d0p1/ack
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity
ack/mach/powerpc/ncg/table
George Koehler 1de1e8f7f0 Experiment with conversions between integers and floats. 
Switch some conversions from libem calls to inline code.  The
conversions from integers to floats are now too slow, because each
conversion allocates 4 or 5 registers, and the register allocator is
too slow.  I might use these slow conversions to experiment with the
register allocator.

I add the missing conversions between 4-byte single floats and
integers, simply by going through 8-byte double floats.  (These
replace the calls to nonexistant functions in libem.)

I remove the placeholder for fef 4, because it doesn't exist in libem,
and our language runtimes only use fef 8.
2017-02-12 15:45:28 -05:00

2418 lines
58 KiB
Plaintext
Raw Blame History

EM_WSIZE = 4
EM_PSIZE = 4
EM_BSIZE = 8 /* two words saved in call frame */
INT8 = 1 /* Size of values */
INT16 = 2
INT32 = 4
INT64 = 8
FP_OFFSET = 0 /* Offset of saved FP relative to our FP */
PC_OFFSET = 4 /* Offset of saved PC relative to our FP */
#define COMMENT(n) /* comment {LABEL, n} */
#define nicesize(x) ((x)==INT8 || (x)==INT16 || (x)==INT32 || (x)==INT64)
#define smalls(n) sfit(n, 16)
#define smallu(n) ufit(n, 16)
#define lo(n) ((n) & 0xFFFF)
#define hi(n) (((n)>>16) & 0xFFFF)
/* Use these for instructions that treat the low half as signed --- his()
* includes a modifier to produce the correct value when the low half gets
* sign extended. Er, do make sure you load the low half second. */
#define los(n) (lo(n) | (((0-(lo(n)>>15)) & ~0xFFFF)))
#define his(n) ((hi(n) + (lo(n)>>15)) & 0xFFFF)
PROPERTIES
GPR /* any GPR */
REG /* any allocatable GPR */
REG_PAIR(8) /* speed hack for sti 8 */
FPR(8) /* any FPR */
FREG(8) /* any allocatable FPR */
FSREG /* any allocatable single-precision FPR */
SPR /* any SPR */
CR /* any CR */
GPR0 GPRSP GPRFP GPR3 GPR4 GPR5 GPR6 GPR7
GPR8 GPR9 GPR10 GPR11 GPR12 GPR13 GPR14 GPR15
GPR16 GPR17 GPR18 GPR19 GPR20 GPR21 GPR22 GPR23
GPR24 GPR25 GPR26 GPR27 GPR28 GPR29 GPR30 GPR31
FPR0(8) FPR1(8) FPR2(8) FPR3(8) FPR4(8) FPR5(8) FPR6(8) FPR7(8)
FPR8(8) FPR9(8) FPR10(8) FPR11(8) FPR12(8) FPR13(8) FPR14(8) FPR15(8)
FPR16(8) FPR17(8) FPR18(8) FPR19(8) FPR20(8) FPR21(8) FPR22(8) FPR23(8)
FPR24(8) FPR25(8) FPR26(8) FPR27(8) FPR28(8) FPR29(8) FPR30(8) FPR31(8)
REGISTERS
/* Reverse order to encourage ncg to allocate them from r31 down */
R31("r31") : GPR, REG, GPR31 regvar.
R30("r30") : GPR, REG, GPR30 regvar.
R29("r29") : GPR, REG, GPR29 regvar.
R28("r28") : GPR, REG, GPR28 regvar.
R27("r27") : GPR, REG, GPR27 regvar.
R26("r26") : GPR, REG, GPR26 regvar.
R25("r25") : GPR, REG, GPR25 regvar.
R24("r24") : GPR, REG, GPR24 regvar.
R23("r23") : GPR, REG, GPR23 regvar.
R22("r22") : GPR, REG, GPR22 regvar.
R21("r21") : GPR, REG, GPR21 regvar.
R20("r20") : GPR, REG, GPR20 regvar.
R19("r19") : GPR, REG, GPR19 regvar.
R18("r18") : GPR, REG, GPR18 regvar.
R17("r17") : GPR, REG, GPR17 regvar.
R16("r16") : GPR, REG, GPR16 regvar.
R15("r15") : GPR, REG, GPR15 regvar.
R14("r14") : GPR, REG, GPR14 regvar.
R13("r13") : GPR, REG, GPR13 regvar.
R12("r12") : GPR, REG, GPR12.
R11("r11") : GPR, REG, GPR11.
R10("r10") : GPR, REG, GPR10.
R9("r9") : GPR, REG, GPR9.
R8("r8") : GPR, REG, GPR8.
R7("r7") : GPR, REG, GPR7.
R6("r6") : GPR, REG, GPR6.
R5("r5") : GPR, REG, GPR5.
R4("r4") : GPR, REG, GPR4.
R3("r3") : GPR, REG, GPR3.
FP("fp") : GPR, GPRFP.
SP("sp") : GPR, GPRSP.
R0("r0") : GPR, GPR0.
/* speed hack for sti 8 */
PAIR_R9_R10=R9+R10 : REG_PAIR.
PAIR_R7_R8=R7+R8 : REG_PAIR.
PAIR_R5_R6=R5+R6 : REG_PAIR.
PAIR_R3_R4=R3+R4 : REG_PAIR.
/*
* F14 to F31 are reserved for regvar, if we ever implement
* it. Don't add them to FREG; the register allocator would
* be too slow.
*/
F31("f31") : FPR, FPR31.
F30("f30") : FPR, FPR30.
F29("f29") : FPR, FPR29.
F28("f28") : FPR, FPR28.
F27("f27") : FPR, FPR27.
F26("f26") : FPR, FPR26.
F25("f25") : FPR, FPR25.
F24("f24") : FPR, FPR24.
F23("f23") : FPR, FPR23.
F22("f22") : FPR, FPR22.
F21("f21") : FPR, FPR21.
F20("f20") : FPR, FPR20.
F19("f19") : FPR, FPR19.
F18("f18") : FPR, FPR18.
F17("f17") : FPR, FPR17.
F16("f16") : FPR, FPR16.
F15("f15") : FPR, FPR15.
F14("f14") : FPR, FPR14.
F13("f13") : FPR, FREG, FPR13.
F12("f12") : FPR, FREG, FPR12.
F11("f11") : FPR, FREG, FPR11.
F10("f10") : FPR, FREG, FPR10.
F9("f9") : FPR, FREG, FPR9.
F8("f8") : FPR, FREG, FPR8.
F7("f7") : FPR, FREG, FPR7.
F6("f6") : FPR, FREG, FPR6.
F5("f5") : FPR, FREG, FPR5.
F4("f4") : FPR, FREG, FPR4.
F3("f3") : FPR, FREG, FPR3.
F2("f2") : FPR, FREG, FPR2.
F1("f1") : FPR, FREG, FPR1.
F0("f0") : FPR, FPR0.
FS13("f13")=F13 : FSREG.
FS12("f12")=F12 : FSREG.
FS11("f11")=F11 : FSREG.
FS10("f10")=F10 : FSREG.
FS9("f9")=F9 : FSREG.
FS8("f8")=F8 : FSREG.
FS7("f7")=F7 : FSREG.
FS6("f6")=F6 : FSREG.
FS5("f5")=F5 : FSREG.
FS4("f4")=F4 : FSREG.
FS3("f3")=F3 : FSREG.
FS2("f2")=F2 : FSREG.
FS1("f1")=F1 : FSREG.
LR("lr") : SPR.
CTR("ctr") : SPR.
CR0("cr0") : CR.
#define RSCRATCH R0
#define FSCRATCH F0
TOKENS
/* Primitives */
CONST = { INT val; } 4 val.
LABEL = { ADDR adr; } 4 adr.
LABEL_HI = { ADDR adr; } 4 "hi16[" adr "]".
LABEL_HA = { ADDR adr; } 4 "ha16[" adr "]".
LABEL_LO = { ADDR adr; } 4 "lo16[" adr "]".
LOCAL = { INT off; } 4 ">>> BUG IN LOCAL".
/* Allows us to use regvar() to refer to registers */
GPRE = { GPR reg; } 4 reg.
/* Constants on the stack */
CONST_N8000 = { INT val; } 4.
CONST_N7FFF_N0001 = { INT val; } 4.
CONST_0000_7FFF = { INT val; } 4.
CONST_8000 = { INT val; } 4.
CONST_8001_FFFF = { INT val; } 4.
CONST_HZ = { INT val; } 4.
CONST_HL = { INT val; } 4.
/* Expression partial results */
SUM_RIS = { GPR reg; INT offhi; } 4. /* reg + (offhi << 16) */
SUM_RC = { GPR reg; INT off; } 4. /* reg + off */
SUM_RL = { GPR reg; ADDR adr; } 4. /* reg + lo16[adr] */
SUM_RR = { GPR reg1; GPR reg2; } 4. /* reg1 + reg2 */
SEX_B = { GPR reg; } 4.
SEX_H = { GPR reg; } 4.
IND_RC_B = { GPR reg; INT off; } 4 off "(" reg ")".
IND_RL_B = { GPR reg; ADDR adr; } 4 "lo16[" adr "](" reg ")".
IND_RR_B = { GPR reg1; GPR reg2; } 4.
IND_RC_H = { GPR reg; INT off; } 4 off "(" reg ")".
IND_RL_H = { GPR reg; ADDR adr; } 4 "lo16[" adr "](" reg ")".
IND_RR_H = { GPR reg1; GPR reg2; } 4.
IND_RC_H_S = { GPR reg; INT off; } 4 off "(" reg ")".
IND_RL_H_S = { GPR reg; ADDR adr; } 4 "lo16[" adr "](" reg ")".
IND_RR_H_S = { GPR reg1; GPR reg2; } 4.
IND_RC_W = { GPR reg; INT off; } 4 off "(" reg ")".
IND_RL_W = { GPR reg; ADDR adr; } 4 "lo16[" adr "](" reg ")".
IND_RR_W = { GPR reg1; GPR reg2; } 4.
IND_RC_D = { GPR reg; INT off; } 8 off "(" reg ")".
IND_RL_D = { GPR reg; ADDR adr; } 8 "lo16[" adr "](" reg ")".
IND_RR_D = { GPR reg1; GPR reg2; } 8.
NOT_R = { GPR reg; } 4.
AND_RR = { GPR reg1; GPR reg2; } 4.
OR_RR = { GPR reg1; GPR reg2; } 4.
OR_RIS = { GPR reg; INT valhi; } 4.
OR_RC = { GPR reg; INT val; } 4.
XOR_RR = { GPR reg1; GPR reg2; } 4.
XOR_RIS = { GPR reg; INT valhi; } 4.
XOR_RC = { GPR reg; INT val; } 4.
COND_RC = { GPR reg; INT val; } 4.
COND_RR = { GPR reg1; GPR reg2; } 4.
CONDL_RC = { GPR reg; INT val; } 4.
CONDL_RR = { GPR reg1; GPR reg2; } 4.
COND_FS = { FSREG reg1; FSREG reg2; } 4.
COND_FD = { FREG reg1; FREG reg2; } 4.
XEQ = { GPR reg; } 4.
XNE = { GPR reg; } 4.
XGT = { GPR reg; } 4.
XGE = { GPR reg; } 4.
XLT = { GPR reg; } 4.
XLE = { GPR reg; } 4.
SETS
/* signed 16-bit integer */
CONST2 = CONST_N8000 + CONST_N7FFF_N0001 + CONST_0000_7FFF.
/* integer that, when negated, fits signed 16-bit */
CONST2_WHEN_NEG = CONST_N7FFF_N0001 + CONST_0000_7FFF + CONST_8000.
/* unsigned 16-bit integer */
UCONST2 = CONST_0000_7FFF + CONST_8000 + CONST_8001_FFFF.
/* any constant on stack */
CONST_STACK = CONST_N8000 + CONST_N7FFF_N0001 + CONST_0000_7FFF +
CONST_8000 + CONST_8001_FFFF + CONST_HZ + CONST_HL.
SUM_ALL = SUM_RC + SUM_RL + SUM_RR.
SEX_ALL = SEX_B + SEX_H.
LOGICAL_ALL = NOT_R + AND_RR + OR_RR + OR_RC + XOR_RR +
XOR_RC.
IND_ALL_B = IND_RC_B + IND_RL_B + IND_RR_B.
IND_ALL_H = IND_RC_H + IND_RL_H + IND_RR_H +
IND_RC_H_S + IND_RL_H_S + IND_RR_H_S.
IND_ALL_W = IND_RC_W + IND_RL_W + IND_RR_W.
IND_ALL_D = IND_RC_D + IND_RL_D + IND_RR_D.
IND_ALL_BHW = IND_ALL_B + IND_ALL_H + IND_ALL_W.
/* anything killed by sti (store indirect) */
MEMORY = IND_ALL_BHW + IND_ALL_D.
/* any stack token that we can easily move to GPR */
ANY_BHW = REG + CONST_STACK + SEX_ALL +
SUM_ALL + IND_ALL_BHW + LOGICAL_ALL.
INSTRUCTIONS
/* We give time as cycles of total latency from Freescale
* Semiconductor, MPC7450 RISC Microprocessor Family Reference
* Manual, Rev. 5, section 6.6.
*
* We have only 4-byte alignment for doubles; 8-byte alignment is
* optimal. We guess the misalignment penalty by adding 1 cycle to
* the cost of loading or storing a double:
* lfd lfdu lfdx: 4 -> 5
* stfd stfdu stfdx: 3 -> 4
*/
cost(4, 1) /* space, time */
add GPR:wo, GPR:ro, GPR:ro.
addX "add." GPR:wo, GPR:ro, GPR:ro.
addi GPR:wo, GPR:ro, CONST+LABEL_LO:ro.
li GPR:wo, CONST:ro.
addis GPR:wo, GPR:ro, CONST+LABEL_HI+LABEL_HA:ro.
lis GPR:wo, CONST+LABEL_HI+LABEL_HA:ro.
and GPR:wo, GPR:ro, GPR:ro.
andc GPR:wo, GPR:ro, GPR:ro.
andiX "andi." GPR:wo:cc, GPR:ro, CONST:ro.
andisX "andis." GPR:wo:cc, GPR:ro, CONST:ro.
b LABEL:ro.
bc CONST:ro, CONST:ro, LABEL:ro.
bdnz LABEL:ro.
beq LABEL:ro.
bne LABEL:ro.
bgt LABEL:ro.
bge LABEL:ro.
blt LABEL:ro.
ble LABEL:ro.
bxx LABEL:ro. /* dummy */
bcctr CONST:ro, CONST:ro, CONST:ro.
bctr.
bcctrl CONST:ro, CONST:ro, CONST:ro.
bctrl.
bclr CONST:ro, CONST:ro, CONST:ro.
bl LABEL:ro.
cmp CR:ro, CONST:ro, GPR:ro, GPR:ro kills :cc.
cmpw GPR:ro, GPR:ro kills :cc.
cmpi CR:ro, CONST:ro, GPR:ro, CONST:ro kills :cc.
cmpwi GPR:ro, CONST:ro kills :cc.
cmpl CR:ro, CONST:ro, GPR:ro, GPR:ro kills :cc.
cmplw GPR:ro, GPR:ro kills :cc.
cmpli CR:ro, CONST:ro, GPR:ro, CONST:ro kills :cc.
cmplwi GPR:ro, CONST:ro kills :cc.
divw GPR:wo, GPR:ro, GPR:ro cost(4, 23).
divwu GPR:wo, GPR:ro, GPR:ro cost(4, 23).
eqv GPR:wo, GPR:ro, GPR:ro.
extsb GPR:wo, GPR:ro.
extsh GPR:wo, GPR:ro.
fadd FREG:wo, FREG:ro, FREG:ro cost(4, 5).
fadds FSREG:wo, FSREG:ro, FSREG:ro cost(4, 5).
fcmpo CR:wo, FREG:ro, FREG:ro cost(4, 5).
fcmpo CR:wo, FSREG:ro, FSREG:ro cost(4, 5).
fctiwz FREG:wo, FREG:ro.
fdiv FREG:wo, FREG:ro, FREG:ro cost(4, 35).
fdivs FSREG:wo, FSREG:ro, FSREG:ro cost(4, 21).
fmr FPR:wo, FPR:ro cost(4, 5).
fmr FSREG:wo, FSREG:ro cost(4, 5).
fmul FREG:wo, FREG:ro, FREG:ro cost(4, 5).
fmuls FSREG:wo, FSREG:ro, FSREG:ro cost(4, 5).
fneg FREG:wo, FREG:ro cost(4, 5).
fneg FSREG:wo, FSREG:ro cost(4, 5).
frsp FSREG:wo, FREG:ro cost(4, 5).
fsub FREG:wo, FREG:ro, FREG:ro cost(4, 5).
fsubs FSREG:wo, FSREG:ro, FSREG:ro cost(4, 5).
lbz GPR:wo, IND_RC_B+IND_RL_B:ro cost(4, 3).
lbzx GPR:wo, GPR:ro, GPR:ro cost(4, 3).
lfd FPR:wo, IND_RC_D+IND_RL_D:ro cost(4, 5).
lfdu FPR:wo, IND_RC_D:ro cost(4, 5).
lfdx FPR:wo, GPR:ro, GPR:ro cost(4, 5).
lfs FSREG:wo, IND_RC_W+IND_RL_W:ro cost(4, 4).
lfsu FSREG:wo, IND_RC_W:rw cost(4, 4).
lfsx FSREG:wo, GPR:ro, GPR:ro cost(4, 4).
lha GPR:wo, IND_RC_H_S+IND_RL_H_S:ro cost(4, 3).
lhax GPR:wo, GPR:ro, GPR:ro cost(4, 3).
lhz GPR:wo, IND_RC_H+IND_RL_H:ro cost(4, 3).
lhzx GPR:wo, GPR:ro, GPR:ro cost(4, 3).
lwzu GPR:wo, IND_RC_W:ro cost(4, 3).
lwzx GPR:wo, GPR:ro, GPR:ro cost(4, 3).
lwz GPR:wo, IND_RC_W+IND_RL_W:ro cost(4, 3).
nand GPR:wo, GPR:ro, GPR:ro.
neg GPR:wo, GPR:ro.
nor GPR:wo, GPR:ro, GPR:ro.
mfcr GPR:wo cost(4,2).
mullw GPR:wo, GPR:ro, GPR:ro cost(4, 4).
mfspr GPR:wo, SPR:ro cost(4, 3).
mtspr SPR:wo, GPR:ro cost(4, 2).
or GPR:wo, GPR:ro, GPR:ro.
mr GPR:wo, GPR:ro.
orX "or." GPR:wo:cc, GPR:ro, GPR:ro.
orX_readonly "or." GPR:ro:cc, GPR:ro, GPR:ro.
orc GPR:wo, GPR:ro, GPR:ro.
ori GPR:wo, GPR:ro, CONST+LABEL_LO:ro.
oris GPR:wo, GPR:ro, CONST:ro.
rlwinm GPR:wo, GPR:ro, CONST:ro, CONST:ro, CONST:ro.
extlwi GPR:wo, GPR:ro, CONST:ro, CONST:ro.
extrwi GPR:wo, GPR:ro, CONST:ro, CONST:ro.
srwi GPR:wo, GPR:ro, CONST:ro.
slw GPR:wo, GPR:ro, GPR:ro.
subf GPR:wo, GPR:ro, GPR:ro.
sraw GPR:wo, GPR:ro, GPR:ro cost(4, 2).
srawi GPR:wo, GPR:ro, CONST:ro cost(4, 2).
srw GPR:wo, GPR:ro, GPR:ro.
stb GPR:ro, IND_RC_B+IND_RL_B:rw cost(4, 3).
stbx GPR:ro, GPR:ro, GPR:ro cost(4, 3).
stfd FPR:ro, IND_RC_D+IND_RL_D:rw cost(4, 4).
stfdu FPR:ro, IND_RC_D:rw cost(4, 4).
stfdx FPR:ro, GPR:ro, GPR:ro cost(4, 4).
stfs FSREG:ro, IND_RC_W+IND_RL_W:rw cost(4, 3).
stfsu FSREG:ro, IND_RC_W:rw cost(4, 3).
stfsx FSREG:ro, GPR:ro, GPR:ro cost(4, 3).
sth GPR:ro, IND_RC_H+IND_RL_H:rw cost(4, 3).
sthx GPR:ro, GPR:ro, GPR:ro cost(4, 3).
stw GPR:ro, IND_RC_W+IND_RL_W:rw cost(4, 3).
stwx GPR:ro, GPR:ro, GPR:ro cost(4, 3).
stwu GPR+LOCAL:ro, IND_RC_W:rw cost(4, 3).
xor GPR:wo, GPR:ro, GPR:ro.
xori GPR:wo, GPR:ro, CONST:ro.
xoris GPR:wo, GPR:ro, CONST:ro.
comment "!" LABEL:ro cost(0, 0).
MOVES
from GPR to GPR
gen mr %2, %1
/* Constants */
from CONST + CONST_STACK smalls(%val) to GPR
gen
COMMENT("move CONST->GPR smalls")
li %2, {CONST, %1.val}
from CONST + CONST_STACK lo(%val)==0 to GPR
gen
COMMENT("move CONST->GPR shifted")
lis %2, {CONST, hi(%1.val)}
from CONST + CONST_STACK to GPR
gen
COMMENT("move CONST->GPR")
lis %2, {CONST, hi(%1.val)}
ori %2, %2, {CONST, lo(%1.val)}
/* Can't use addi %2, %2, {CONST, los(%1.val)}
* because %2 might be R0. */
from LABEL to GPR
gen
COMMENT("move LABEL->GPR")
lis %2, {LABEL_HI, %1.adr}
ori %2, %2, {LABEL_LO, %1.adr}
from LABEL_HA to GPR
gen lis %2, %1
/* Sign extension */
from SEX_B to GPR
gen extsb %2, %1.reg
from SEX_H to GPR
gen extsh %2, %1.reg
/* Register + something */
from SUM_RIS to GPR
gen addis %2, %1.reg, {CONST, %1.offhi}
from SUM_RC to GPR
gen addi %2, %1.reg, {CONST, %1.off}
from SUM_RL to GPR
gen addi %2, %1.reg, {LABEL_LO, %1.adr}
from SUM_RR to GPR
gen add %2, %1.reg1, %1.reg2
/* Read byte */
from IND_RC_B+IND_RL_B to GPR
gen lbz %2, %1
from IND_RR_B to GPR
gen lbzx %2, %1.reg1, %1.reg2
/* Write byte */
from GPR to IND_RC_B+IND_RL_B
gen stb %1, %2
from GPR to IND_RR_B
gen stbx %1, %2.reg1, %2.reg2
/* Read halfword (short) */
from IND_RC_H+IND_RL_H to GPR
gen lhz %2, %1
from IND_RR_H to GPR
gen lhzx %2, %1.reg1, %1.reg2
from IND_RC_H_S+IND_RL_H_S to GPR
gen lha %2, %1
from IND_RR_H_S to GPR
gen lhax %2, %1.reg1, %1.reg2
/* Write halfword */
from GPR to IND_RC_H+IND_RL_H
gen sth %1, %2
from GPR to IND_RR_H
gen sthx %1, %2.reg1, %2.reg2
/* Read word */
from IND_RC_W+IND_RL_W to GPR
gen lwz %2, %1
from IND_RR_W to GPR
gen lwzx %2, %1.reg1, %1.reg2
from IND_RC_W+IND_RL_W to FSREG
gen lfs %2, %1
from IND_RR_W to FSREG
gen lfsx %2, %1.reg1, %1.reg2
/* Write word */
from GPR to IND_RC_W+IND_RL_W
gen stw %1, %2
from GPR to IND_RR_W
gen stwx %1, %2.reg1, %2.reg2
from FSREG to IND_RC_W+IND_RL_W
gen stfs %1, %2
from FSREG to IND_RR_W
gen stfsx %1, %2.reg1, %2.reg2
/* Read double */
from IND_RC_D+IND_RL_D to FPR
gen lfd %2, %1
from IND_RR_D to FPR
gen lfdx %2, %1.reg1, %1.reg2
/* Write double */
from FPR to IND_RC_D+IND_RL_D
gen stfd %1, %2
from FPR to IND_RR_D
gen stfdx %1, %2.reg1, %2.reg2
/* Logicals */
from NOT_R to GPR
gen nor %2, %1.reg, %1.reg
from AND_RR to GPR
gen and %2, %1.reg1, %1.reg2
from OR_RR to GPR
gen or %2, %1.reg1, %1.reg2
from OR_RIS to GPR
gen oris %2, %1.reg, {CONST, %1.valhi}
from OR_RC to GPR
gen ori %2, %1.reg, {CONST, %1.val}
from XOR_RR to GPR
gen xor %2, %1.reg1, %1.reg2
from XOR_RIS to GPR
gen xoris %2, %1.reg, {CONST, %1.valhi}
from XOR_RC to GPR
gen xori %2, %1.reg, {CONST, %1.val}
/* Conditions */
/* Compare values, then copy cr0 to GPR. */
from COND_RC to GPR
gen
cmpwi %1.reg, {CONST, %1.val}
mfcr %2
from COND_RR to GPR
gen
cmpw %1.reg1, %1.reg2
mfcr %2
from CONDL_RC to GPR
gen
cmplwi %1.reg, {CONST, %1.val}
mfcr %2
from CONDL_RR to GPR
gen
cmplw %1.reg1, %1.reg2
mfcr %2
from COND_FS to GPR
gen
fcmpo CR0, %1.reg1, %1.reg2
mfcr %2
from COND_FD to GPR
gen
fcmpo CR0, %1.reg1, %1.reg2
mfcr %2
/* Given a copy of cr0 in %1.reg, extract a condition bit
* (lt, gt, eq) and perhaps flip it.
*/
from XEQ to GPR
gen
extrwi %2, %1.reg, {CONST, 1}, {CONST, 2}
from XNE to GPR
gen
extrwi %2, %1.reg, {CONST, 1}, {CONST, 2}
xori %2, %2, {CONST, 1}
from XGT to GPR
gen
extrwi %2, %1.reg, {CONST, 1}, {CONST, 1}
from XGE to GPR
gen
extrwi %2, %1.reg, {CONST, 1}, {CONST, 0}
xori %2, %2, {CONST, 1}
from XLT to GPR
gen
extrwi %2, %1.reg, {CONST, 1}, {CONST, 0}
from XLE to GPR
gen
extrwi %2, %1.reg, {CONST, 1}, {CONST, 1}
xori %2, %2, {CONST, 1}
/* GPRE exists solely to allow us to use regvar() (which can only be used in
an expression) as a register constant. */
from ANY_BHW to GPRE
gen move %1, %2.reg
TESTS
/* Given orX %1, %1, %1, ncgg says, "Instruction destroys %1,
* not allowed here". We use orX_readonly to trick ncgg.
*
* Using "or." and not "mr." because mach/powerpc/top/table
* was optimizing "or." and not "mr.".
*/
to test GPR
gen
orX_readonly %1, %1, %1
STACKINGRULES
from LOCAL to STACK
gen
COMMENT("stack LOCAL")
stwu %1, {IND_RC_W, SP, 0-4}
from REG to STACK
gen
COMMENT("stack REG")
stwu %1, {IND_RC_W, SP, 0-4}
from REG_PAIR to STACK
gen
COMMENT("stack REG_PAIR")
stwu %1.2, {IND_RC_W, SP, 0-4}
stwu %1.1, {IND_RC_W, SP, 0-4}
from ANY_BHW-REG to STACK
gen
COMMENT("stack ANY_BHW-REG")
move %1, RSCRATCH
stwu RSCRATCH, {IND_RC_W, SP, 0-4}
from IND_ALL_D to STACK
gen
COMMENT("stack IND_ALL_D")
move %1, FSCRATCH
stfdu FSCRATCH, {IND_RC_D, SP, 0-8}
from FREG to STACK
gen
COMMENT("stack FPR")
stfdu %1, {IND_RC_D, SP, 0-8}
from FSREG to STACK
gen
COMMENT("stack FSREG")
stfsu %1, {IND_RC_W, SP, 0-4}
COERCIONS
from ANY_BHW
uses REG
gen
COMMENT("coerce ANY_BHW->REG")
move %1, %a
yields %a
from STACK
uses REG
gen
COMMENT("coerce STACK->REG")
lwz %a, {IND_RC_W, SP, 0}
addi SP, SP, {CONST, 4}
yields %a
from STACK
uses REG_PAIR
gen
COMMENT("coerce STACK->REG_PAIR")
lwz %a.1, {IND_RC_W, SP, 0}
lwz %a.2, {IND_RC_W, SP, 4}
addi SP, SP, {CONST, 8}
yields %a
from FSREG
uses FSREG
gen
fmr %a, %1
yields %a
from FREG
uses FREG
gen
fmr %a, %1
yields %a
from STACK
uses FREG
gen
COMMENT("coerce STACK->FREG")
lfd %a, {IND_RC_D, SP, 0}
addi SP, SP, {CONST, 8}
yields %a
from STACK
uses FSREG
gen
COMMENT("coerce STACK->FSREG")
lfs %a, {IND_RC_W, SP, 0}
addi SP, SP, {CONST, 4}
yields %a
from IND_ALL_W
uses FSREG
gen
move %1, %a
yields %a
/*
* from IND_RC_D to REG_PAIR is not possible, because
* %1.off+4 might overflow a signed 16-bit integer in
* move {IND_RC_W, %1.val, %1.off+4}, %a.2
*/
from IND_ALL_D
uses FREG
gen
move %1, %a
yields %a
PATTERNS
/* Intrinsics */
pat loc $1==(0-0x8000) /* Load constant */
yields {CONST_N8000, $1}
pat loc $1>=(0-0x7FFF) && $1<=(0-1)
yields {CONST_N7FFF_N0001, $1}
pat loc $1>=0 && $1<=0x7FFF
yields {CONST_0000_7FFF, $1}
pat loc $1==0x8000
yields {CONST_8000, $1}
pat loc $1>=0x8001 && $1<=0xFFFF
yields {CONST_8001_FFFF, $1}
pat loc lo($1)==0
yields {CONST_HZ, $1}
pat loc
yields {CONST_HL, $1}
pat dup $1==INT32 /* Duplicate word on top of stack */
with REG
yields %1 %1
with FSREG
yields %1 %1
pat dup $1==INT64 /* Duplicate double-word on top of stack */
with REG REG
yields %2 %1 %2 %1
with FREG
yields %1 %1
pat exg $1==INT32 /* Exchange top two words on stack */
with REG REG
yields %1 %2
pat stl lol $1==$2 /* Store then load local */
leaving
dup 4
stl $1
pat sdl ldl $1==$2 /* Store then load double local */
leaving
dup 8
sdl $1
pat lal sti lal loi $1==$3 && $2==$4 /* Store then load local, of a different size */
leaving
dup INT32
lal $1
sti $2
pat ste loe $1==$2 /* Store then load external */
leaving
dup 4
ste $1
/* Type conversions */
pat loc loc ciu /* signed X -> unsigned X */
leaving
loc $1
loc $2
cuu
pat loc loc cuu $1==$2 /* unsigned X -> unsigned X */
/* nop */
pat loc loc cii $1==$2 /* signed X -> signed X */
/* nop */
pat loc loc cui $1==$2 /* unsigned X -> signed X */
/* nop */
pat loc loc cui $1==INT8 && $2==INT32 /* unsigned char -> signed int */
/* nop */
pat loc loc cui $1==INT16 && $2==INT32 /* unsigned short -> signed int */
/* nop */
pat loc loc cii $1==INT8 && $2==INT32 /* signed char -> signed int */
with REG
yields {SEX_B, %1}
pat loc loc cii $1==2 && $2==4 /* signed char -> signed short */
with REG
yields {SEX_H, %1}
/* Local variables */
pat lal smalls($1) /* Load address of local */
yields {SUM_RC, FP, $1}
pat lal /* Load address of local */
uses REG={SUM_RIS, FP, his($1)}
yields {SUM_RC, %a, los($1)}
pat lol inreg($1)>0 /* Load from local */
yields {LOCAL, $1}
pat lol /* Load from local */
leaving
lal $1
loi INT32
pat ldl /* Load double-word from local */
leaving
lal $1
loi INT32*2
pat stl inreg($1)>0 /* Store to local */
with ANY_BHW
kills regvar($1), LOCAL %off==$1
gen
move %1, {GPRE, regvar($1)}
pat stl /* Store to local */
leaving
lal $1
sti INT32
pat sdl /* Store double-word to local */
leaving
lal $1
sti INT32*2
pat lil inreg($1)>0 /* Load from indirected local */
yields {IND_RC_W, regvar($1), 0}
pat lil /* Load from indirected local */
leaving
lol $1
loi INT32
pat sil /* Save to indirected local */
leaving
lol $1
sti INT32
pat zrl /* Zero local */
leaving
loc 0
stl $1
pat inl /* Increment local */
leaving
lol $1
loc 1
adi 4
stl $1
pat del /* Decrement local */
leaving
lol $1
loc 1
sbi 4
stl $1
/* Global variables */
pat lpi /* Load address of external function */
leaving
lae $1
pat lae /* Load address of external */
uses REG={LABEL_HA, $1}
yields {SUM_RL, %a, $1}
pat loe /* Load word external */
leaving
lae $1
loi INT32
pat ste /* Store word external */
leaving
lae $1
sti INT32
pat lde /* Load double-word external */
leaving
lae $1
loi INT64
pat sde /* Store double-word external */
leaving
lae $1
sti INT64
pat zre /* Zero external */
leaving
loc 0
ste $1
pat ine /* Increment external */
leaving
loe $1
inc
ste $1
pat dee /* Decrement external */
leaving
loe $1
dec
ste $1
/* Structures */
pat lof /* Load word offsetted */
leaving
adp $1
loi INT32
pat ldf /* Load double-word offsetted */
leaving
adp $1
loi INT64
pat stf /* Store word offsetted */
leaving
adp $1
sti INT32
pat sdf /* Store double-word offsetted */
leaving
adp $1
sti INT64
/* Loads and stores */
pat loi $1==INT8 /* Load byte indirect */
with REG
yields {IND_RC_B, %1, 0}
with exact SUM_RC
yields {IND_RC_B, %1.reg, %1.off}
with exact SUM_RL
yields {IND_RL_B, %1.reg, %1.adr}
with exact SUM_RR
yields {IND_RR_B, %1.reg1, %1.reg2}
pat loi loc loc cii $1==INT16 && $2==INT16 && $3==INT32
/* Load half-word indirect and sign extend */
with REG
yields {IND_RC_H_S, %1, 0}
with exact SUM_RC
yields {IND_RC_H_S, %1.reg, %1.off}
with exact SUM_RL
yields {IND_RL_H_S, %1.reg, %1.adr}
with exact SUM_RR
yields {IND_RR_H_S, %1.reg1, %1.reg2}
pat loi $1==INT16 /* Load half-word indirect */
with REG
yields {IND_RC_H, %1, 0}
with exact SUM_RC
yields {IND_RC_H, %1.reg, %1.off}
with exact SUM_RL
yields {IND_RL_H, %1.reg, %1.adr}
with exact SUM_RR
yields {IND_RR_H, %1.reg1, %1.reg2}
pat loi $1==INT32 /* Load word indirect */
with REG
yields {IND_RC_W, %1, 0}
with exact SUM_RC
yields {IND_RC_W, %1.reg, %1.off}
with exact SUM_RL
yields {IND_RL_W, %1.reg, %1.adr}
with exact SUM_RR
yields {IND_RR_W, %1.reg1, %1.reg2}
pat loi $1==INT64 /* Load double-word indirect */
with REG
yields {IND_RC_D, %1, 0}
with exact SUM_RC
yields {IND_RC_D, %1.reg, %1.off}
with exact SUM_RL
yields {IND_RL_D, %1.reg, %1.adr}
with exact SUM_RR
yields {IND_RR_D, %1.reg1, %1.reg2}
pat loi /* Load arbitrary size */
leaving
loc $1
los INT32
pat los $1==INT32 /* Load arbitrary size */
with GPR3 GPR4 STACK
kills ALL
gen
bl {LABEL, ".los"}
pat sti $1==INT8 /* Store byte indirect */
with REG REG
kills MEMORY
gen move %2, {IND_RC_B, %1, 0}
with SUM_RC REG
kills MEMORY
gen move %2, {IND_RC_B, %1.reg, %1.off}
with SUM_RL REG
kills MEMORY
gen move %2, {IND_RL_B, %1.reg, %1.adr}
with SUM_RR REG
kills MEMORY
gen move %2, {IND_RR_B, %1.reg1, %1.reg2}
pat sti $1==INT16 /* Store half-word indirect */
with REG REG
kills MEMORY
gen move %2, {IND_RC_H, %1, 0}
with SUM_RC REG
kills MEMORY
gen move %2, {IND_RC_H, %1.reg, %1.off}
with SUM_RL REG
kills MEMORY
gen move %2, {IND_RL_H, %1.reg, %1.adr}
with SUM_RR REG
kills MEMORY
gen move %2, {IND_RR_H, %1.reg1, %1.reg2}
pat sti $1==INT32 /* Store word indirect */
with REG REG+FSREG
kills MEMORY
gen move %2, {IND_RC_W, %1, 0}
with SUM_RC REG+FSREG
kills MEMORY
gen move %2, {IND_RC_W, %1.reg, %1.off}
with SUM_RL REG+FSREG
kills MEMORY
gen move %2, {IND_RL_W, %1.reg, %1.adr}
with SUM_RR REG+FSREG
kills MEMORY
gen move %2, {IND_RR_W, %1.reg1, %1.reg2}
pat sti $1==INT64 /* Store double-word indirect */
with REG FREG
kills MEMORY
gen move %2, {IND_RC_D, %1, 0}
with SUM_RC FREG
kills MEMORY
gen move %2, {IND_RC_D, %1.reg, %1.off}
with SUM_RL FREG
kills MEMORY
gen move %2, {IND_RL_D, %1.reg, %1.adr}
with SUM_RR FREG
kills MEMORY
gen move %2, {IND_RR_D, %1.reg1, %1.reg2}
/*
* This pattern would be too slow:
* with REG REG REG
* ncg can't handle that many registers, and would
* take about 2 seconds on each sti 8. So we use
* REG_PAIR as a speed hack for sti 8.
*/
with REG REG_PAIR
kills MEMORY
gen
move %2.1, {IND_RC_W, %1, 0}
move %2.2, {IND_RC_W, %1, 4}
/*
* Next 2 patterns exist because there is no coercion
* from IND_ALL_D to REG_PAIR.
*/
with REG IND_RC_D
kills MEMORY
uses REG={SUM_RC, %2.reg, %2.off}, REG_PAIR
gen
move {IND_RC_W, %a, 0}, %b.1
move {IND_RC_W, %a, 4}, %b.2
move %b.1, {IND_RC_W, %1, 0}
move %b.2, {IND_RC_W, %1, 4}
with REG IND_RR_D
kills MEMORY
uses REG={SUM_RR, %2.reg1, %2.reg2}, REG_PAIR
gen
move {IND_RC_W, %a, 0}, %b.1
move {IND_RC_W, %a, 4}, %b.2
move %b.1, {IND_RC_W, %1, 0}
move %b.2, {IND_RC_W, %1, 4}
pat sti /* Store arbitrary size */
leaving
loc $1
sts INT32
pat sts $1==INT32 /* Store arbitrary size */
with GPR3 GPR4 STACK
kills ALL
gen
bl {LABEL, ".sts"}
/* Arithmetic wrappers */
pat ads $1==4 /* Add var to pointer */
leaving adi $1
pat sbs $1==4 /* Subtract var from pointer */
leaving sbi $1
pat adp /* Add constant to pointer */
leaving
loc $1
adi 4
pat adu /* Add unsigned */
leaving
adi $1
pat sbu /* Subtract unsigned */
leaving
sbi $1
pat inc /* Add 1 */
leaving
loc 1
adi 4
pat dec /* Subtract 1 */
leaving
loc 1
sbi 4
pat mlu /* Multiply unsigned */
leaving
mli $1
pat slu /* Shift left unsigned */
leaving
sli $1
/* Word arithmetic */
pat adi $1==4 /* Add word (second + top) */
with REG REG
yields {SUM_RR, %1, %2}
with CONST2 REG
yields {SUM_RC, %2, %1.val}
with REG CONST2
yields {SUM_RC, %1, %2.val}
with CONST_HZ REG
uses reusing %2, REG={SUM_RIS, %2, his(%1.val)}
yields %a
with REG CONST_HZ
uses reusing %1, REG={SUM_RIS, %1, his(%2.val)}
yields %a
with CONST_STACK-CONST2-CONST_HZ REG
uses reusing %2, REG={SUM_RIS, %2, his(%1.val)}
yields {SUM_RC, %a, los(%1.val)}
with REG CONST_STACK-CONST2-CONST_HZ
uses reusing %1, REG={SUM_RIS, %1, his(%2.val)}
yields {SUM_RC, %a, los(%2.val)}
pat sbi $1==4 /* Subtract word (second - top) */
with REG REG
uses reusing %2, REG
gen
subf %a, %1, %2
yields %a
with CONST2_WHEN_NEG REG
yields {SUM_RC, %2, 0-%1.val}
with CONST_HZ REG
uses reusing %2, REG={SUM_RIS, %2, his(0-%1.val)}
yields %a
with CONST_STACK-CONST2_WHEN_NEG-CONST_HZ REG
uses reusing %2, REG={SUM_RIS, %2, his(0-%1.val)}
yields {SUM_RC, %a, los(0-%1.val)}
pat ngi $1==4 /* Negate word */
with REG
uses reusing %1, REG
gen
neg %a, %1
yields %a
pat mli $1==4 /* Multiply word (second * top) */
with REG REG
uses reusing %2, REG
gen
mullw %a, %2, %1
yields %a
pat dvi $1==4 /* Divide word (second / top) */
with REG REG
uses reusing %2, REG
gen
divw %a, %2, %1
yields %a
pat dvu $1==4 /* Divide unsigned word (second / top) */
with REG REG
uses reusing %2, REG
gen
divwu %a, %2, %1
yields %a
pat rmi $1==4 /* Remainder word (second % top) */
with REG REG
uses REG
gen
divw %a, %2, %1
mullw %a, %a, %1
subf %a, %a, %2
yields %a
pat rmu $1==4 /* Remainder unsigned word (second % top) */
with REG REG
uses REG
gen
divwu %a, %2, %1
mullw %a, %a, %1
subf %a, %a, %2
yields %a
pat and $1==4 /* AND word */
with REG NOT_R
uses reusing %1, REG
gen
andc %a, %1, %2.reg
yields %a
with NOT_R REG
uses reusing %1, REG
gen
andc %a, %2, %1.reg
yields %a
with REG REG
yields {AND_RR, %1, %2}
with REG UCONST2
uses reusing %1, REG
gen
andiX %a, %1, {CONST, %2.val}
yields %a
with UCONST2 REG
uses reusing %2, REG
gen
andiX %a, %2, {CONST, %1.val}
yields %a
with REG CONST_HZ
uses reusing %1, REG
gen
andisX %a, %1, {CONST, hi(%2.val)}
yields %a
with CONST_HZ REG
uses reusing %2, REG
gen
andisX %a, %2, {CONST, hi(%1.val)}
yields %a
pat and defined($1) /* AND set */
leaving
loc $1
cal ".and"
pat and !defined($1)
leaving
cal ".and"
pat ior $1==4 /* OR word */
with REG NOT_R
uses reusing %1, REG
gen
orc %a, %1, %2.reg
yields %a
with NOT_R REG
uses reusing %2, REG
gen
orc %a, %2, %1.reg
yields %a
with REG REG
yields {OR_RR, %1, %2}
with REG UCONST2
yields {OR_RC, %1, %2.val}
with UCONST2 REG
yields {OR_RC, %2, %1.val}
with REG CONST_HZ
uses reusing %1, REG={OR_RIS, %1, hi(%2.val)}
yields %a
with CONST_HZ REG
uses reusing %2, REG={OR_RIS, %2, hi(%1.val)}
yields %a
with REG CONST_STACK-UCONST2-CONST_HZ
uses reusing %1, REG={OR_RIS, %1, hi(%2.val)}
yields {OR_RC, %1, lo(%2.val)}
with CONST_STACK-UCONST2-CONST_HZ REG
uses reusing %2, REG={OR_RIS, %2, hi(%1.val)}
yields {OR_RC, %2, lo(%1.val)}
pat ior defined($1) /* OR set */
leaving
loc $1
cal ".ior"
/* OR set (variable), used in lang/m2/libm2/LtoUset.e */
pat ior !defined($1)
leaving
cal ".ior"
pat xor $1==4 /* XOR word */
with REG REG
yields {XOR_RR, %1, %2}
with REG UCONST2
yields {XOR_RC, %1, %2.val}
with UCONST2 REG
yields {XOR_RC, %2, %1.val}
with REG CONST_HZ
uses reusing %1, REG={XOR_RIS, %1, hi(%2.val)}
yields %a
with CONST_HZ REG
uses reusing %2, REG={XOR_RIS, %2, hi(%1.val)}
yields %a
with REG CONST_STACK-UCONST2-CONST_HZ
uses reusing %1, REG={XOR_RIS, %1, hi(%2.val)}
yields {XOR_RC, %1, lo(%2.val)}
with CONST_STACK-UCONST2-CONST_HZ REG
uses reusing %2, REG={XOR_RIS, %2, hi(%1.val)}
yields {XOR_RC, %2, lo(%1.val)}
pat xor defined($1) /* XOR set */
leaving
loc $1
cal ".xor"
pat xor !defined($1)
leaving
cal ".xor"
pat com $1==INT32 /* NOT word */
with AND_RR
uses REG
gen
nand %a, %1.reg1, %1.reg2
yields %a
with OR_RR
uses REG
gen
nor %a, %1.reg1, %1.reg2
yields %a
with XOR_RR
uses REG
gen
eqv %a, %1.reg1, %1.reg2
yields %a
with REG
yields {NOT_R, %1}
pat com defined($1) /* NOT set */
leaving
loc $1
cal ".com"
pat com !defined($1)
leaving
cal ".com"
pat zer $1==4 /* Push zero */
leaving
loc 0
pat zer defined($1) /* Create empty set */
leaving
loc $1
cal ".zer"
pat sli $1==4 /* Shift left (second << top) */
with CONST_STACK REG
uses reusing %2, REG
gen
rlwinm %a, %2, {CONST, (%1.val & 0x1F)}, {CONST, 0}, {CONST, 31-(%1.val & 0x1F)}
yields %a
with REG REG
uses reusing %2, REG
gen
slw %a, %2, %1
yields %a
pat sri $1==4 /* Shift right signed (second >> top) */
with CONST_STACK REG
uses reusing %2, REG
gen
srawi %a, %2, {CONST, %1.val & 0x1F}
yields %a
with REG REG
uses reusing %2, REG
gen
sraw %a, %2, %1
yields %a
pat sru $1==4 /* Shift right unsigned (second >> top) */
with CONST_STACK REG
uses reusing %2, REG
gen
rlwinm %a, %2, {CONST, 32-(%1.val & 0x1F)}, {CONST, (%1.val & 0x1F)}, {CONST, 31}
yields %a
with REG REG
uses reusing %2, REG
gen
srw %a, %2, %1
yields %a
/* Arrays */
pat aar $1==INT32 /* Index array */
with GPR3 GPR4 GPR5
kills ALL
gen
bl {LABEL, ".aar4"}
yields R3
pat lae lar $2==INT32 && nicesize(rom($1, 3)) /* Load array */
leaving
lae $1
aar INT32
loi rom($1, 3)
pat lar $1==INT32 /* Load array */
with GPR3 GPR4 GPR5 STACK
kills ALL
gen
bl {LABEL, ".lar4"}
pat lae sar $2==INT32 && nicesize(rom($1, 3)) /* Store array */
leaving
lae $1
aar INT32
sti rom($1, 3)
pat sar $1==INT32 /* Store array */
with GPR3 GPR4 GPR5 STACK
kills ALL
gen
bl {LABEL, ".sar4"}
/* Sets */
pat set defined($1) /* Create singleton set */
leaving
loc $1
cal ".set"
/* Create set (variable), used in lang/m2/libm2/LtoUset.e */
pat set !defined($1)
leaving
cal ".set"
pat inn defined($1) /* Test for set bit */
leaving
loc $1
cal ".inn"
pat inn !defined($1)
leaving
cal ".inn"
/* Boolean resolutions */
pat teq /* top = (top == 0) */
with REG
uses reusing %1, REG
gen
test %1
mfcr %a
move {XEQ, %a}, %a
yields %a
pat tne /* top = (top != 0) */
with REG
uses reusing %1, REG
gen
test %1
mfcr %a
move {XNE, %a}, %a
yields %a
pat tlt /* top = (top < 0) */
with REG
uses reusing %1, REG
gen
test %1
mfcr %a
move {XLT, %a}, %a
yields %a
pat tle /* top = (top <= 0) */
with REG
uses reusing %1, REG
gen
test %1
mfcr %a
move {XLE, %a}, %a
yields %a
pat tgt /* top = (top > 0) */
with REG
uses reusing %1, REG
gen
test %1
mfcr %a
move {XGT, %a}, %a
yields %a
pat tge /* top = (top >= 0) */
with REG
uses reusing %1, REG
gen
test %1
mfcr %a
move {XGE, %a}, %a
yields %a
pat cmi teq $1==4 /* Signed second == top */
with REG CONST2
uses reusing %1, REG={COND_RC, %1, %2.val}
gen move {XEQ, %a}, %a
yields %a
with CONST2 REG
uses reusing %1, REG={COND_RC, %2, %1.val}
gen move {XEQ, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={COND_RR, %2, %1}
gen move {XEQ, %a}, %a
yields %a
pat cmi tne $1==4 /* Signed second != top */
with REG CONST2
uses reusing %1, REG={COND_RC, %1, %2.val}
gen move {XNE, %a}, %a
yields %a
with CONST2 REG
uses reusing %1, REG={COND_RC, %2, %1.val}
gen move {XNE, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={COND_RR, %2, %1}
gen move {XNE, %a}, %a
yields %a
pat cmi tgt $1==4 /* Signed second > top */
with REG CONST2
uses reusing %1, REG={COND_RC, %1, %2.val}
gen move {XLT, %a}, %a
yields %a
with CONST2 REG
uses reusing %1, REG={COND_RC, %2, %1.val}
gen move {XGT, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={COND_RR, %2, %1}
gen move {XGT, %a}, %a
yields %a
pat cmi tge $1==4 /* Signed second >= top */
with REG CONST2
uses reusing %1, REG={COND_RC, %1, %2.val}
gen move {XLE, %a}, %a
yields %a
with CONST2 REG
uses reusing %1, REG={COND_RC, %2, %1.val}
gen move {XGE, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={COND_RR, %2, %1}
gen move {XGE, %a}, %a
yields %a
pat cmi tlt $1==4 /* Signed second < top */
with REG CONST2
uses reusing %1, REG={COND_RC, %1, %2.val}
gen move {XGT, %a}, %a
yields %a
with CONST2 REG
uses reusing %1, REG={COND_RC, %2, %1.val}
gen move {XLT, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={COND_RR, %2, %1}
gen move {XLT, %a}, %a
yields %a
pat cmi tle $1==4 /* Signed second <= top */
with REG CONST2
uses reusing %1, REG={COND_RC, %1, %2.val}
gen move {XGE, %a}, %a
yields %a
with CONST2 REG
uses reusing %1, REG={COND_RC, %2, %1.val}
gen move {XLE, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={COND_RR, %2, %1}
gen move {XLE, %a}, %a
yields %a
pat cmu teq $1==4 /* Unsigned second == top */
with REG UCONST2
uses reusing %1, REG={CONDL_RC, %1, %2.val}
gen move {XEQ, %a}, %a
yields %a
with UCONST2 REG
uses reusing %1, REG={CONDL_RC, %2, %1.val}
gen move {XEQ, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={CONDL_RR, %2, %1}
gen move {XEQ, %a}, %a
yields %a
pat cmu tne $1==4 /* Unsigned second != top */
with REG UCONST2
uses reusing %1, REG={CONDL_RC, %1, %2.val}
gen move {XNE, %a}, %a
yields %a
with UCONST2 REG
uses reusing %1, REG={CONDL_RC, %2, %1.val}
gen move {XNE, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={CONDL_RR, %2, %1}
gen move {XNE, %a}, %a
yields %a
pat cmu tgt $1==4 /* Unsigned second > top */
with REG UCONST2
uses reusing %1, REG={CONDL_RC, %1, %2.val}
gen move {XLT, %a}, %a
yields %a
with UCONST2 REG
uses reusing %1, REG={CONDL_RC, %2, %1.val}
gen move {XGT, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={CONDL_RR, %2, %1}
gen move {XGT, %a}, %a
yields %a
pat cmu tge $1==4 /* Unsigned second >= top */
with REG UCONST2
uses reusing %1, REG={CONDL_RC, %1, %2.val}
gen move {XLE, %a}, %a
yields %a
with UCONST2 REG
uses reusing %1, REG={CONDL_RC, %2, %1.val}
gen move {XGE, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={CONDL_RR, %2, %1}
gen move {XGE, %a}, %a
yields %a
pat cmu tlt $1==4 /* Unsigned second < top */
with REG UCONST2
uses reusing %1, REG={CONDL_RC, %1, %2.val}
gen move {XGT, %a}, %a
yields %a
with UCONST2 REG
uses reusing %1, REG={CONDL_RC, %2, %1.val}
gen move {XLT, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={CONDL_RR, %2, %1}
gen move {XLT, %a}, %a
yields %a
pat cmu tle $1==4 /* Unsigned second <= top */
with REG UCONST2
uses reusing %1, REG={CONDL_RC, %1, %2.val}
gen move {XGE, %a}, %a
yields %a
with UCONST2 REG
uses reusing %1, REG={CONDL_RC, %2, %1.val}
gen move {XLE, %a}, %a
yields %a
with REG REG
uses reusing %1, REG={CONDL_RR, %2, %1}
gen move {XLE, %a}, %a
yields %a
/* Simple branches */
proc zxx example zeq
with REG STACK
gen
test %1
bxx* {LABEL, $1}
/* Pop signed int, branch if... */
pat zeq call zxx("beq") /* top == 0 */
pat zne call zxx("bne") /* top != 0 */
pat zgt call zxx("bgt") /* top > 0 */
pat zge call zxx("bge") /* top >= 0 */
pat zlt call zxx("blt") /* top < 0 */
pat zle call zxx("ble") /* top >= 0 */
/* The peephole optimizer rewrites
* cmi 4 zeq
* as beq, and does same for bne, bgt, and so on.
*/
proc bxx example beq
with REG CONST2 STACK
gen
cmpwi %1, {CONST, %2.val}
bxx[2] {LABEL, $1}
with CONST2 REG STACK
gen
cmpwi %2, {CONST, %1.val}
bxx[1] {LABEL, $1}
with REG REG STACK
gen
cmpw %2, %1
bxx[1] {LABEL, $1}
/* Pop two signed ints, branch if... */
pat beq call bxx("beq", "beq") /* second == top */
pat bne call bxx("bne", "bne") /* second != top */
pat bgt call bxx("bgt", "blt") /* second > top */
pat bge call bxx("bge", "ble") /* second >= top */
pat blt call bxx("blt", "bgt") /* second < top */
pat ble call bxx("ble", "bge") /* second >= top */
proc cmu4zxx example cmu zeq
with REG CONST2 STACK
gen
cmplwi %1, {CONST, %2.val}
bxx[2] {LABEL, $2}
with CONST2 REG STACK
gen
cmplwi %2, {CONST, %1.val}
bxx[1] {LABEL, $2}
with REG REG STACK
gen
cmplw %2, %1
bxx[1] {LABEL, $2}
/* Pop two unsigned ints, branch if... */
pat cmu zeq $1==4 call cmu4zxx("beq", "beq")
pat cmu zne $1==4 call cmu4zxx("bne", "bne")
pat cmu zgt $1==4 call cmu4zxx("bgt", "blt")
pat cmu zge $1==4 call cmu4zxx("bge", "ble")
pat cmu zlt $1==4 call cmu4zxx("blt", "bgt")
pat cmu zle $1==4 call cmu4zxx("ble", "bge")
/* Comparisons */
/* Each comparison extracts the lt and gt bits from cr0.
* extlwi %a, %a, 2, 0
* puts lt in the sign bit, so lt yields a negative result,
* gt yields positive.
* rlwinm %a, %a, 1, 31, 0
* puts gt in the sign bit, to reverse the comparison.
*/
pat cmi $1==INT32 /* Signed tristate compare */
with REG CONST2
uses reusing %1, REG={COND_RC, %1, %2.val}
gen rlwinm %a, %a, {CONST, 1}, {CONST, 31}, {CONST, 0}
yields %a
with CONST2 REG
uses reusing %2, REG={COND_RC, %2, %1.val}
gen extlwi %a, %a, {CONST, 2}, {CONST, 0}
yields %a
with REG REG
uses reusing %1, REG={COND_RR, %2, %1}
gen extlwi %a, %a, {CONST, 2}, {CONST, 0}
yields %a
pat cmu $1==INT32 /* Unsigned tristate compare */
with REG UCONST2
uses reusing %1, REG={CONDL_RC, %1, %2.val}
gen rlwinm %a, %a, {CONST, 1}, {CONST, 31}, {CONST, 0}
yields %a
with UCONST2 REG
uses reusing %2, REG={CONDL_RC, %2, %1.val}
gen extlwi %a, %a, {CONST, 2}, {CONST, 0}
yields %a
with REG REG
uses reusing %1, REG={CONDL_RR, %2, %1}
gen extlwi %a, %a, {CONST, 2}, {CONST, 0}
yields %a
pat cmp /* Compare pointers */
leaving
cmu INT32
pat cms $1==INT32 /* Compare blocks (word sized) */
leaving
cmi INT32
pat cms defined($1)
with STACK
kills ALL
gen
move {CONST, $1}, R3
bl {LABEL, ".cms"}
yields R3
/* Other branching and labelling */
pat lab topeltsize($1)==4 && !fallthrough($1)
kills ALL
gen
labeldef $1
yields R3
pat lab topeltsize($1)==4 && fallthrough($1)
with GPR3 STACK
kills ALL
gen
labeldef $1
yields %1
pat lab topeltsize($1)!=4
with STACK
kills ALL
gen
labeldef $1
pat bra topeltsize($1)==4 /* Unconditional jump with TOS GPRister */
with GPR3 STACK
gen
b {LABEL, $1}
pat bra topeltsize($1)!=4 /* Unconditional jump without TOS GPRister */
with STACK
gen
b {LABEL, $1}
/* Miscellaneous */
pat cal /* Call procedure */
with STACK
kills ALL
gen
bl {LABEL, $1}
pat cai /* Call procedure indirect */
with REG STACK
kills ALL
gen
mtspr CTR, %1
bctrl.
pat lfr $1==INT32 /* Load function result, word */
yields R3
pat lfr $1==INT64 /* Load function result, double-word */
yields R4 R3
pat ret $1==0 /* Return from procedure */
gen
return
b {LABEL, ".ret"}
pat ret $1==INT32 /* Return from procedure, word */
with GPR3
gen
return
b {LABEL, ".ret"}
pat ret $1==INT64 /* Return from procedure, double-word */
with GPR3 GPR4
gen
return
b {LABEL, ".ret"}
pat blm /* Block move constant length */
leaving
loc $1
bls
pat bls /* Block move variable length */
with REG REG REG
uses reusing %1, REG, REG={CONST_0000_7FFF, 0}
gen
/* Wrong if size is zero */
srwi %1, %1, {CONST, 2}
mtspr CTR, %1
1:
lwzx %a, %3, %b
stwx %a, %2, %b
addi %b, %b, {CONST, 4}
bdnz {LABEL, "1b"}
pat csa /* Array-lookup switch */
with STACK
gen
b {LABEL, ".csa"}
pat csb /* Table-lookup switch */
with STACK
gen
b {LABEL, ".csb"}
/* EM specials */
pat fil /* Set current filename */
leaving
lae $1
ste "hol0+4"
pat lin /* Set current line number */
leaving
loc $1
ste "hol0"
pat lni /* Increment line number */
leaving
ine "hol0"
pat lim /* Load EM trap ignore mask */
leaving
lde ".ignmask"
pat sim /* Store EM trap ignore mask */
leaving
ste ".ignmask"
pat trp /* Raise EM trap */
with GPR3
gen
bl {LABEL, ".trap"}
pat sig /* Set trap handler */
leaving
ste ".trppc"
pat rtt /* Return from trap */
leaving
ret 0
pat lxl $1==0 /* Load FP */
leaving
lor 0
pat lxl $1==1 /* Load caller's FP */
leaving
lxl 0
dch
pat dch /* FP -> caller FP */
with REG
uses reusing %1, REG
gen
lwz %a, {IND_RC_W, %1, FP_OFFSET}
yields %a
pat lpb /* Convert FP to argument address */
leaving
adp EM_BSIZE
pat lxa /* Load caller's SP */
leaving
lxl $1
lpb
pat gto /* longjmp */
uses REG
gen
move {LABEL, $1}, %a
move {IND_RC_W, %a, 8}, FP
move {IND_RC_W, %a, 4}, SP
move {IND_RC_W, %a, 0}, %a
mtspr CTR, %a
bctr.
pat lor $1==0 /* Load FP */
uses REG
gen
move FP, %a
yields %a
pat lor $1==1 /* Load SP */
uses REG
gen
move SP, %a
yields %a
pat str $1==0 /* Store FP */
with REG
gen
move %1, FP
pat str $1==1 /* Store SP */
with REG
gen
move %1, SP
pat loc ass $1==4 && $2==4 /* Drop 4 bytes from stack */
with exact REG
/* nop */
with STACK
gen
addi SP, SP, {CONST, 4}
pat ass $1==4 /* Adjust stack by variable amount */
with CONST2 STACK
gen
move {SUM_RC, SP, %1.val}, SP
with CONST_HZ STACK
gen
move {SUM_RC, SP, his(%1.val)}, SP
with CONST_STACK-CONST2-CONST_HZ STACK
gen
move {SUM_RC, SP, his(%1.val)}, SP
move {SUM_RC, SP, los(%1.val)}, SP
with REG STACK
gen
move {SUM_RR, SP, %1}, SP
pat asp /* Adjust stack by constant amount */
leaving
loc $1
ass 4
pat lae rck $2==4 /* Range check */
with REG
gen
cmpwi %1, {CONST, rom($1, 1)}
blt {LABEL, ".trap_erange"}
cmpwi %1, {CONST, rom($1, 2)}
bgt {LABEL, ".trap_erange"}
yields %1
/* Floating point support */
/* All very cheap and nasty --- this needs to be properly integrated into
* the code generator. ncg doesn't like having separate FPU registers. */
/* Single-precision */
pat zrf $1==INT32 /* Push zero */
leaving
loe ".fs_00000000"
pat adf $1==INT32 /* Add single */
with FSREG FSREG
uses reusing %1, FSREG
gen
fadds %a, %2, %1
yields %a
pat sbf $1==INT32 /* Subtract single */
with FSREG FSREG
uses reusing %1, FSREG
gen
fsubs %a, %2, %1
yields %a
pat mlf $1==INT32 /* Multiply single */
with FSREG FSREG
uses reusing %1, FSREG
gen
fmuls %a, %2, %1
yields %a
pat dvf $1==INT32 /* Divide single */
with FSREG FSREG
uses reusing %1, FSREG
gen
fdivs %a, %2, %1
yields %a
pat ngf $1==INT32 /* Negate single */
with FSREG
uses reusing %1, FSREG
gen
fneg %a, %1
yields %a
pat cmf $1==INT32 /* Compare single */
with FSREG FSREG
uses REG={COND_FS, %2, %1}
gen extlwi %a, %a, {CONST, 2}, {CONST, 0}
yields %a
pat cmf teq $1==4 /* Single second == top */
with FSREG FSREG
uses REG={COND_FS, %2, %1}
gen move {XEQ, %a}, %a
yields %a
pat cmf tne $1==4 /* Single second == top */
with FSREG FSREG
uses REG={COND_FS, %2, %1}
gen move {XNE, %a}, %a
yields %a
pat cmf tgt $1==4 /* Single second > top */
with FSREG FSREG
uses REG={COND_FS, %2, %1}
gen move {XGT, %a}, %a
yields %a
pat cmf tge $1==4 /* Single second >= top */
with FSREG FSREG
uses REG={COND_FS, %2, %1}
gen move {XGE, %a}, %a
yields %a
pat cmf tlt $1==4 /* Single second < top */
with FSREG FSREG
uses REG={COND_FS, %2, %1}
gen move {XLT, %a}, %a
yields %a
pat cmf tle $1==4 /* Single second <= top */
with FSREG FSREG
uses REG={COND_FS, %2, %1}
gen move {XLE, %a}, %a
yields %a
proc cmf4zxx example cmf zeq
with FREG FREG STACK
uses REG
gen
fcmpo CR0, %2, %1
bxx* {LABEL, $2}
/* Pop 2 singles, branch if... */
pat cmf zeq $1==4 call cmf4zxx("beq")
pat cmf zne $1==4 call cmf4zxx("bne")
pat cmf zgt $1==4 call cmf4zxx("bgt")
pat cmf zge $1==4 call cmf4zxx("bge")
pat cmf zlt $1==4 call cmf4zxx("blt")
pat cmf zle $1==4 call cmf4zxx("ble")
pat loc loc cff $1==INT32 && $2==INT64 /* Convert single to double */
with FSREG
yields %1.1
/* Convert single to signed int */
pat loc loc cfi $1==4 && $2==4
leaving
loc 4
loc 8
cff
loc 8
loc 4
cfi
/* Convert single to unsigned int */
pat loc loc cfu $1==4 && $2==4
leaving
loc 4
loc 8
cff
loc 8
loc 4
cfu
/* Convert signed int to single */
pat loc loc cif $1==4 && $2==4
leaving
loc 4
loc 8
cif
loc 8
loc 4
cff
/* Convert unsigned int to single */
pat loc loc cuf $1==4 && $2==4
leaving
loc 4
loc 8
cuf
loc 8
loc 4
cff
/* Double-precision */
pat zrf $1==INT64 /* Push zero */
leaving
lde ".fd_00000000"
pat adf $1==INT64 /* Add double */
with FREG FREG
uses FREG
gen
fadd %a, %2, %1
yields %a
pat sbf $1==INT64 /* Subtract double */
with FREG FREG
uses FREG
gen
fsub %a, %2, %1
yields %a
pat mlf $1==INT64 /* Multiply double */
with FREG FREG
uses reusing %1, FREG
gen
fmul %a, %2, %1
yields %a
pat dvf $1==INT64 /* Divide double */
with FREG FREG
uses reusing %1, FREG
gen
fdiv %a, %2, %1
yields %a
pat ngf $1==INT64 /* Negate double */
with FREG
uses reusing %1, FREG
gen
fneg %a, %1
yields %a
pat cmf $1==INT64 /* Compare double */
with FREG FREG
uses REG={COND_FD, %2, %1}
gen extlwi %a, %a, {CONST, 2}, {CONST, 0}
yields %a
pat cmf teq $1==8 /* Double second == top */
with FREG FREG
uses REG={COND_FD, %2, %1}
gen move {XEQ, %a}, %a
yields %a
pat cmf tne $1==8 /* Single second == top */
with FREG FREG
uses REG={COND_FD, %2, %1}
gen move {XNE, %a}, %a
yields %a
pat cmf tgt $1==8 /* Double second > top */
with FREG FREG
uses REG={COND_FD, %2, %1}
gen move {XGT, %a}, %a
yields %a
pat cmf tge $1==8 /* Double second >= top */
with FREG FREG
uses REG={COND_FD, %2, %1}
gen move {XGE, %a}, %a
yields %a
pat cmf tlt $1==8 /* Double second < top */
with FREG FREG
uses REG={COND_FD, %2, %1}
gen move {XLT, %a}, %a
yields %a
pat cmf tle $1==8 /* Double second <= top */
with FREG FREG
uses REG={COND_FD, %2, %1}
gen move {XLE, %a}, %a
yields %a
proc cmf8zxx example cmf zeq
with FREG FREG STACK
uses REG
gen
fcmpo CR0, %2, %1
bxx* {LABEL, $2}
/* Pop 2 doubles, branch if... */
pat cmf zeq $1==8 call cmf8zxx("beq")
pat cmf zne $1==8 call cmf8zxx("bne")
pat cmf zgt $1==8 call cmf8zxx("bgt")
pat cmf zge $1==8 call cmf8zxx("bge")
pat cmf zlt $1==8 call cmf8zxx("blt")
pat cmf zle $1==8 call cmf8zxx("ble")
pat loc loc cff $1==INT64 && $2==INT32 /* Convert double to single */
with FREG
uses reusing %1, FSREG
gen
frsp %a, %1
yields %a
/* Convert double to signed int */
pat loc loc cfi $1==8 && $2==4
with FREG STACK
uses reusing %1, FREG
gen
fctiwz %a, %1
stfdu %a, {IND_RC_D, SP, 0-8}
addi SP, SP, {CONST, 4}
/* Convert double to unsigned int */
pat loc loc cfu $1==8 && $2==4
with STACK
gen
bl {LABEL, ".cfu8"}
/*
* To convert integer to IEEE double, we pack the integer in
* the low bits of the magic double
* 1 << 52 == 0x 4330 0000 0000 0000
*
* For signed integer i, we flip its sign bit, then compute
* ((1 << 52) + i) - ((1 << 52) + (1 << 31))
*/
pat loc loc cif $1==4 && $2==8
with REG
uses reusing %1, REG={XOR_RIS, %1, 0x8000},
REG={CONST_HZ, 0x43300000},
REG={CONST_HZ, 0x80000000},
FREG, FREG
gen
stwu %b, {IND_RC_W, SP, 0-8}
stw %a, {IND_RC_W, SP, 4}
lfd %d, {IND_RC_D, SP, 0}
stw %c, {IND_RC_W, SP, 4}
lfd %e, {IND_RC_D, SP, 0}
fsub %d, %d, %e
addi SP, SP, {CONST, 8}
yields %d
/*
* To convert unsigned integer u to IEEE double, we compute
* ((1 << 52) + u) - (1 << 52)
*/
pat loc loc cuf $1==4 && $2==8
with REG
uses REG={CONST_HZ, 0x43300000},
REG={CONST_0000_7FFF, 0},
FREG, FREG
gen
stwu %a, {IND_RC_W, SP, 0-8}
stw %1, {IND_RC_W, SP, 4}
lfd %c, {IND_RC_D, SP, 0}
stw %b, {IND_RC_W, SP, 4}
lfd %d, {IND_RC_D, SP, 0}
fsub %c, %c, %d
addi SP, SP, {CONST, 8}
yields %c
pat fef $1==INT64 /* Split exponent, fraction */
with GPR3 GPR4
kills ALL
gen
bl {LABEL, ".fef8"}
yields R4 R3 R5
pat fif $1==INT64 /* Multiply then split integer, fraction */
with FPR1 FPR2
kills ALL
gen
bl {LABEL, ".fif8"}
yields F1 F2
Reference in a new issue View git blame Copy permalink