(UNSPEC_SET_RIP 16)
(UNSPEC_SET_GOT_OFFSET 17)
(UNSPEC_MEMORY_BLOCKAGE 18)
+ (UNSPEC_SSE_PROLOGUE_SAVE_LOW 19)
; TLS support
(UNSPEC_TP 20)
(define_code_iterator maxmin [smax smin umax umin])
;; Base name for integer and FP insn mnemonic
-(define_code_attr maxminiprefix [(smax "maxs") (smin "mins")
- (umax "maxu") (umin "minu")])
-(define_code_attr maxminfprefix [(smax "max") (smin "min")])
+(define_code_attr maxmin_int [(smax "maxs") (smin "mins")
+ (umax "maxu") (umin "minu")])
+(define_code_attr maxmin_float [(smax "max") (smin "min")])
;; Mapping of logic operators
(define_code_iterator any_logic [and ior xor])
(define_code_iterator any_or [ior xor])
;; Base name for insn mnemonic.
-(define_code_attr logicprefix [(and "and") (ior "or") (xor "xor")])
+(define_code_attr logic [(and "and") (ior "or") (xor "xor")])
;; Mapping of shift-right operators
(define_code_iterator any_shiftrt [lshiftrt ashiftrt])
(define_code_iterator absneg [abs neg])
;; Base name for x87 insn mnemonic.
-(define_code_attr absnegprefix [(abs "abs") (neg "chs")])
+(define_code_attr absneg_mnemonic [(abs "abs") (neg "chs")])
;; Used in signed and unsigned widening multiplications.
(define_code_iterator any_extend [sign_extend zero_extend])
(clobber (reg:CC FLAGS_REG))]
""
"#"
- "&& reload_completed"
+ "reload_completed"
[(parallel [(set (match_dup 1)
(ashiftrt:SWIM248 (match_dup 4) (match_dup 5)))
(clobber (reg:CC FLAGS_REG))])
(use (match_dup 1))
(clobber (reg:CC FLAGS_REG))])]
{
- operands[5] = GEN_INT (GET_MODE_BITSIZE (<MODE>mode) - 1);
+ operands[5] = GEN_INT (GET_MODE_BITSIZE (<MODE>mode)-1);
if (<MODE>mode != HImode
&& (optimize_function_for_size_p (cfun) || TARGET_USE_CLTD))
(clobber (reg:CC FLAGS_REG))]
""
"#"
- "&& reload_completed"
+ "reload_completed"
[(set (match_dup 1) (const_int 0))
(parallel [(set (match_dup 0)
(udiv:SWIM248 (match_dup 2) (match_dup 3)))
(match_operand:SWI248 2 "<general_operand>" "<g>,r<i>")))
(clobber (reg:CC FLAGS_REG))]
"ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
- "<logicprefix>{<imodesuffix>}\t{%2, %0|%0, %2}"
+ "<logic>{<imodesuffix>}\t{%2, %0|%0, %2}"
[(set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(clobber (reg:CC FLAGS_REG))]
"ix86_binary_operator_ok (<CODE>, QImode, operands)"
"@
- <logicprefix>{b}\t{%2, %0|%0, %2}
- <logicprefix>{b}\t{%2, %0|%0, %2}
- <logicprefix>{l}\t{%k2, %k0|%k0, %k2}"
+ <logic>{b}\t{%2, %0|%0, %2}
+ <logic>{b}\t{%2, %0|%0, %2}
+ <logic>{l}\t{%k2, %k0|%k0, %k2}"
[(set_attr "type" "alu")
(set_attr "mode" "QI,QI,SI")])
(match_operand:SI 2 "general_operand" "g"))))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT && ix86_binary_operator_ok (<CODE>, SImode, operands)"
- "<logicprefix>{l}\t{%2, %k0|%k0, %2}"
+ "<logic>{l}\t{%2, %k0|%k0, %2}"
[(set_attr "type" "alu")
(set_attr "mode" "SI")])
(match_operand:DI 2 "x86_64_zext_immediate_operand" "Z")))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT && ix86_binary_operator_ok (<CODE>, SImode, operands)"
- "<logicprefix>{l}\t{%2, %k0|%k0, %2}"
+ "<logic>{l}\t{%2, %k0|%k0, %2}"
[(set_attr "type" "alu")
(set_attr "mode" "SI")])
(clobber (reg:CC FLAGS_REG))]
"(!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
&& !(MEM_P (operands[0]) && MEM_P (operands[1]))"
- "<logicprefix>{b}\t{%1, %0|%0, %1}"
+ "<logic>{b}\t{%1, %0|%0, %1}"
[(set_attr "type" "alu1")
(set_attr "mode" "QI")])
(any_or:SWI (match_dup 1) (match_dup 2)))]
"ix86_match_ccmode (insn, CCNOmode)
&& ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
- "<logicprefix>{<imodesuffix>}\t{%2, %0|%0, %2}"
+ "<logic>{<imodesuffix>}\t{%2, %0|%0, %2}"
[(set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(zero_extend:DI (any_or:SI (match_dup 1) (match_dup 2))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCNOmode)
&& ix86_binary_operator_ok (<CODE>, SImode, operands)"
- "<logicprefix>{l}\t{%2, %k0|%k0, %2}"
+ "<logic>{l}\t{%2, %k0|%k0, %2}"
[(set_attr "type" "alu")
(set_attr "mode" "SI")])
(any_or:DI (zero_extend:DI (match_dup 1)) (match_dup 2)))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCNOmode)
&& ix86_binary_operator_ok (<CODE>, SImode, operands)"
- "<logicprefix>{l}\t{%2, %k0|%k0, %2}"
+ "<logic>{l}\t{%2, %k0|%k0, %2}"
[(set_attr "type" "alu")
(set_attr "mode" "SI")])
"(!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
&& ix86_match_ccmode (insn, CCNOmode)
&& !(MEM_P (operands[0]) && MEM_P (operands[1]))"
- "<logicprefix>{b}\t{%1, %0|%0, %1}"
+ "<logic>{b}\t{%1, %0|%0, %1}"
[(set_attr "type" "alu1")
(set_attr "mode" "QI")])
(clobber (match_scratch:SWI 0 "=<r>"))]
"ix86_match_ccmode (insn, CCNOmode)
&& ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
- "<logicprefix>{<imodesuffix>}\t{%2, %0|%0, %2}"
+ "<logic>{<imodesuffix>}\t{%2, %0|%0, %2}"
[(set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(match_operand 2 "const_int_operand" "n")))
(clobber (reg:CC FLAGS_REG))]
"!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
- "<logicprefix>{b}\t{%2, %h0|%h0, %2}"
+ "<logic>{b}\t{%2, %h0|%h0, %2}"
[(set_attr "type" "alu")
(set_attr "length_immediate" "1")
(set_attr "modrm" "1")
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT
&& (!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))"
- "<logicprefix>{b}\t{%2, %h0|%h0, %2}"
+ "<logic>{b}\t{%2, %h0|%h0, %2}"
[(set_attr "type" "alu")
(set_attr "length_immediate" "0")
(set_attr "mode" "QI")])
(clobber (reg:CC FLAGS_REG))]
"!TARGET_64BIT
&& (!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))"
- "<logicprefix>{b}\t{%2, %h0|%h0, %2}"
+ "<logic>{b}\t{%2, %h0|%h0, %2}"
[(set_attr "type" "alu")
(set_attr "length_immediate" "0")
(set_attr "mode" "QI")])
(const_int 8))))
(clobber (reg:CC FLAGS_REG))]
"!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
- "<logicprefix>{b}\t{%h2, %h0|%h0, %h2}"
+ "<logic>{b}\t{%h2, %h0|%h0, %h2}"
[(set_attr "type" "alu")
(set_attr "length_immediate" "0")
(set_attr "mode" "QI")])
"TARGET_80387
&& (reload_completed
|| !(SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH))"
- "f<absnegprefix>"
+ "f<absneg_mnemonic>"
[(set_attr "type" "fsgn")
(set_attr "mode" "<MODE>")])
(absneg:DF (float_extend:DF
(match_operand:SF 1 "register_operand" "0"))))]
"TARGET_80387 && (!TARGET_SSE_MATH || TARGET_MIX_SSE_I387)"
- "f<absnegprefix>"
+ "f<absneg_mnemonic>"
[(set_attr "type" "fsgn")
(set_attr "mode" "DF")])
(absneg:XF (float_extend:XF
(match_operand:SF 1 "register_operand" "0"))))]
"TARGET_80387"
- "f<absnegprefix>"
+ "f<absneg_mnemonic>"
[(set_attr "type" "fsgn")
(set_attr "mode" "XF")])
(define_insn "*<code>extenddfxf2"
[(set (match_operand:XF 0 "register_operand" "=f")
(absneg:XF (float_extend:XF
- (match_operand:DF 1 "register_operand" "0"))))]
+ (match_operand:DF 1 "register_operand" "0"))))]
"TARGET_80387"
- "f<absnegprefix>"
+ "f<absneg_mnemonic>"
[(set_attr "type" "fsgn")
(set_attr "mode" "XF")])
(const_string "*")))
(set_attr "mode" "QI,SI,SI")])
+(define_insn "*ashlqi3_1_slp"
+ [(set (strict_low_part (match_operand:QI 0 "nonimmediate_operand" "+qm"))
+ (ashift:QI (match_dup 0)
+ (match_operand:QI 1 "nonmemory_operand" "cI")))
+ (clobber (reg:CC FLAGS_REG))]
+ "(optimize_function_for_size_p (cfun)
+ || !TARGET_PARTIAL_FLAG_REG_STALL
+ || (operands[1] == const1_rtx
+ && (TARGET_SHIFT1
+ || (TARGET_DOUBLE_WITH_ADD && REG_P (operands[0])))))"
+{
+ switch (get_attr_type (insn))
+ {
+ case TYPE_ALU:
+ gcc_assert (operands[1] == const1_rtx);
+ return "add{b}\t%0, %0";
+
+ default:
+ if (operands[1] == const1_rtx
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ return "sal{b}\t%0";
+ else
+ return "sal{b}\t{%1, %0|%0, %1}";
+ }
+}
+ [(set (attr "type")
+ (cond [(and (and (ne (symbol_ref "TARGET_DOUBLE_WITH_ADD")
+ (const_int 0))
+ (match_operand 0 "register_operand" ""))
+ (match_operand 1 "const1_operand" ""))
+ (const_string "alu")
+ ]
+ (const_string "ishift1")))
+ (set (attr "length_immediate")
+ (if_then_else
+ (ior (eq_attr "type" "alu")
+ (and (eq_attr "type" "ishift1")
+ (and (match_operand 1 "const1_operand" "")
+ (ne (symbol_ref "TARGET_SHIFT1 || optimize_function_for_size_p (cfun)")
+ (const_int 0)))))
+ (const_string "0")
+ (const_string "*")))
+ (set_attr "mode" "QI")])
+
;; Convert lea to the lea pattern to avoid flags dependency.
(define_split
[(set (match_operand:DI 0 "register_operand" "")
"shrd{l}\t{%s2%1, %0|%0, %1, %2}"
[(set_attr "type" "ishift")
(set_attr "prefix_0f" "1")
+ (set_attr "mode" "SI")
(set_attr "pent_pair" "np")
- (set_attr "mode" "SI")])
+ (set_attr "athlon_decode" "vector")
+ (set_attr "amdfam10_decode" "vector")])
(define_insn "ashrdi3_cvt"
[(set (match_operand:DI 0 "nonimmediate_operand" "=*d,rm")
DONE;
})
-(define_insn "*btdi_rex64"
- [(set (reg:CCC FLAGS_REG)
- (compare:CCC
- (zero_extract:DI
- (match_operand:DI 0 "register_operand" "r")
- (const_int 1)
- (match_operand:DI 1 "nonmemory_operand" "rN"))
- (const_int 0)))]
- "TARGET_64BIT && (TARGET_USE_BT || optimize_function_for_size_p (cfun))"
- "bt{q}\t{%1, %0|%0, %1}"
- [(set_attr "type" "alu1")
- (set_attr "prefix_0f" "1")
- (set_attr "mode" "DI")])
-
-(define_insn "*btsi"
+(define_insn "*bt<mode>"
[(set (reg:CCC FLAGS_REG)
(compare:CCC
- (zero_extract:SI
- (match_operand:SI 0 "register_operand" "r")
+ (zero_extract:SWI48
+ (match_operand:SWI48 0 "register_operand" "r")
(const_int 1)
- (match_operand:SI 1 "nonmemory_operand" "rN"))
+ (match_operand:SWI48 1 "nonmemory_operand" "rN"))
(const_int 0)))]
"TARGET_USE_BT || optimize_function_for_size_p (cfun)"
- "bt{l}\t{%1, %0|%0, %1}"
+ "bt{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "type" "alu1")
(set_attr "prefix_0f" "1")
- (set_attr "mode" "SI")])
+ (set_attr "mode" "<MODE>")])
\f
;; Store-flag instructions.
FAIL;
})
-;; zero_extend in SImode is correct, since this is what combine pass
-;; generates from shift insn with QImode operand. Actually, the mode of
-;; operand 2 (bit offset operand) doesn't matter since bt insn takes
+;; zero_extend in SImode is correct also for DImode, since this is what combine
+;; pass generates from shift insn with QImode operand. Actually, the mode
+;; of operand 2 (bit offset operand) doesn't matter since bt insn takes
;; appropriate modulo of the bit offset value.
-(define_insn_and_split "*jcc_btdi_rex64"
+(define_insn_and_split "*jcc_bt<mode>"
[(set (pc)
(if_then_else (match_operator 0 "bt_comparison_operator"
- [(zero_extract:DI
- (match_operand:DI 1 "register_operand" "r")
+ [(zero_extract:SWI48
+ (match_operand:SWI48 1 "register_operand" "r")
(const_int 1)
(zero_extend:SI
(match_operand:QI 2 "register_operand" "r")))
(label_ref (match_operand 3 "" ""))
(pc)))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && (TARGET_USE_BT || optimize_function_for_size_p (cfun))"
+ "TARGET_USE_BT || optimize_function_for_size_p (cfun)"
"#"
"&& 1"
[(set (reg:CCC FLAGS_REG)
(compare:CCC
- (zero_extract:DI
+ (zero_extract:SWI48
(match_dup 1)
(const_int 1)
(match_dup 2))
(label_ref (match_dup 3))
(pc)))]
{
- operands[2] = simplify_gen_subreg (DImode, operands[2], QImode, 0);
+ operands[2] = simplify_gen_subreg (<MODE>mode, operands[2], QImode, 0);
PUT_CODE (operands[0], reverse_condition (GET_CODE (operands[0])));
})
-;; avoid useless masking of bit offset operand
-(define_insn_and_split "*jcc_btdi_mask_rex64"
+;; Avoid useless masking of bit offset operand. "and" in SImode is correct
+;; also for DImode, this is what combine produces.
+(define_insn_and_split "*jcc_bt<mode>_mask"
[(set (pc)
(if_then_else (match_operator 0 "bt_comparison_operator"
- [(zero_extract:DI
- (match_operand:DI 1 "register_operand" "r")
+ [(zero_extract:SWI48
+ (match_operand:SWI48 1 "register_operand" "r")
(const_int 1)
(and:SI
(match_operand:SI 2 "register_operand" "r")
(label_ref (match_operand 4 "" ""))
(pc)))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && (TARGET_USE_BT || optimize_function_for_size_p (cfun))
- && (INTVAL (operands[3]) & 0x3f) == 0x3f"
+ "(TARGET_USE_BT || optimize_function_for_size_p (cfun))
+ && (INTVAL (operands[3]) & (GET_MODE_BITSIZE (<MODE>mode)-1))
+ == GET_MODE_BITSIZE (<MODE>mode)-1"
"#"
"&& 1"
[(set (reg:CCC FLAGS_REG)
(compare:CCC
- (zero_extract:DI
+ (zero_extract:SWI48
(match_dup 1)
(const_int 1)
(match_dup 2))
(label_ref (match_dup 4))
(pc)))]
{
- operands[2] = simplify_gen_subreg (DImode, operands[2], SImode, 0);
-
- PUT_CODE (operands[0], reverse_condition (GET_CODE (operands[0])));
-})
-
-(define_insn_and_split "*jcc_btsi"
- [(set (pc)
- (if_then_else (match_operator 0 "bt_comparison_operator"
- [(zero_extract:SI
- (match_operand:SI 1 "register_operand" "r")
- (const_int 1)
- (zero_extend:SI
- (match_operand:QI 2 "register_operand" "r")))
- (const_int 0)])
- (label_ref (match_operand 3 "" ""))
- (pc)))
- (clobber (reg:CC FLAGS_REG))]
- "TARGET_USE_BT || optimize_function_for_size_p (cfun)"
- "#"
- "&& 1"
- [(set (reg:CCC FLAGS_REG)
- (compare:CCC
- (zero_extract:SI
- (match_dup 1)
- (const_int 1)
- (match_dup 2))
- (const_int 0)))
- (set (pc)
- (if_then_else (match_op_dup 0 [(reg:CCC FLAGS_REG) (const_int 0)])
- (label_ref (match_dup 3))
- (pc)))]
-{
- operands[2] = simplify_gen_subreg (SImode, operands[2], QImode, 0);
+ operands[2] = simplify_gen_subreg (<MODE>mode, operands[2], SImode, 0);
PUT_CODE (operands[0], reverse_condition (GET_CODE (operands[0])));
})
-;; avoid useless masking of bit offset operand
-(define_insn_and_split "*jcc_btsi_mask"
- [(set (pc)
- (if_then_else (match_operator 0 "bt_comparison_operator"
- [(zero_extract:SI
- (match_operand:SI 1 "register_operand" "r")
- (const_int 1)
- (and:SI
- (match_operand:SI 2 "register_operand" "r")
- (match_operand:SI 3 "const_int_operand" "n")))])
- (label_ref (match_operand 4 "" ""))
- (pc)))
- (clobber (reg:CC FLAGS_REG))]
- "(TARGET_USE_BT || optimize_function_for_size_p (cfun))
- && (INTVAL (operands[3]) & 0x1f) == 0x1f"
- "#"
- "&& 1"
- [(set (reg:CCC FLAGS_REG)
- (compare:CCC
- (zero_extract:SI
- (match_dup 1)
- (const_int 1)
- (match_dup 2))
- (const_int 0)))
- (set (pc)
- (if_then_else (match_op_dup 0 [(reg:CCC FLAGS_REG) (const_int 0)])
- (label_ref (match_dup 4))
- (pc)))]
- "PUT_CODE (operands[0], reverse_condition (GET_CODE (operands[0])));")
-
(define_insn_and_split "*jcc_btsi_1"
[(set (pc)
(if_then_else (match_operator 0 "bt_comparison_operator"
"leave"
[(set_attr "type" "leave")])
\f
-(define_expand "ffssi2"
- [(parallel
- [(set (match_operand:SI 0 "register_operand" "")
- (ffs:SI (match_operand:SI 1 "nonimmediate_operand" "")))
- (clobber (match_scratch:SI 2 ""))
- (clobber (reg:CC FLAGS_REG))])]
- ""
-{
- if (TARGET_CMOVE)
- {
- emit_insn (gen_ffs_cmove (operands[0], operands[1]));
- DONE;
- }
-})
+;; Bit manipulation instructions.
-(define_expand "ffs_cmove"
+(define_expand "ffs<mode>2"
[(set (match_dup 2) (const_int -1))
(parallel [(set (reg:CCZ FLAGS_REG)
- (compare:CCZ (match_operand:SI 1 "nonimmediate_operand" "")
- (const_int 0)))
- (set (match_operand:SI 0 "register_operand" "")
- (ctz:SI (match_dup 1)))])
- (set (match_dup 0) (if_then_else:SI
+ (compare:CCZ
+ (match_operand:SWI48 1 "nonimmediate_operand" "")
+ (const_int 0)))
+ (set (match_operand:SWI48 0 "register_operand" "")
+ (ctz:SWI48 (match_dup 1)))])
+ (set (match_dup 0) (if_then_else:SWI48
(eq (reg:CCZ FLAGS_REG) (const_int 0))
(match_dup 2)
(match_dup 0)))
- (parallel [(set (match_dup 0) (plus:SI (match_dup 0) (const_int 1)))
+ (parallel [(set (match_dup 0) (plus:SWI48 (match_dup 0) (const_int 1)))
(clobber (reg:CC FLAGS_REG))])]
- "TARGET_CMOVE"
- "operands[2] = gen_reg_rtx (SImode);")
+ ""
+{
+ if (<MODE>mode == SImode && !TARGET_CMOVE)
+ {
+ emit_insn (gen_ffssi2_no_cmove (operands[0], operands [1]));
+ DONE;
+ }
+ operands[2] = gen_reg_rtx (<MODE>mode);
+})
-(define_insn_and_split "*ffs_no_cmove"
+(define_insn_and_split "ffssi2_no_cmove"
[(set (match_operand:SI 0 "register_operand" "=r")
(ffs:SI (match_operand:SI 1 "nonimmediate_operand" "rm")))
(clobber (match_scratch:SI 2 "=&q"))
ix86_expand_clear (operands[2]);
})
-(define_insn "*ffssi_1"
+(define_insn "*ffs<mode>_1"
[(set (reg:CCZ FLAGS_REG)
- (compare:CCZ (match_operand:SI 1 "nonimmediate_operand" "rm")
+ (compare:CCZ (match_operand:SWI48 1 "nonimmediate_operand" "rm")
(const_int 0)))
- (set (match_operand:SI 0 "register_operand" "=r")
- (ctz:SI (match_dup 1)))]
+ (set (match_operand:SWI48 0 "register_operand" "=r")
+ (ctz:SWI48 (match_dup 1)))]
""
- "bsf{l}\t{%1, %0|%0, %1}"
+ "bsf{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "type" "alu1")
(set_attr "prefix_0f" "1")
- (set_attr "mode" "SI")])
-
-(define_expand "ffsdi2"
- [(set (match_dup 2) (const_int -1))
- (parallel [(set (reg:CCZ FLAGS_REG)
- (compare:CCZ (match_operand:DI 1 "nonimmediate_operand" "")
- (const_int 0)))
- (set (match_operand:DI 0 "register_operand" "")
- (ctz:DI (match_dup 1)))])
- (set (match_dup 0) (if_then_else:DI
- (eq (reg:CCZ FLAGS_REG) (const_int 0))
- (match_dup 2)
- (match_dup 0)))
- (parallel [(set (match_dup 0) (plus:DI (match_dup 0) (const_int 1)))
- (clobber (reg:CC FLAGS_REG))])]
- "TARGET_64BIT"
- "operands[2] = gen_reg_rtx (DImode);")
-
-(define_insn "*ffsdi_1"
- [(set (reg:CCZ FLAGS_REG)
- (compare:CCZ (match_operand:DI 1 "nonimmediate_operand" "rm")
- (const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
- (ctz:DI (match_dup 1)))]
- "TARGET_64BIT"
- "bsf{q}\t{%1, %0|%0, %1}"
- [(set_attr "type" "alu1")
- (set_attr "prefix_0f" "1")
- (set_attr "mode" "DI")])
+ (set_attr "mode" "<MODE>")])
-(define_insn "ctzsi2"
- [(set (match_operand:SI 0 "register_operand" "=r")
- (ctz:SI (match_operand:SI 1 "nonimmediate_operand" "rm")))
+(define_insn "ctz<mode>2"
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (ctz:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "rm")))
(clobber (reg:CC FLAGS_REG))]
""
- "bsf{l}\t{%1, %0|%0, %1}"
+ "bsf{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "type" "alu1")
(set_attr "prefix_0f" "1")
- (set_attr "mode" "SI")])
-
-(define_insn "ctzdi2"
- [(set (match_operand:DI 0 "register_operand" "=r")
- (ctz:DI (match_operand:DI 1 "nonimmediate_operand" "rm")))
- (clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT"
- "bsf{q}\t{%1, %0|%0, %1}"
- [(set_attr "type" "alu1")
- (set_attr "prefix_0f" "1")
- (set_attr "mode" "DI")])
+ (set_attr "mode" "<MODE>")])
-(define_expand "clzsi2"
+(define_expand "clz<mode>2"
[(parallel
- [(set (match_operand:SI 0 "register_operand" "")
- (minus:SI (const_int 31)
- (clz:SI (match_operand:SI 1 "nonimmediate_operand" ""))))
+ [(set (match_operand:SWI248 0 "register_operand" "")
+ (minus:SWI248
+ (match_dup 2)
+ (clz:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" ""))))
(clobber (reg:CC FLAGS_REG))])
(parallel
- [(set (match_dup 0) (xor:SI (match_dup 0) (const_int 31)))
+ [(set (match_dup 0) (xor:SWI248 (match_dup 0) (match_dup 2)))
(clobber (reg:CC FLAGS_REG))])]
""
{
if (TARGET_ABM)
{
- emit_insn (gen_clzsi2_abm (operands[0], operands[1]));
+ emit_insn (gen_clz<mode>2_abm (operands[0], operands[1]));
DONE;
}
+ operands[2] = GEN_INT (GET_MODE_BITSIZE (<MODE>mode)-1);
})
-(define_insn "clzsi2_abm"
- [(set (match_operand:SI 0 "register_operand" "=r")
- (clz:SI (match_operand:SI 1 "nonimmediate_operand" "rm")))
+(define_insn "clz<mode>2_abm"
+ [(set (match_operand:SWI248 0 "register_operand" "=r")
+ (clz:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "rm")))
(clobber (reg:CC FLAGS_REG))]
"TARGET_ABM"
- "lzcnt{l}\t{%1, %0|%0, %1}"
+ "lzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "prefix_rep" "1")
(set_attr "type" "bitmanip")
- (set_attr "mode" "SI")])
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "bsr_rex64"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (minus:DI (const_int 63)
+ (clz:DI (match_operand:DI 1 "nonimmediate_operand" "rm"))))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_64BIT"
+ "bsr{q}\t{%1, %0|%0, %1}"
+ [(set_attr "type" "alu1")
+ (set_attr "prefix_0f" "1")
+ (set_attr "mode" "DI")])
(define_insn "bsr"
[(set (match_operand:SI 0 "register_operand" "=r")
(set_attr "prefix_0f" "1")
(set_attr "mode" "SI")])
+(define_insn "*bsrhi"
+ [(set (match_operand:HI 0 "register_operand" "=r")
+ (minus:HI (const_int 15)
+ (clz:HI (match_operand:HI 1 "nonimmediate_operand" "rm"))))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+ "bsr{w}\t{%1, %0|%0, %1}"
+ [(set_attr "type" "alu1")
+ (set_attr "prefix_0f" "1")
+ (set_attr "mode" "HI")])
+
(define_insn "popcount<mode>2"
[(set (match_operand:SWI248 0 "register_operand" "=r")
(popcount:SWI248
#if TARGET_MACHO
return "popcnt\t{%1, %0|%0, %1}";
#else
- return "popcnt{<imodesuffix>}\t{%1, %0|%0, %1}";
+ return "popcnt{l}\t{%1, %0|%0, %1}";
#endif
}
[(set_attr "prefix_rep" "1")
(set_attr "type" "bitmanip")
(set_attr "mode" "SI")])
-(define_expand "bswapsi2"
- [(set (match_operand:SI 0 "register_operand" "")
- (bswap:SI (match_operand:SI 1 "register_operand" "")))]
+(define_expand "bswap<mode>2"
+ [(set (match_operand:SWI48 0 "register_operand" "")
+ (bswap:SWI48 (match_operand:SWI48 1 "register_operand" "")))]
""
{
- if (!(TARGET_BSWAP || TARGET_MOVBE))
+ if (<MODE>mode == SImode && !(TARGET_BSWAP || TARGET_MOVBE))
{
rtx x = operands[0];
}
})
-(define_insn "*bswapsi_movbe"
- [(set (match_operand:SI 0 "nonimmediate_operand" "=r,r,m")
- (bswap:SI (match_operand:SI 1 "nonimmediate_operand" "0,m,r")))]
- "TARGET_MOVBE && !(MEM_P (operands[0]) && MEM_P (operands[1]))"
+(define_insn "*bswap<mode>2_movbe"
+ [(set (match_operand:SWI48 0 "nonimmediate_operand" "=r,r,m")
+ (bswap:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "0,m,r")))]
+ "TARGET_MOVBE
+ && !(MEM_P (operands[0]) && MEM_P (operands[1]))"
"@
bswap\t%0
movbe\t{%1, %0|%0, %1}
movbe\t{%1, %0|%0, %1}"
- [(set_attr "type" "*,imov,imov")
- (set_attr "modrm" "*,1,1")
- (set_attr "prefix_0f" "1")
+ [(set_attr "type" "bitmanip,imov,imov")
+ (set_attr "modrm" "0,1,1")
+ (set_attr "prefix_0f" "*,1,1")
(set_attr "prefix_extra" "*,1,1")
- (set_attr "length" "2,*,*")
- (set_attr "mode" "SI")])
+ (set_attr "mode" "<MODE>")])
-(define_insn "*bswapsi_1"
- [(set (match_operand:SI 0 "register_operand" "=r")
- (bswap:SI (match_operand:SI 1 "register_operand" "0")))]
+(define_insn "*bswap<mode>2_1"
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (bswap:SWI48 (match_operand:SWI48 1 "register_operand" "0")))]
"TARGET_BSWAP"
"bswap\t%0"
- [(set_attr "prefix_0f" "1")
- (set_attr "length" "2")])
+ [(set_attr "type" "bitmanip")
+ (set_attr "modrm" "0")
+ (set_attr "mode" "<MODE>")])
(define_insn "*bswaphi_lowpart_1"
[(set (strict_low_part (match_operand:HI 0 "register_operand" "+Q,r"))
[(set_attr "length" "4")
(set_attr "mode" "HI")])
-(define_expand "bswapdi2"
- [(set (match_operand:DI 0 "register_operand" "")
- (bswap:DI (match_operand:DI 1 "register_operand" "")))]
- "TARGET_64BIT"
- "")
-
-(define_insn "*bswapdi_movbe"
- [(set (match_operand:DI 0 "nonimmediate_operand" "=r,r,m")
- (bswap:DI (match_operand:DI 1 "nonimmediate_operand" "0,m,r")))]
- "TARGET_64BIT && TARGET_MOVBE
- && !(MEM_P (operands[0]) && MEM_P (operands[1]))"
- "@
- bswap\t%0
- movbe\t{%1, %0|%0, %1}
- movbe\t{%1, %0|%0, %1}"
- [(set_attr "type" "*,imov,imov")
- (set_attr "modrm" "*,1,1")
- (set_attr "prefix_0f" "1")
- (set_attr "prefix_extra" "*,1,1")
- (set_attr "length" "3,*,*")
- (set_attr "mode" "DI")])
-
-(define_insn "*bswapdi_1"
- [(set (match_operand:DI 0 "register_operand" "=r")
- (bswap:DI (match_operand:DI 1 "register_operand" "0")))]
- "TARGET_64BIT"
- "bswap\t%0"
- [(set_attr "prefix_0f" "1")
- (set_attr "length" "3")])
-
-(define_expand "clzdi2"
- [(parallel
- [(set (match_operand:DI 0 "register_operand" "")
- (minus:DI (const_int 63)
- (clz:DI (match_operand:DI 1 "nonimmediate_operand" ""))))
- (clobber (reg:CC FLAGS_REG))])
- (parallel
- [(set (match_dup 0) (xor:DI (match_dup 0) (const_int 63)))
- (clobber (reg:CC FLAGS_REG))])]
- "TARGET_64BIT"
-{
- if (TARGET_ABM)
- {
- emit_insn (gen_clzdi2_abm (operands[0], operands[1]));
- DONE;
- }
-})
-
-(define_insn "clzdi2_abm"
- [(set (match_operand:DI 0 "register_operand" "=r")
- (clz:DI (match_operand:DI 1 "nonimmediate_operand" "rm")))
- (clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && TARGET_ABM"
- "lzcnt{q}\t{%1, %0|%0, %1}"
- [(set_attr "prefix_rep" "1")
- (set_attr "type" "bitmanip")
- (set_attr "mode" "DI")])
-
-(define_insn "bsr_rex64"
- [(set (match_operand:DI 0 "register_operand" "=r")
- (minus:DI (const_int 63)
- (clz:DI (match_operand:DI 1 "nonimmediate_operand" "rm"))))
- (clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT"
- "bsr{q}\t{%1, %0|%0, %1}"
- [(set_attr "type" "alu1")
- (set_attr "prefix_0f" "1")
- (set_attr "mode" "DI")])
-
-(define_expand "clzhi2"
- [(parallel
- [(set (match_operand:HI 0 "register_operand" "")
- (minus:HI (const_int 15)
- (clz:HI (match_operand:HI 1 "nonimmediate_operand" ""))))
- (clobber (reg:CC FLAGS_REG))])
- (parallel
- [(set (match_dup 0) (xor:HI (match_dup 0) (const_int 15)))
- (clobber (reg:CC FLAGS_REG))])]
- ""
-{
- if (TARGET_ABM)
- {
- emit_insn (gen_clzhi2_abm (operands[0], operands[1]));
- DONE;
- }
-})
-
-(define_insn "clzhi2_abm"
- [(set (match_operand:HI 0 "register_operand" "=r")
- (clz:HI (match_operand:HI 1 "nonimmediate_operand" "rm")))
- (clobber (reg:CC FLAGS_REG))]
- "TARGET_ABM"
- "lzcnt{w}\t{%1, %0|%0, %1}"
- [(set_attr "prefix_rep" "1")
- (set_attr "type" "bitmanip")
- (set_attr "mode" "HI")])
-
-(define_insn "*bsrhi"
- [(set (match_operand:HI 0 "register_operand" "=r")
- (minus:HI (const_int 15)
- (clz:HI (match_operand:HI 1 "nonimmediate_operand" "rm"))))
- (clobber (reg:CC FLAGS_REG))]
- ""
- "bsr{w}\t{%1, %0|%0, %1}"
- [(set_attr "type" "alu1")
- (set_attr "prefix_0f" "1")
- (set_attr "mode" "HI")])
-
(define_expand "paritydi2"
[(set (match_operand:DI 0 "register_operand" "")
(parity:DI (match_operand:DI 1 "register_operand" "")))]
DONE;
})
+(define_expand "paritysi2"
+ [(set (match_operand:SI 0 "register_operand" "")
+ (parity:SI (match_operand:SI 1 "register_operand" "")))]
+ "! TARGET_POPCNT"
+{
+ rtx scratch = gen_reg_rtx (QImode);
+ rtx cond;
+
+ emit_insn (gen_paritysi2_cmp (NULL_RTX, NULL_RTX, operands[1]));
+
+ cond = gen_rtx_fmt_ee (ORDERED, QImode,
+ gen_rtx_REG (CCmode, FLAGS_REG),
+ const0_rtx);
+ emit_insn (gen_rtx_SET (VOIDmode, scratch, cond));
+
+ emit_insn (gen_zero_extendqisi2 (operands[0], scratch));
+ DONE;
+})
+
(define_insn_and_split "paritydi2_cmp"
[(set (reg:CC FLAGS_REG)
(parity:CC (match_operand:DI 3 "register_operand" "0")))
operands[1] = gen_highpart (SImode, operands[3]);
})
-(define_expand "paritysi2"
- [(set (match_operand:SI 0 "register_operand" "")
- (parity:SI (match_operand:SI 1 "register_operand" "")))]
- "! TARGET_POPCNT"
-{
- rtx scratch = gen_reg_rtx (QImode);
- rtx cond;
-
- emit_insn (gen_paritysi2_cmp (NULL_RTX, NULL_RTX, operands[1]));
-
- cond = gen_rtx_fmt_ee (ORDERED, QImode,
- gen_rtx_REG (CCmode, FLAGS_REG),
- const0_rtx);
- emit_insn (gen_rtx_SET (VOIDmode, scratch, cond));
-
- emit_insn (gen_zero_extendqisi2 (operands[0], scratch));
- DONE;
-})
-
(define_insn_and_split "paritysi2_cmp"
[(set (reg:CC FLAGS_REG)
(parity:CC (match_operand:SI 2 "register_operand" "0")))
(match_operand:MODEF 1 "nonimmediate_operand" "%x")
(match_operand:MODEF 2 "nonimmediate_operand" "xm")))]
"AVX_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH"
- "v<maxminfprefix>s<ssemodefsuffix>\t{%2, %1, %0|%0, %1, %2}"
+ "v<maxmin_float>s<ssemodefsuffix>\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "type" "sseadd")
(set_attr "prefix" "vex")
(set_attr "mode" "<MODE>")])
(match_operand:MODEF 1 "nonimmediate_operand" "%0")
(match_operand:MODEF 2 "nonimmediate_operand" "xm")))]
"SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH"
- "<maxminfprefix>s<ssemodefsuffix>\t{%2, %0|%0, %2}"
+ "<maxmin_float>s<ssemodefsuffix>\t{%2, %0|%0, %2}"
[(set_attr "type" "sseadd")
(set_attr "mode" "<MODE>")])
(reg:DI XMM5_REG)
(reg:DI XMM6_REG)
(reg:DI XMM7_REG)] UNSPEC_SSE_PROLOGUE_SAVE))
- (use (match_operand:DI 1 "register_operand" ""))
+ (clobber (match_operand:DI 1 "register_operand" ""))
(use (match_operand:DI 2 "immediate_operand" ""))
- (use (label_ref:DI (match_operand 3 "" "")))])]
+ (use (label_ref:DI (match_operand 3 "" "")))
+ (clobber (match_operand:DI 4 "register_operand" ""))
+ (use (match_dup 1))])]
"TARGET_64BIT"
"")
-(define_insn "*sse_prologue_save_insn"
+;; Pre-reload version of prologue save. Until after prologue generation we don't know
+;; what the size of save instruction will be.
+;; Operand 0+operand 6 is the memory save area
+;; Operand 1 is number of registers to save (will get overwritten to operand 5)
+;; Operand 2 is number of non-vaargs SSE arguments
+;; Operand 3 is label starting the save block
+;; Operand 4 is used for temporary computation of jump address
+(define_insn "*sse_prologue_save_insn1"
[(set (mem:BLK (plus:DI (match_operand:DI 0 "register_operand" "R")
- (match_operand:DI 4 "const_int_operand" "n")))
+ (match_operand:DI 6 "const_int_operand" "n")))
(unspec:BLK [(reg:DI XMM0_REG)
(reg:DI XMM1_REG)
(reg:DI XMM2_REG)
(reg:DI XMM5_REG)
(reg:DI XMM6_REG)
(reg:DI XMM7_REG)] UNSPEC_SSE_PROLOGUE_SAVE))
+ (clobber (match_operand:DI 1 "register_operand" "=r"))
+ (use (match_operand:DI 2 "const_int_operand" "i"))
+ (use (label_ref:DI (match_operand 3 "" "X")))
+ (clobber (match_operand:DI 4 "register_operand" "=&r"))
+ (use (match_operand:DI 5 "register_operand" "1"))]
+ "TARGET_64BIT
+ && INTVAL (operands[6]) + X86_64_SSE_REGPARM_MAX * 16 - 16 < 128
+ && INTVAL (operands[6]) + INTVAL (operands[2]) * 16 >= -128"
+ "#"
+ [(set_attr "type" "other")
+ (set_attr "memory" "store")
+ (set_attr "mode" "DI")])
+
+;; We know size of save instruction; expand the computation of jump address
+;; in the jumptable.
+(define_split
+ [(parallel [(set (match_operand:BLK 0 "" "")
+ (unspec:BLK [(reg:DI XMM0_REG)
+ (reg:DI XMM1_REG)
+ (reg:DI XMM2_REG)
+ (reg:DI XMM3_REG)
+ (reg:DI XMM4_REG)
+ (reg:DI XMM5_REG)
+ (reg:DI XMM6_REG)
+ (reg:DI XMM7_REG)] UNSPEC_SSE_PROLOGUE_SAVE))
+ (clobber (match_operand:DI 1 "register_operand" ""))
+ (use (match_operand:DI 2 "const_int_operand" ""))
+ (use (match_operand 3 "" ""))
+ (clobber (match_operand:DI 4 "register_operand" ""))
+ (use (match_operand:DI 5 "register_operand" ""))])]
+ "reload_completed"
+ [(parallel [(set (match_dup 0)
+ (unspec:BLK [(reg:DI XMM0_REG)
+ (reg:DI XMM1_REG)
+ (reg:DI XMM2_REG)
+ (reg:DI XMM3_REG)
+ (reg:DI XMM4_REG)
+ (reg:DI XMM5_REG)
+ (reg:DI XMM6_REG)
+ (reg:DI XMM7_REG)] UNSPEC_SSE_PROLOGUE_SAVE_LOW))
+ (use (match_dup 1))
+ (use (match_dup 2))
+ (use (match_dup 3))
+ (use (match_dup 5))])]
+{
+ /* Movaps is 4 bytes, AVX and movsd is 5 bytes. */
+ int size = 4 + (TARGET_AVX || crtl->stack_alignment_needed < 128);
+
+ /* Compute address to jump to:
+ label - eax*size + nnamed_sse_arguments*size. */
+ if (size == 5)
+ emit_insn (gen_rtx_SET (VOIDmode, operands[4],
+ gen_rtx_PLUS
+ (Pmode,
+ gen_rtx_MULT (Pmode, operands[1],
+ GEN_INT (4)),
+ operands[1])));
+ else if (size == 4)
+ emit_insn (gen_rtx_SET (VOIDmode, operands[4],
+ gen_rtx_MULT (Pmode, operands[1],
+ GEN_INT (4))));
+ else
+ gcc_unreachable ();
+ if (INTVAL (operands[2]))
+ emit_move_insn
+ (operands[1],
+ gen_rtx_CONST (DImode,
+ gen_rtx_PLUS (DImode,
+ operands[3],
+ GEN_INT (INTVAL (operands[2])
+ * size))));
+ else
+ emit_move_insn (operands[1], operands[3]);
+ emit_insn (gen_subdi3 (operands[1], operands[1], operands[4]));
+ operands[5] = GEN_INT (size);
+})
+
+(define_insn "sse_prologue_save_insn"
+ [(set (mem:BLK (plus:DI (match_operand:DI 0 "register_operand" "R")
+ (match_operand:DI 4 "const_int_operand" "n")))
+ (unspec:BLK [(reg:DI XMM0_REG)
+ (reg:DI XMM1_REG)
+ (reg:DI XMM2_REG)
+ (reg:DI XMM3_REG)
+ (reg:DI XMM4_REG)
+ (reg:DI XMM5_REG)
+ (reg:DI XMM6_REG)
+ (reg:DI XMM7_REG)] UNSPEC_SSE_PROLOGUE_SAVE_LOW))
(use (match_operand:DI 1 "register_operand" "r"))
(use (match_operand:DI 2 "const_int_operand" "i"))
- (use (label_ref:DI (match_operand 3 "" "X")))]
+ (use (label_ref:DI (match_operand 3 "" "X")))
+ (use (match_operand:DI 5 "const_int_operand" "i"))]
"TARGET_64BIT
&& INTVAL (operands[4]) + X86_64_SSE_REGPARM_MAX * 16 - 16 < 128
&& INTVAL (operands[4]) + INTVAL (operands[2]) * 16 >= -128"
PUT_MODE (operands[4], TImode);
if (GET_CODE (XEXP (operands[0], 0)) != PLUS)
output_asm_insn ("rex", operands);
- output_asm_insn ("%vmovaps\t{%5, %4|%4, %5}", operands);
+ if (crtl->stack_alignment_needed < 128)
+ output_asm_insn ("%vmovsd\t{%5, %4|%4, %5}", operands);
+ else
+ output_asm_insn ("%vmovaps\t{%5, %4|%4, %5}", operands);
}
(*targetm.asm_out.internal_label) (asm_out_file, "L",
CODE_LABEL_NUMBER (operands[3]));
[(set_attr "type" "other")
(set_attr "length_immediate" "0")
(set_attr "length_address" "0")
+ ;; 2 bytes for jump and opernds[4] bytes for each save.
(set (attr "length")
- (if_then_else
- (eq (symbol_ref "TARGET_AVX") (const_int 0))
- (const_string "34")
- (const_string "42")))
+ (plus (const_int 2)
+ (mult (symbol_ref ("INTVAL (operands[5])"))
+ (symbol_ref ("X86_64_SSE_REGPARM_MAX - INTVAL (operands[2])")))))
(set_attr "memory" "store")
(set_attr "modrm" "0")
(set_attr "prefix" "maybe_vex")