shrl $31, %ecx
movl %eax, %edx
addl %ecx, %edx
sarl $1, %eax
ret
t: ;; X / -2
movl 4(%esp), %eax
movl %eax, %ecx
shrl $31, %ecx
movl %eax, %edx
addl %ecx, %edx
sarl $1, %eax
negl %eax
ret
Emit:
s:
movl 4(%esp), %eax
cmpl $-2147483648, %eax
sbbl $-1, %eax
sarl $1, %eax
ret
t:
movl 4(%esp), %eax
cmpl $-2147483648, %eax
sbbl $-1, %eax
sarl $1, %eax
negl %eax
ret
llvm-svn: 16760
|
| |
|
|
| |
llvm-svn: 16759
|
| |
|
|
| |
llvm-svn: 16756
|
| |
|
|
|
|
|
|
| |
* Update comments
* Rearrange code a bit
* Finally ELIMINATE the GAS workaround emitter for Intel mode. woot!
llvm-svn: 16647
|
| |
|
|
|
|
| |
may now choose their output format with the -x86-asm-syntax={intel|att} flag.
llvm-svn: 16646
|
| |
|
|
| |
llvm-svn: 16645
|
| |
|
|
|
|
|
|
|
| |
old and broken AT&T syntax assemblers. The problem with this hack is that
*SOME* forms of the fdiv and fsub instructions have the 'r' bit inverted.
This was a real pain to figure out, but is trivially easy to support: thus
we are now bug compatible with gas and gcc.
llvm-svn: 16644
|
| |
|
|
| |
llvm-svn: 16642
|
| |
|
|
| |
llvm-svn: 16641
|
| |
|
|
| |
llvm-svn: 16640
|
| |
|
|
|
|
|
|
| |
Intel and AT&T style assembly language. The ultimate goal of this is to
eliminate the GasBugWorkaroundEmitter class, but for now AT&T style emission
is not fully operational.
llvm-svn: 16639
|
| |
|
|
|
|
|
|
|
| |
hopefully lead to the death of the 'GasBugWorkaroundEmitter'. This also
includes changes to wrap the whole file to 80 columns! Woot! :)
Note that the AT&T style output has not been tested at all.
llvm-svn: 16638
|
| |
|
|
| |
llvm-svn: 16635
|
| |
|
|
|
|
| |
or cleared externally.
llvm-svn: 16623
|
| |
|
|
| |
llvm-svn: 16618
|
| |
|
|
|
|
| |
Add some comments.
llvm-svn: 16611
|
| |
|
|
|
|
| |
to find instrs that have delay slots.
llvm-svn: 16610
|
| |
|
|
|
|
|
| |
won't work if not compiled in V9 mode, currently by GCC only, because Sun's
system compiler does not tell us if it's a V8 or V9 system.
llvm-svn: 16602
|
| |
|
|
| |
llvm-svn: 16595
|
| |
|
|
| |
llvm-svn: 16594
|
| |
|
|
| |
llvm-svn: 16591
|
| |
|
|
|
|
| |
something, because the wrong bit patterns get output.
llvm-svn: 16590
|
| |
|
|
| |
llvm-svn: 16586
|
| |
|
|
|
|
| |
instruction. Don't create overlapping register lifetimes
llvm-svn: 16580
|
| |
|
|
| |
llvm-svn: 16579
|
| |
|
|
| |
llvm-svn: 16578
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Copy constant-pool entries' addresses into registers before loading out of them,
to avoid errors from the assembler.
Handle loading call args past the 6th one off the stack.
Add IMPLICIT_DEF pseudo-instrs for double and long arguments passed in register
pairs.
Use FpMOVD to copy doubles around instead of the horrible store-load thing we
were doing before.
Handle 'ret double' and 'ret long'.
Fix a bug in handling 'and/or/xor long'.
llvm-svn: 16577
|
| |
|
|
|
|
| |
moves, not all ORs.
llvm-svn: 16576
|
| |
|
|
| |
llvm-svn: 16575
|
| |
|
|
| |
llvm-svn: 16574
|
| |
|
|
|
|
| |
Call the FPMover pass after register allocation.
llvm-svn: 16573
|
| |
|
|
| |
llvm-svn: 16572
|
| |
|
|
| |
llvm-svn: 16571
|
| |
|
|
|
|
| |
of FMOVS instrs.
llvm-svn: 16570
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
integers that we can use as immediate values in instructions.
Example from yacr2:
- lis r10, -1
- ori r10, r10, 65535
- add r28, r28, r10
+ addi r28, r28, -1
addi r7, r7, 1
addi r9, r9, 1
b .LBB_main_9 ; loopentry.1.i214
llvm-svn: 16566
|
| |
|
|
|
|
| |
scheduler
llvm-svn: 16555
|
| |
|
|
| |
llvm-svn: 16551
|
| |
|
|
| |
llvm-svn: 16536
|
| |
|
|
|
|
| |
compilation problem in windows.
llvm-svn: 16535
|
| |
|
|
|
|
| |
compile under windows. Patch contributed by Paolo Invernizzi!
llvm-svn: 16534
|