doc.go raw

   1  // Copyright 2018 The Go Authors. All rights reserved.
   2  // Use of this source code is governed by a BSD-style
   3  // license that can be found in the LICENSE file.
   4  
   5  /*
   6  Package arm64 implements an ARM64 assembler. Go assembly syntax is different from GNU ARM64
   7  syntax, but we can still follow the general rules to map between them.
   8  
   9  Instructions mnemonics mapping rules
  10  
  11  1. Most instructions use width suffixes of instruction names to indicate operand width rather than
  12  using different register names.
  13  
  14    Examples:
  15      ADC R24, R14, R12          <=>     adc x12, x24
  16      ADDW R26->24, R21, R15     <=>     add w15, w21, w26, asr #24
  17      FCMPS F2, F3               <=>     fcmp s3, s2
  18      FCMPD F2, F3               <=>     fcmp d3, d2
  19      FCVTDH F2, F3              <=>     fcvt h3, d2
  20  
  21  2. Go uses .P and .W suffixes to indicate post-increment and pre-increment.
  22  
  23    Examples:
  24      MOVD.P -8(R10), R8         <=>      ldr x8, [x10],#-8
  25      MOVB.W 16(R16), R10        <=>      ldrsb x10, [x16,#16]!
  26      MOVBU.W 16(R16), R10       <=>      ldrb x10, [x16,#16]!
  27  
  28  3. Go uses a series of MOV instructions as load and store.
  29  
  30  64-bit variant ldr, str, stur => MOVD;
  31  32-bit variant str, stur, ldrsw => MOVW;
  32  32-bit variant ldr => MOVWU;
  33  ldrb => MOVBU; ldrh => MOVHU;
  34  ldrsb, sturb, strb => MOVB;
  35  ldrsh, sturh, strh =>  MOVH.
  36  
  37  4. Go moves conditions into opcode suffix, like BLT.
  38  
  39  5. Go adds a V prefix for most floating-point and SIMD instructions, except cryptographic extension
  40  instructions and floating-point(scalar) instructions.
  41  
  42    Examples:
  43      VADD V5.H8, V18.H8, V9.H8         <=>      add v9.8h, v18.8h, v5.8h
  44      VLD1.P (R6)(R11), [V31.D1]        <=>      ld1 {v31.1d}, [x6], x11
  45      VFMLA V29.S2, V20.S2, V14.S2      <=>      fmla v14.2s, v20.2s, v29.2s
  46      AESD V22.B16, V19.B16             <=>      aesd v19.16b, v22.16b
  47      SCVTFWS R3, F16                   <=>      scvtf s17, w6
  48  
  49  6. Align directive
  50  
  51  Go asm supports the PCALIGN directive, which indicates that the next instruction should be aligned
  52  to a specified boundary by padding with NOOP instruction. The alignment value supported on arm64
  53  must be a power of 2 and in the range of [8, 2048].
  54  
  55    Examples:
  56      PCALIGN $16
  57      MOVD $2, R0          // This instruction is aligned with 16 bytes.
  58      PCALIGN $1024
  59      MOVD $3, R1          // This instruction is aligned with 1024 bytes.
  60  
  61  PCALIGN also changes the function alignment. If a function has one or more PCALIGN directives,
  62  its address will be aligned to the same or coarser boundary, which is the maximum of all the
  63  alignment values.
  64  
  65  In the following example, the function Add is aligned with 128 bytes.
  66    Examples:
  67      TEXT ·Add(SB),$40-16
  68      MOVD $2, R0
  69      PCALIGN $32
  70      MOVD $4, R1
  71      PCALIGN $128
  72      MOVD $8, R2
  73      RET
  74  
  75  On arm64, functions in Go are aligned to 16 bytes by default, we can also use PCALGIN to set the
  76  function alignment. The functions that need to be aligned are preferably using NOFRAME and NOSPLIT
  77  to avoid the impact of the prologues inserted by the assembler, so that the function address will
  78  have the same alignment as the first hand-written instruction.
  79  
  80  In the following example, PCALIGN at the entry of the function Add will align its address to 2048 bytes.
  81  
  82    Examples:
  83      TEXT ·Add(SB),NOSPLIT|NOFRAME,$0
  84        PCALIGN $2048
  85        MOVD $1, R0
  86        MOVD $1, R1
  87        RET
  88  
  89  Special Cases.
  90  
  91  (1) umov is written as VMOV.
  92  
  93  (2) br is renamed JMP, blr is renamed CALL.
  94  
  95  (3) No need to add "W" suffix: LDARB, LDARH, LDAXRB, LDAXRH, LDTRH, LDXRB, LDXRH.
  96  
  97  (4) In Go assembly syntax, NOP is a zero-width pseudo-instruction serves generic purpose, nothing
  98  related to real ARM64 instruction. NOOP serves for the hardware nop instruction. NOOP is an alias of
  99  HINT $0.
 100  
 101    Examples:
 102      VMOV V13.B[1], R20      <=>      mov x20, v13.b[1]
 103      VMOV V13.H[1], R20      <=>      mov w20, v13.h[1]
 104      JMP (R3)                <=>      br x3
 105      CALL (R17)              <=>      blr x17
 106      LDAXRB (R19), R16       <=>      ldaxrb w16, [x19]
 107      NOOP                    <=>      nop
 108  
 109  
 110  Register mapping rules
 111  
 112  1. All basic register names are written as Rn.
 113  
 114  2. Go uses ZR as the zero register and RSP as the stack pointer.
 115  
 116  3. Bn, Hn, Dn, Sn and Qn instructions are written as Fn in floating-point instructions and as Vn
 117  in SIMD instructions.
 118  
 119  
 120  Argument mapping rules
 121  
 122  1. The operands appear in left-to-right assignment order.
 123  
 124  Go reverses the arguments of most instructions.
 125  
 126      Examples:
 127        ADD R11.SXTB<<1, RSP, R25      <=>      add x25, sp, w11, sxtb #1
 128        VADD V16, V19, V14             <=>      add d14, d19, d16
 129  
 130  Special Cases.
 131  
 132  (1) Argument order is the same as in the GNU ARM64 syntax: cbz, cbnz and some store instructions,
 133  such as str, stur, strb, sturb, strh, sturh stlr, stlrb. stlrh, st1.
 134  
 135    Examples:
 136      MOVD R29, 384(R19)    <=>    str x29, [x19,#384]
 137      MOVB.P R30, 30(R4)    <=>    strb w30, [x4],#30
 138      STLRH R21, (R19)      <=>    stlrh w21, [x19]
 139  
 140  (2) MADD, MADDW, MSUB, MSUBW, SMADDL, SMSUBL, UMADDL, UMSUBL <Rm>, <Ra>, <Rn>, <Rd>
 141  
 142    Examples:
 143      MADD R2, R30, R22, R6       <=>    madd x6, x22, x2, x30
 144      SMSUBL R10, R3, R17, R27    <=>    smsubl x27, w17, w10, x3
 145  
 146  (3) FMADDD, FMADDS, FMSUBD, FMSUBS, FNMADDD, FNMADDS, FNMSUBD, FNMSUBS <Fm>, <Fa>, <Fn>, <Fd>
 147  
 148    Examples:
 149      FMADDD F30, F20, F3, F29    <=>    fmadd d29, d3, d30, d20
 150      FNMSUBS F7, F25, F7, F22    <=>    fnmsub s22, s7, s7, s25
 151  
 152  (4) BFI, BFXIL, SBFIZ, SBFX, UBFIZ, UBFX $<lsb>, <Rn>, $<width>, <Rd>
 153  
 154    Examples:
 155      BFIW $16, R20, $6, R0      <=>    bfi w0, w20, #16, #6
 156      UBFIZ $34, R26, $5, R20    <=>    ubfiz x20, x26, #34, #5
 157  
 158  (5) FCCMPD, FCCMPS, FCCMPED, FCCMPES <cond>, Fm. Fn, $<nzcv>
 159  
 160    Examples:
 161      FCCMPD AL, F8, F26, $0     <=>    fccmp d26, d8, #0x0, al
 162      FCCMPS VS, F29, F4, $4     <=>    fccmp s4, s29, #0x4, vs
 163      FCCMPED LE, F20, F5, $13   <=>    fccmpe d5, d20, #0xd, le
 164      FCCMPES NE, F26, F10, $0   <=>    fccmpe s10, s26, #0x0, ne
 165  
 166  (6) CCMN, CCMNW, CCMP, CCMPW <cond>, <Rn>, $<imm>, $<nzcv>
 167  
 168    Examples:
 169      CCMP MI, R22, $12, $13     <=>    ccmp x22, #0xc, #0xd, mi
 170      CCMNW AL, R1, $11, $8      <=>    ccmn w1, #0xb, #0x8, al
 171  
 172  (7) CCMN, CCMNW, CCMP, CCMPW <cond>, <Rn>, <Rm>, $<nzcv>
 173  
 174    Examples:
 175      CCMN VS, R13, R22, $10     <=>    ccmn x13, x22, #0xa, vs
 176      CCMPW HS, R19, R14, $11    <=>    ccmp w19, w14, #0xb, cs
 177  
 178  (9) CSEL, CSELW, CSNEG, CSNEGW, CSINC, CSINCW <cond>, <Rn>, <Rm>, <Rd> ;
 179  FCSELD, FCSELS <cond>, <Fn>, <Fm>, <Fd>
 180  
 181    Examples:
 182      CSEL GT, R0, R19, R1        <=>    csel x1, x0, x19, gt
 183      CSNEGW GT, R7, R17, R8      <=>    csneg w8, w7, w17, gt
 184      FCSELD EQ, F15, F18, F16    <=>    fcsel d16, d15, d18, eq
 185  
 186  (10) TBNZ, TBZ $<imm>, <Rt>, <label>
 187  
 188  
 189  (11) STLXR, STLXRW, STXR, STXRW, STLXRB, STLXRH, STXRB, STXRH  <Rf>, (<Rn|RSP>), <Rs>
 190  
 191    Examples:
 192      STLXR ZR, (R15), R16    <=>    stlxr w16, xzr, [x15]
 193      STXRB R9, (R21), R19    <=>    stxrb w19, w9, [x21]
 194  
 195  (12) STLXP, STLXPW, STXP, STXPW (<Rf1>, <Rf2>), (<Rn|RSP>), <Rs>
 196  
 197    Examples:
 198      STLXP (R17, R19), (R4), R5      <=>    stlxp w5, x17, x19, [x4]
 199      STXPW (R30, R25), (R22), R13    <=>    stxp w13, w30, w25, [x22]
 200  
 201  2. Expressions for special arguments.
 202  
 203  #<immediate> is written as $<immediate>.
 204  
 205  Optionally-shifted immediate.
 206  
 207    Examples:
 208      ADD $(3151<<12), R14, R20     <=>    add x20, x14, #0xc4f, lsl #12
 209      ADDW $1864, R25, R6           <=>    add w6, w25, #0x748
 210  
 211  Optionally-shifted registers are written as <Rm>{<shift><amount>}.
 212  The <shift> can be <<(lsl), >>(lsr), ->(asr), @>(ror).
 213  
 214    Examples:
 215      ADD R19>>30, R10, R24     <=>    add x24, x10, x19, lsr #30
 216      ADDW R26->24, R21, R15    <=>    add w15, w21, w26, asr #24
 217  
 218  Extended registers are written as <Rm>{.<extend>{<<<amount>}}.
 219  <extend> can be UXTB, UXTH, UXTW, UXTX, SXTB, SXTH, SXTW or SXTX.
 220  
 221    Examples:
 222      ADDS R19.UXTB<<4, R9, R26     <=>    adds x26, x9, w19, uxtb #4
 223      ADDSW R14.SXTX, R14, R6       <=>    adds w6, w14, w14, sxtx
 224  
 225  Memory references: [<Xn|SP>{,#0}] is written as (Rn|RSP), a base register and an immediate
 226  offset is written as imm(Rn|RSP), a base register and an offset register is written as (Rn|RSP)(Rm).
 227  
 228    Examples:
 229      LDAR (R22), R9                  <=>    ldar x9, [x22]
 230      LDP 28(R17), (R15, R23)         <=>    ldp x15, x23, [x17,#28]
 231      MOVWU (R4)(R12<<2), R8          <=>    ldr w8, [x4, x12, lsl #2]
 232      MOVD (R7)(R11.UXTW<<3), R25     <=>    ldr x25, [x7,w11,uxtw #3]
 233      MOVBU (R27)(R23), R14           <=>    ldrb w14, [x27,x23]
 234  
 235  Register pairs are written as (Rt1, Rt2).
 236  
 237    Examples:
 238      LDP.P -240(R11), (R12, R26)    <=>    ldp x12, x26, [x11],#-240
 239  
 240  Register with arrangement and register with arrangement and index.
 241  
 242    Examples:
 243      VADD V5.H8, V18.H8, V9.H8                     <=>    add v9.8h, v18.8h, v5.8h
 244      VLD1 (R2), [V21.B16]                          <=>    ld1 {v21.16b}, [x2]
 245      VST1.P V9.S[1], (R16)(R21)                    <=>    st1 {v9.s}[1], [x16], x28
 246      VST1.P [V13.H8, V14.H8, V15.H8], (R3)(R14)    <=>    st1 {v13.8h-v15.8h}, [x3], x14
 247      VST1.P [V14.D1, V15.D1], (R7)(R23)            <=>    st1 {v14.1d, v15.1d}, [x7], x23
 248  */
 249  package arm64
 250