else
{
/* Print SImode register names to force addr32 prefix. */
- if (GET_CODE (addr) == SUBREG)
- {
- gcc_assert (TARGET_64BIT);
- gcc_assert (GET_MODE (addr) == SImode);
- gcc_assert (GET_MODE (SUBREG_REG (addr)) == DImode);
- gcc_assert (!code);
- code = 'l';
- }
- else if (GET_CODE (addr) == ZERO_EXTEND
- || GET_CODE (addr) == AND)
+ if (SImode_address_operand (addr, VOIDmode))
{
+#ifdef ENABLE_CHECKING
gcc_assert (TARGET_64BIT);
- gcc_assert (GET_MODE (addr) == DImode);
+ switch (GET_CODE (addr))
+ {
+ case SUBREG:
+ gcc_assert (GET_MODE (addr) == SImode);
+ gcc_assert (GET_MODE (SUBREG_REG (addr)) == DImode);
+ break;
+ case ZERO_EXTEND:
+ case AND:
+ gcc_assert (GET_MODE (addr) == DImode);
+ break;
+ default:
+ gcc_unreachable ();
+ }
+#endif
gcc_assert (!code);
code = 'l';
}
{
rtx m;
rtx (*extract) (rtx, rtx, rtx);
- rtx (*move_unaligned) (rtx, rtx);
+ rtx (*load_unaligned) (rtx, rtx);
+ rtx (*store_unaligned) (rtx, rtx);
enum machine_mode mode;
switch (GET_MODE (op0))
gcc_unreachable ();
case V32QImode:
extract = gen_avx_vextractf128v32qi;
- move_unaligned = gen_avx_movdqu256;
+ load_unaligned = gen_avx_loaddqu256;
+ store_unaligned = gen_avx_storedqu256;
mode = V16QImode;
break;
case V8SFmode:
extract = gen_avx_vextractf128v8sf;
- move_unaligned = gen_avx_movups256;
+ load_unaligned = gen_avx_loadups256;
+ store_unaligned = gen_avx_storeups256;
mode = V4SFmode;
break;
case V4DFmode:
extract = gen_avx_vextractf128v4df;
- move_unaligned = gen_avx_movupd256;
+ load_unaligned = gen_avx_loadupd256;
+ store_unaligned = gen_avx_storeupd256;
mode = V2DFmode;
break;
}
- if (MEM_P (op1) && TARGET_AVX256_SPLIT_UNALIGNED_LOAD)
+ if (MEM_P (op1))
{
- rtx r = gen_reg_rtx (mode);
- m = adjust_address (op1, mode, 0);
- emit_move_insn (r, m);
- m = adjust_address (op1, mode, 16);
- r = gen_rtx_VEC_CONCAT (GET_MODE (op0), r, m);
- emit_move_insn (op0, r);
+ if (TARGET_AVX256_SPLIT_UNALIGNED_LOAD)
+ {
+ rtx r = gen_reg_rtx (mode);
+ m = adjust_address (op1, mode, 0);
+ emit_move_insn (r, m);
+ m = adjust_address (op1, mode, 16);
+ r = gen_rtx_VEC_CONCAT (GET_MODE (op0), r, m);
+ emit_move_insn (op0, r);
+ }
+ else
+ emit_insn (load_unaligned (op0, op1));
}
- else if (MEM_P (op0) && TARGET_AVX256_SPLIT_UNALIGNED_STORE)
+ else if (MEM_P (op0))
{
- m = adjust_address (op0, mode, 0);
- emit_insn (extract (m, op1, const0_rtx));
- m = adjust_address (op0, mode, 16);
- emit_insn (extract (m, op1, const1_rtx));
+ if (TARGET_AVX256_SPLIT_UNALIGNED_STORE)
+ {
+ m = adjust_address (op0, mode, 0);
+ emit_insn (extract (m, op1, const0_rtx));
+ m = adjust_address (op0, mode, 16);
+ emit_insn (extract (m, op1, const1_rtx));
+ }
+ else
+ emit_insn (store_unaligned (op0, op1));
}
else
- emit_insn (move_unaligned (op0, op1));
+ gcc_unreachable ();
}
/* Implement the movmisalign patterns for SSE. Non-SSE modes go
ix86_expand_vector_move_misalign (enum machine_mode mode, rtx operands[])
{
rtx op0, op1, m;
+ rtx (*move_unaligned) (rtx, rtx);
op0 = operands[0];
op1 = operands[1];
/* If we're optimizing for size, movups is the smallest. */
if (TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL)
{
+ if (MEM_P (op1))
+ move_unaligned = gen_sse_loadups;
+ else if (MEM_P (op0))
+ move_unaligned = gen_sse_storeups;
+ else
+ gcc_unreachable ();
+
op0 = gen_lowpart (V4SFmode, op0);
op1 = gen_lowpart (V4SFmode, op1);
- emit_insn (gen_sse_movups (op0, op1));
+ emit_insn (move_unaligned (op0, op1));
return;
}
+ if (MEM_P (op1))
+ move_unaligned = gen_sse2_loaddqu;
+ else if (MEM_P (op0))
+ move_unaligned = gen_sse2_storedqu;
+ else
+ gcc_unreachable ();
+
op0 = gen_lowpart (V16QImode, op0);
op1 = gen_lowpart (V16QImode, op1);
- emit_insn (gen_sse2_movdqu (op0, op1));
+ emit_insn (move_unaligned (op0, op1));
break;
case 32:
op0 = gen_lowpart (V32QImode, op0);
switch (mode)
{
case V4SFmode:
- emit_insn (gen_sse_movups (op0, op1));
+ if (MEM_P (op1))
+ move_unaligned = gen_sse_loadups;
+ else if (MEM_P (op0))
+ move_unaligned = gen_sse_storeups;
+ else
+ gcc_unreachable ();
+
+ emit_insn (move_unaligned (op0, op1));
break;
case V8SFmode:
ix86_avx256_split_vector_move_misalign (op0, op1);
case V2DFmode:
if (TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL)
{
+ if (MEM_P (op1))
+ move_unaligned = gen_sse_loadups;
+ else if (MEM_P (op0))
+ move_unaligned = gen_sse_storeups;
+ else
+ gcc_unreachable ();
+
op0 = gen_lowpart (V4SFmode, op0);
op1 = gen_lowpart (V4SFmode, op1);
- emit_insn (gen_sse_movups (op0, op1));
+ emit_insn (move_unaligned (op0, op1));
return;
}
- emit_insn (gen_sse2_movupd (op0, op1));
+ if (MEM_P (op1))
+ move_unaligned = gen_sse2_loadupd;
+ else if (MEM_P (op0))
+ move_unaligned = gen_sse2_storeupd;
+ else
+ gcc_unreachable ();
+
+ emit_insn (move_unaligned (op0, op1));
break;
case V4DFmode:
ix86_avx256_split_vector_move_misalign (op0, op1);
{
op0 = gen_lowpart (V4SFmode, op0);
op1 = gen_lowpart (V4SFmode, op1);
- emit_insn (gen_sse_movups (op0, op1));
+ emit_insn (gen_sse_loadups (op0, op1));
return;
}
{
op0 = gen_lowpart (V16QImode, op0);
op1 = gen_lowpart (V16QImode, op1);
- emit_insn (gen_sse2_movdqu (op0, op1));
+ emit_insn (gen_sse2_loaddqu (op0, op1));
return;
}
{
op0 = gen_lowpart (V2DFmode, op0);
op1 = gen_lowpart (V2DFmode, op1);
- emit_insn (gen_sse2_movupd (op0, op1));
+ emit_insn (gen_sse2_loadupd (op0, op1));
return;
}
{
op0 = gen_lowpart (V4SFmode, op0);
op1 = gen_lowpart (V4SFmode, op1);
- emit_insn (gen_sse_movups (op0, op1));
+ emit_insn (gen_sse_loadups (op0, op1));
return;
}
{
op0 = gen_lowpart (V4SFmode, op0);
op1 = gen_lowpart (V4SFmode, op1);
- emit_insn (gen_sse_movups (op0, op1));
+ emit_insn (gen_sse_storeups (op0, op1));
return;
}
{
op0 = gen_lowpart (V16QImode, op0);
op1 = gen_lowpart (V16QImode, op1);
- emit_insn (gen_sse2_movdqu (op0, op1));
+ emit_insn (gen_sse2_storedqu (op0, op1));
return;
}
{
op0 = gen_lowpart (V2DFmode, op0);
op1 = gen_lowpart (V2DFmode, op1);
- emit_insn (gen_sse2_movupd (op0, op1));
+ emit_insn (gen_sse2_storeupd (op0, op1));
}
else
{
if (TARGET_SSE_UNALIGNED_STORE_OPTIMAL)
{
op0 = gen_lowpart (V4SFmode, op0);
- emit_insn (gen_sse_movups (op0, op1));
+ emit_insn (gen_sse_storeups (op0, op1));
}
else
{
\f
/* Calculate the length of the memory address in the instruction encoding.
Includes addr32 prefix, does not include the one-byte modrm, opcode,
- or other prefixes. */
+ or other prefixes. We never generate addr32 prefix for LEA insn. */
int
-memory_address_length (rtx addr)
+memory_address_length (rtx addr, bool lea)
{
struct ix86_address parts;
rtx base, index, disp;
ok = ix86_decompose_address (addr, &parts);
gcc_assert (ok);
- if (parts.base && GET_CODE (parts.base) == SUBREG)
- parts.base = SUBREG_REG (parts.base);
- if (parts.index && GET_CODE (parts.index) == SUBREG)
- parts.index = SUBREG_REG (parts.index);
+ len = (parts.seg == SEG_DEFAULT) ? 0 : 1;
+
+ /* If this is not LEA instruction, add the length of addr32 prefix. */
+ if (TARGET_64BIT && !lea
+ && (SImode_address_operand (addr, VOIDmode)
+ || (parts.base && GET_MODE (parts.base) == SImode)
+ || (parts.index && GET_MODE (parts.index) == SImode)))
+ len++;
base = parts.base;
index = parts.index;
disp = parts.disp;
- /* Add length of addr32 prefix. */
- len = (GET_CODE (addr) == ZERO_EXTEND
- || GET_CODE (addr) == AND);
+ if (base && GET_CODE (base) == SUBREG)
+ base = SUBREG_REG (base);
+ if (index && GET_CODE (index) == SUBREG)
+ index = SUBREG_REG (index);
+
+ gcc_assert (base == NULL_RTX || REG_P (base));
+ gcc_assert (index == NULL_RTX || REG_P (index));
/* Rule of thumb:
- esp as the base always wants an index,
/* esp (for its index) and ebp (for its displacement) need
the two-byte modrm form. Similarly for r12 and r13 in 64-bit
code. */
- if (REG_P (addr)
- && (addr == arg_pointer_rtx
- || addr == frame_pointer_rtx
- || REGNO (addr) == SP_REG
- || REGNO (addr) == BP_REG
- || REGNO (addr) == R12_REG
- || REGNO (addr) == R13_REG))
- len = 1;
+ if (base == arg_pointer_rtx
+ || base == frame_pointer_rtx
+ || REGNO (base) == SP_REG
+ || REGNO (base) == BP_REG
+ || REGNO (base) == R12_REG
+ || REGNO (base) == R13_REG)
+ len++;
}
/* Direct Addressing. In 64-bit mode mod 00 r/m 5
by UNSPEC. */
else if (disp && !base && !index)
{
- len = 4;
+ len += 4;
if (TARGET_64BIT)
{
rtx symbol = disp;
|| (XINT (symbol, 1) != UNSPEC_GOTPCREL
&& XINT (symbol, 1) != UNSPEC_PCREL
&& XINT (symbol, 1) != UNSPEC_GOTNTPOFF)))
- len += 1;
+ len++;
}
}
-
else
{
/* Find the length of the displacement constant. */
if (disp)
{
if (base && satisfies_constraint_K (disp))
- len = 1;
+ len += 1;
else
- len = 4;
+ len += 4;
}
/* ebp always wants a displacement. Similarly r13. */
- else if (base && REG_P (base)
- && (REGNO (base) == BP_REG || REGNO (base) == R13_REG))
- len = 1;
+ else if (base && (REGNO (base) == BP_REG || REGNO (base) == R13_REG))
+ len++;
/* An index requires the two-byte modrm form.... */
if (index
/* ...like esp (or r12), which always wants an index. */
|| base == arg_pointer_rtx
|| base == frame_pointer_rtx
- || (base && REG_P (base)
- && (REGNO (base) == SP_REG || REGNO (base) == R12_REG)))
- len += 1;
- }
-
- switch (parts.seg)
- {
- case SEG_FS:
- case SEG_GS:
- len += 1;
- break;
- default:
- break;
+ || (base && (REGNO (base) == SP_REG || REGNO (base) == R12_REG)))
+ len++;
}
return len;
case MODE_SI:
len = 4;
break;
- /* Immediates for DImode instructions are encoded as 32bit sign extended values. */
+ /* Immediates for DImode instructions are encoded
+ as 32bit sign extended values. */
case MODE_DI:
len = 4;
break;
}
return len;
}
+
/* Compute default value for "length_address" attribute. */
int
ix86_attr_length_address_default (rtx insn)
gcc_assert (GET_CODE (set) == SET);
addr = SET_SRC (set);
- if (TARGET_64BIT && get_attr_mode (insn) == MODE_SI)
- {
- if (GET_CODE (addr) == ZERO_EXTEND)
- addr = XEXP (addr, 0);
- if (GET_CODE (addr) == SUBREG)
- addr = SUBREG_REG (addr);
- }
- return memory_address_length (addr);
+ return memory_address_length (addr, true);
}
extract_insn_cached (insn);
if (*constraints == 'X')
continue;
}
- return memory_address_length (XEXP (recog_data.operand[i], 0));
+ return memory_address_length (XEXP (recog_data.operand[i], 0), false);
}
return 0;
}
{ OPTION_MASK_ISA_3DNOW, CODE_FOR_mmx_femms, "__builtin_ia32_femms", IX86_BUILTIN_FEMMS, UNKNOWN, (int) VOID_FTYPE_VOID },
/* SSE */
- { OPTION_MASK_ISA_SSE, CODE_FOR_sse_movups, "__builtin_ia32_storeups", IX86_BUILTIN_STOREUPS, UNKNOWN, (int) VOID_FTYPE_PFLOAT_V4SF },
+ { OPTION_MASK_ISA_SSE, CODE_FOR_sse_storeups, "__builtin_ia32_storeups", IX86_BUILTIN_STOREUPS, UNKNOWN, (int) VOID_FTYPE_PFLOAT_V4SF },
{ OPTION_MASK_ISA_SSE, CODE_FOR_sse_movntv4sf, "__builtin_ia32_movntps", IX86_BUILTIN_MOVNTPS, UNKNOWN, (int) VOID_FTYPE_PFLOAT_V4SF },
- { OPTION_MASK_ISA_SSE, CODE_FOR_sse_movups, "__builtin_ia32_loadups", IX86_BUILTIN_LOADUPS, UNKNOWN, (int) V4SF_FTYPE_PCFLOAT },
+ { OPTION_MASK_ISA_SSE, CODE_FOR_sse_loadups, "__builtin_ia32_loadups", IX86_BUILTIN_LOADUPS, UNKNOWN, (int) V4SF_FTYPE_PCFLOAT },
{ OPTION_MASK_ISA_SSE, CODE_FOR_sse_loadhps_exp, "__builtin_ia32_loadhps", IX86_BUILTIN_LOADHPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_PCV2SF },
{ OPTION_MASK_ISA_SSE, CODE_FOR_sse_loadlps_exp, "__builtin_ia32_loadlps", IX86_BUILTIN_LOADLPS, UNKNOWN, (int) V4SF_FTYPE_V4SF_PCV2SF },
/* SSE2 */
{ OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_lfence, "__builtin_ia32_lfence", IX86_BUILTIN_LFENCE, UNKNOWN, (int) VOID_FTYPE_VOID },
{ OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_mfence, 0, IX86_BUILTIN_MFENCE, UNKNOWN, (int) VOID_FTYPE_VOID },
- { OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_movupd, "__builtin_ia32_storeupd", IX86_BUILTIN_STOREUPD, UNKNOWN, (int) VOID_FTYPE_PDOUBLE_V2DF },
- { OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_movdqu, "__builtin_ia32_storedqu", IX86_BUILTIN_STOREDQU, UNKNOWN, (int) VOID_FTYPE_PCHAR_V16QI },
+ { OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_storeupd, "__builtin_ia32_storeupd", IX86_BUILTIN_STOREUPD, UNKNOWN, (int) VOID_FTYPE_PDOUBLE_V2DF },
+ { OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_storedqu, "__builtin_ia32_storedqu", IX86_BUILTIN_STOREDQU, UNKNOWN, (int) VOID_FTYPE_PCHAR_V16QI },
{ OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_movntv2df, "__builtin_ia32_movntpd", IX86_BUILTIN_MOVNTPD, UNKNOWN, (int) VOID_FTYPE_PDOUBLE_V2DF },
{ OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_movntv2di, "__builtin_ia32_movntdq", IX86_BUILTIN_MOVNTDQ, UNKNOWN, (int) VOID_FTYPE_PV2DI_V2DI },
{ OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_movntisi, "__builtin_ia32_movnti", IX86_BUILTIN_MOVNTI, UNKNOWN, (int) VOID_FTYPE_PINT_INT },
{ OPTION_MASK_ISA_SSE2 | OPTION_MASK_ISA_64BIT, CODE_FOR_sse2_movntidi, "__builtin_ia32_movnti64", IX86_BUILTIN_MOVNTI64, UNKNOWN, (int) VOID_FTYPE_PLONGLONG_LONGLONG },
- { OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_movupd, "__builtin_ia32_loadupd", IX86_BUILTIN_LOADUPD, UNKNOWN, (int) V2DF_FTYPE_PCDOUBLE },
- { OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_movdqu, "__builtin_ia32_loaddqu", IX86_BUILTIN_LOADDQU, UNKNOWN, (int) V16QI_FTYPE_PCCHAR },
+ { OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_loadupd, "__builtin_ia32_loadupd", IX86_BUILTIN_LOADUPD, UNKNOWN, (int) V2DF_FTYPE_PCDOUBLE },
+ { OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_loaddqu, "__builtin_ia32_loaddqu", IX86_BUILTIN_LOADDQU, UNKNOWN, (int) V16QI_FTYPE_PCCHAR },
{ OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_loadhpd_exp, "__builtin_ia32_loadhpd", IX86_BUILTIN_LOADHPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_PCDOUBLE },
{ OPTION_MASK_ISA_SSE2, CODE_FOR_sse2_loadlpd_exp, "__builtin_ia32_loadlpd", IX86_BUILTIN_LOADLPD, UNKNOWN, (int) V2DF_FTYPE_V2DF_PCDOUBLE },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_vbroadcastf128_v4df, "__builtin_ia32_vbroadcastf128_pd256", IX86_BUILTIN_VBROADCASTPD256, UNKNOWN, (int) V4DF_FTYPE_PCV2DF },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_vbroadcastf128_v8sf, "__builtin_ia32_vbroadcastf128_ps256", IX86_BUILTIN_VBROADCASTPS256, UNKNOWN, (int) V8SF_FTYPE_PCV4SF },
- { OPTION_MASK_ISA_AVX, CODE_FOR_avx_movupd256, "__builtin_ia32_loadupd256", IX86_BUILTIN_LOADUPD256, UNKNOWN, (int) V4DF_FTYPE_PCDOUBLE },
- { OPTION_MASK_ISA_AVX, CODE_FOR_avx_movups256, "__builtin_ia32_loadups256", IX86_BUILTIN_LOADUPS256, UNKNOWN, (int) V8SF_FTYPE_PCFLOAT },
- { OPTION_MASK_ISA_AVX, CODE_FOR_avx_movupd256, "__builtin_ia32_storeupd256", IX86_BUILTIN_STOREUPD256, UNKNOWN, (int) VOID_FTYPE_PDOUBLE_V4DF },
- { OPTION_MASK_ISA_AVX, CODE_FOR_avx_movups256, "__builtin_ia32_storeups256", IX86_BUILTIN_STOREUPS256, UNKNOWN, (int) VOID_FTYPE_PFLOAT_V8SF },
- { OPTION_MASK_ISA_AVX, CODE_FOR_avx_movdqu256, "__builtin_ia32_loaddqu256", IX86_BUILTIN_LOADDQU256, UNKNOWN, (int) V32QI_FTYPE_PCCHAR },
- { OPTION_MASK_ISA_AVX, CODE_FOR_avx_movdqu256, "__builtin_ia32_storedqu256", IX86_BUILTIN_STOREDQU256, UNKNOWN, (int) VOID_FTYPE_PCHAR_V32QI },
+ { OPTION_MASK_ISA_AVX, CODE_FOR_avx_loadupd256, "__builtin_ia32_loadupd256", IX86_BUILTIN_LOADUPD256, UNKNOWN, (int) V4DF_FTYPE_PCDOUBLE },
+ { OPTION_MASK_ISA_AVX, CODE_FOR_avx_loadups256, "__builtin_ia32_loadups256", IX86_BUILTIN_LOADUPS256, UNKNOWN, (int) V8SF_FTYPE_PCFLOAT },
+ { OPTION_MASK_ISA_AVX, CODE_FOR_avx_storeupd256, "__builtin_ia32_storeupd256", IX86_BUILTIN_STOREUPD256, UNKNOWN, (int) VOID_FTYPE_PDOUBLE_V4DF },
+ { OPTION_MASK_ISA_AVX, CODE_FOR_avx_storeups256, "__builtin_ia32_storeups256", IX86_BUILTIN_STOREUPS256, UNKNOWN, (int) VOID_FTYPE_PFLOAT_V8SF },
+ { OPTION_MASK_ISA_AVX, CODE_FOR_avx_loaddqu256, "__builtin_ia32_loaddqu256", IX86_BUILTIN_LOADDQU256, UNKNOWN, (int) V32QI_FTYPE_PCCHAR },
+ { OPTION_MASK_ISA_AVX, CODE_FOR_avx_storedqu256, "__builtin_ia32_storedqu256", IX86_BUILTIN_STOREDQU256, UNKNOWN, (int) VOID_FTYPE_PCHAR_V32QI },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_lddqu256, "__builtin_ia32_lddqu256", IX86_BUILTIN_LDDQU256, UNKNOWN, (int) V32QI_FTYPE_PCCHAR },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_movntv4di, "__builtin_ia32_movntdq256", IX86_BUILTIN_MOVNTDQ256, UNKNOWN, (int) VOID_FTYPE_PV4DI_V4DI },
OSDN Git Service
