+2011-08-25 Uros Bizjak <ubizjak@gmail.com>
+
+ * config/i386/i386.md (isa): Add sse2, sse2_noavx, sse3,
+ sse4 and sse4_noavx.
+ (enabled): Handle sse2, sse2_noavx, sse3, sse4 and sse4_noavx.
+ (*pushdf_rex64): Change Y2 register constraint to x.
+ (*movdf_internal_rex64): Ditto.
+ (*zero_extendsidi2_rex64): Ditto.
+ (*movdi_internal): Change Y2 register constraint to x
+ and update "isa" attribute.
+ (*pushdf): Ditto.
+ (*movdf internal): Ditto.
+ (zero_extendsidi2_1): Ditto.
+ (*truncdfdf_mixed): Ditto.
+ (*truncxfdf2_mixed): Ditto.
+ * config/i386/mmx.md (*mov<mode>_internal_rex64): Change Y2
+ register constraint to x.
+ (*movv2sf_internal_rex64): Ditto.
+ (*mov<mode>_internal): Change Y2 register constraint to x
+ and add "isa" attribute.
+ (*movv2sf_internal): Ditto.
+ (*vec_extractv2si_1): Ditto.
+ * config/i386/sse.md ("vec_set<mode>_0): Change Y2 and Y4 register
+ constraints to x and update "isa" attribute.
+ (*vec_interleave_highv2df): Change Y3 registerconstraint
+ to x and update "isa" attribute.
+ (*vec_interleave_lowv2df): Ditto.
+ (*vec_concatv2df): Change Y2 register constraint to x and
+ update "isa" attribute.
+ (sse2_loadld): Ditto.
+ (*vec_extractv2di_1): Ditto.
+ (*vec_dupv4si): Ditto.
+ (*vec_dupv2di): Ditto.
+ (*vec_concatv4si): Ditto.
+ (vec_concatv2di): Ditto.
+ * config/i386/constraints.md (Y2): Remove.
+ (Y3): Ditto.
+ (Y4): Ditto.
+
2011-08-25 Bernd Schmidt <bernds@codesourcery.com>
* regrename.c (scan_rtx_reg, scan_rtx_address, build_def_use,
* config/avr/avr.c (reg_class_tab): Make local to
avr_regno_reg_class. Return smallest register class available.
-
+
2011-08-25 Georg-Johann Lay <avr@gjlay.de>
* config/avr/avr.c (STR_PREFIX_P): New Define.
(gen_automata_option): Check for COLLAPSE_OPTION.
(collapse_ndfa_insn_decl): New static variable.
(add_collapse_ndfa_insn_decl, special_decl_p): New functions.
- (find_arc): If insn is the collapse-ndfa insn, accept any arc we
- find.
+ (find_arc): If insn is the collapse-ndfa insn, accept any arc we find.
(transform_insn_regexps): Call add_collapse_ndfa_insn_decl if
necessary. Use normal_decls_num rather than decls_num, remove
test for special decls.
- (create_alt_states, form_ainsn_with_same_reservs): Use
- special_decl_p.
+ (create_alt_states, form_ainsn_with_same_reservs): Use special_decl_p.
(make_automaton); Likewise. Use the new advance_cycle_insn member
of struct automaton.
(create_composed_state): Disallow advance-cycle arcs if collapse_flag
2011-08-24 H.J. Lu <hongjiu.lu@intel.com>
PR target/50172
- * config/i386/i386.c (ix86_expand_builtin): Convert to Pmode if
- needed.
+ * config/i386/i386.c (ix86_expand_builtin): Convert to Pmode if needed.
2011-08-24 Richard Guenther <rguenther@suse.de>
;; We use the Y prefix to denote any number of conditional register sets:
;; z First SSE register.
-;; 2 SSE2 enabled
-;; 3 SSE3 enabled
-;; 4 SSE4_1 enabled
;; i SSE2 inter-unit moves enabled
;; m MMX inter-unit moves enabled
;; p Integer register when TARGET_PARTIAL_REG_STALL is disabled
(define_register_constraint "Yz" "TARGET_SSE ? SSE_FIRST_REG : NO_REGS"
"First SSE register (@code{%xmm0}).")
-(define_register_constraint "Y2" "TARGET_SSE2 ? SSE_REGS : NO_REGS"
- "@internal Any SSE register, when SSE2 is enabled.")
-
-(define_register_constraint "Y3" "TARGET_SSE3 ? SSE_REGS : NO_REGS"
- "@internal Any SSE register, when SSE3 is enabled.")
-
-(define_register_constraint "Y4" "TARGET_SSE4_1 ? SSE_REGS : NO_REGS"
- "@internal Any SSE register, when SSE4_1 is enabled.")
-
(define_register_constraint "Yi"
"TARGET_SSE2 && TARGET_INTER_UNIT_MOVES ? SSE_REGS : NO_REGS"
"@internal Any SSE register, when SSE2 and inter-unit moves are enabled.")
(define_attr "movu" "0,1" (const_string "0"))
;; Used to control the "enabled" attribute on a per-instruction basis.
-(define_attr "isa" "base,noavx,avx,bmi2"
+(define_attr "isa" "base,sse2,sse2_noavx,sse3,sse4,sse4_noavx,noavx,avx,bmi2"
(const_string "base"))
(define_attr "enabled" ""
- (cond [(eq_attr "isa" "noavx") (symbol_ref "!TARGET_AVX")
+ (cond [(eq_attr "isa" "sse2") (symbol_ref "TARGET_SSE2")
+ (eq_attr "isa" "sse2_noavx")
+ (symbol_ref "TARGET_SSE2 && !TARGET_AVX")
+ (eq_attr "isa" "sse3") (symbol_ref "TARGET_SSE3")
+ (eq_attr "isa" "sse4") (symbol_ref "TARGET_SSE4_1")
+ (eq_attr "isa" "sse4_noavx")
+ (symbol_ref "TARGET_SSE4_1 && !TARGET_AVX")
(eq_attr "isa" "avx") (symbol_ref "TARGET_AVX")
+ (eq_attr "isa" "noavx") (symbol_ref "!TARGET_AVX")
(eq_attr "isa" "bmi2") (symbol_ref "TARGET_BMI2")
]
(const_int 1)))
(define_insn "*movdi_internal"
[(set (match_operand:DI 0 "nonimmediate_operand"
- "=r ,o ,*y,m*y,*y,*Y2,m ,*Y2,*Y2,*x,m ,*x,*x,?*Y2,?*Ym")
+ "=r ,o ,*y,m*y,*y,*x,m ,*x,*x,*x,m ,*x,*x,?*x,?*Ym")
(match_operand:DI 1 "general_operand"
- "riFo,riF,C ,*y ,m ,C ,*Y2,*Y2,m ,C ,*x,*x,m ,*Ym ,*Y2"))]
+ "riFo,riF,C ,*y ,m ,C ,*x,*x,m ,C ,*x,*x,m ,*Ym,*x"))]
"!TARGET_64BIT && !(MEM_P (operands[0]) && MEM_P (operands[1]))"
{
switch (get_attr_type (insn))
}
}
[(set (attr "isa")
- (if_then_else (eq_attr "alternative" "9,10,11,12")
- (const_string "noavx")
- (const_string "*")))
+ (cond [(eq_attr "alternative" "5,6,7,8,13,14")
+ (const_string "sse2")
+ (eq_attr "alternative" "9,10,11,12")
+ (const_string "noavx")
+ ]
+ (const_string "*")))
(set (attr "type")
(cond [(eq_attr "alternative" "0,1")
(const_string "multi")
(define_insn "*pushdf_rex64"
[(set (match_operand:DF 0 "push_operand" "=<,<,<")
- (match_operand:DF 1 "general_no_elim_operand" "f,Yd*rFm,Y2"))]
+ (match_operand:DF 1 "general_no_elim_operand" "f,Yd*rFm,x"))]
"TARGET_64BIT"
{
/* This insn should be already split before reg-stack. */
(define_insn "*pushdf"
[(set (match_operand:DF 0 "push_operand" "=<,<,<")
- (match_operand:DF 1 "general_no_elim_operand" "f,Yd*rFo,Y2"))]
+ (match_operand:DF 1 "general_no_elim_operand" "f,Yd*rFo,x"))]
"!TARGET_64BIT"
{
/* This insn should be already split before reg-stack. */
gcc_unreachable ();
}
- [(set_attr "type" "multi")
+ [(set_attr "isa" "*,*,sse2")
+ (set_attr "type" "multi")
(set_attr "unit" "i387,*,*")
(set_attr "mode" "DF,DI,DF")])
(define_insn "*movdf_internal_rex64"
[(set (match_operand:DF 0 "nonimmediate_operand"
- "=f,m,f,?r,?m,?r,!o,Y2*x,Y2*x,Y2*x,m ,Yi,r ")
+ "=f,m,f,?r,?m,?r,!o,x,x,x,m,Yi,r ")
(match_operand:DF 1 "general_operand"
- "fm,f,G,rm,r ,F ,F ,C ,Y2*x,m ,Y2*x,r ,Yi"))]
+ "fm,f,G,rm,r ,F ,F ,C,x,m,x,r ,Yi"))]
"TARGET_64BIT && !(MEM_P (operands[0]) && MEM_P (operands[1]))
&& (!can_create_pseudo_p ()
|| (ix86_cmodel == CM_MEDIUM || ix86_cmodel == CM_LARGE)
;; Possible store forwarding (partial memory) stall in alternative 4.
(define_insn "*movdf_internal"
[(set (match_operand:DF 0 "nonimmediate_operand"
- "=f,m,f,?Yd*r ,!o ,Y2*x,Y2*x,Y2*x,m ")
+ "=f,m,f,?Yd*r ,!o ,x,x,x,m,*x,*x,*x,m")
(match_operand:DF 1 "general_operand"
- "fm,f,G,Yd*roF,FYd*r,C ,Y2*x,m ,Y2*x"))]
+ "fm,f,G,Yd*roF,FYd*r,C,x,m,x,C ,*x,m ,*x"))]
"!TARGET_64BIT && !(MEM_P (operands[0]) && MEM_P (operands[1]))
&& (!can_create_pseudo_p ()
|| (ix86_cmodel == CM_MEDIUM || ix86_cmodel == CM_LARGE)
return "#";
case 5:
+ case 9:
return standard_sse_constant_opcode (insn, operands[1]);
case 6:
case 7:
case 8:
+ case 10:
+ case 11:
+ case 12:
switch (get_attr_mode (insn))
{
case MODE_V2DF:
gcc_unreachable ();
}
}
- [(set_attr "type" "fmov,fmov,fmov,multi,multi,sselog1,ssemov,ssemov,ssemov")
+ [(set (attr "isa")
+ (if_then_else (eq_attr "alternative" "5,6,7,8")
+ (const_string "sse2")
+ (const_string "*")))
+ (set_attr "type" "fmov,fmov,fmov,multi,multi,sselog1,ssemov,ssemov,ssemov,sselog1,ssemov,ssemov,ssemov")
(set (attr "prefix")
(if_then_else (eq_attr "alternative" "0,1,2,3,4")
(const_string "orig")
/* For SSE1, we have many fewer alternatives. */
(eq (symbol_ref "TARGET_SSE2") (const_int 0))
(if_then_else
- (eq_attr "alternative" "5,6")
+ (eq_attr "alternative" "5,6,9,10")
(const_string "V4SF")
(const_string "V2SF"))
/* xorps is one byte shorter. */
- (eq_attr "alternative" "5")
+ (eq_attr "alternative" "5,9")
(cond [(ne (symbol_ref "optimize_function_for_size_p (cfun)")
(const_int 0))
(const_string "V4SF")
chains, otherwise use short move to avoid extra work.
movaps encodes one byte shorter. */
- (eq_attr "alternative" "6")
+ (eq_attr "alternative" "6,10")
(cond
[(ne (symbol_ref "optimize_function_for_size_p (cfun)")
(const_int 0))
/* For architectures resolving dependencies on register
parts we may avoid extra work to zero out upper part
of register. */
- (eq_attr "alternative" "7")
+ (eq_attr "alternative" "7,11")
(if_then_else
(ne (symbol_ref "TARGET_SSE_SPLIT_REGS")
(const_int 0))
})
(define_insn "*zero_extendsidi2_rex64"
- [(set (match_operand:DI 0 "nonimmediate_operand" "=r,o,?*Ym,?*y,?*Yi,*Y2")
+ [(set (match_operand:DI 0 "nonimmediate_operand" "=r,o,?*Ym,?*y,?*Yi,*x")
(zero_extend:DI
(match_operand:SI 1 "nonimmediate_operand" "rm,0,r ,m ,r ,m")))]
"TARGET_64BIT"
;; %%% Kill me once multi-word ops are sane.
(define_insn "zero_extendsidi2_1"
- [(set (match_operand:DI 0 "nonimmediate_operand" "=r,?r,?o,?*Ym,?*y,?*Yi,*Y2")
+ [(set (match_operand:DI 0 "nonimmediate_operand" "=r,?r,?o,?*Ym,?*y,?*Yi,*x")
(zero_extend:DI
(match_operand:SI 1 "nonimmediate_operand" "0,rm,r ,r ,m ,r ,m")))
(clobber (reg:CC FLAGS_REG))]
movd\t{%1, %0|%0, %1}
%vmovd\t{%1, %0|%0, %1}
%vmovd\t{%1, %0|%0, %1}"
- [(set_attr "type" "multi,multi,multi,mmxmov,mmxmov,ssemov,ssemov")
+ [(set_attr "isa" "*,*,*,*,*,*,sse2")
+ (set_attr "type" "multi,multi,multi,mmxmov,mmxmov,ssemov,ssemov")
(set_attr "prefix" "*,*,*,orig,orig,maybe_vex,maybe_vex")
(set_attr "mode" "SI,SI,SI,DI,DI,TI,TI")])
(set_attr "mode" "SF")])
(define_insn "*truncdfsf_mixed"
- [(set (match_operand:SF 0 "nonimmediate_operand" "=m,Y2 ,?f,?x,?*r")
+ [(set (match_operand:SF 0 "nonimmediate_operand" "=m,x ,?f,?x,?*r")
(float_truncate:SF
- (match_operand:DF 1 "nonimmediate_operand" "f ,Y2m,f ,f ,f")))
- (clobber (match_operand:SF 2 "memory_operand" "=X,X ,m ,m ,m"))]
+ (match_operand:DF 1 "nonimmediate_operand" "f ,xm,f ,f ,f")))
+ (clobber (match_operand:SF 2 "memory_operand" "=X,X ,m ,m ,m"))]
"TARGET_MIX_SSE_I387"
{
switch (which_alternative)
return "#";
}
}
- [(set_attr "type" "fmov,ssecvt,multi,multi,multi")
+ [(set_attr "isa" "*,sse2,*,*,*")
+ (set_attr "type" "fmov,ssecvt,multi,multi,multi")
(set_attr "unit" "*,*,i387,i387,i387")
(set_attr "prefix" "orig,maybe_vex,orig,orig,orig")
(set_attr "mode" "SF")])
(set_attr "mode" "SF")])
(define_insn "*truncxfdf2_mixed"
- [(set (match_operand:DF 0 "nonimmediate_operand" "=m,?f,?Y2,?*r")
+ [(set (match_operand:DF 0 "nonimmediate_operand" "=m,?f,?x,?*r")
(float_truncate:DF
(match_operand:XF 1 "register_operand" "f ,f ,f ,f")))
(clobber (match_operand:DF 2 "memory_operand" "=X,m ,m ,m"))]
gcc_assert (!which_alternative);
return output_387_reg_move (insn, operands);
}
- [(set_attr "type" "fmov,multi,multi,multi")
+ [(set_attr "isa" "*,*,sse2,*")
+ (set_attr "type" "fmov,multi,multi,multi")
(set_attr "unit" "*,i387,i387,i387")
(set_attr "mode" "DF")])
;; Avoid vector decoded forms of the instruction.
(define_peephole2
- [(match_scratch:DF 2 "Y2")
+ [(match_scratch:DF 2 "x")
(set (match_operand:SWI48x 0 "register_operand" "")
(fix:SWI48x (match_operand:DF 1 "memory_operand" "")))]
- "TARGET_AVOID_VECTOR_DECODE && optimize_insn_for_speed_p ()"
+ "TARGET_SSE2 && TARGET_AVOID_VECTOR_DECODE && optimize_insn_for_speed_p ()"
[(set (match_dup 2) (match_dup 1))
(set (match_dup 0) (fix:SWI48x (match_dup 2)))])
;; movd instead of movq is required to handle broken assemblers.
(define_insn "*mov<mode>_internal_rex64"
[(set (match_operand:MMXMODEI8 0 "nonimmediate_operand"
- "=rm,r,!?y,!y,!?y,m ,!y ,*Y2,x,x ,m,r ,Yi")
+ "=rm,r,!?y,!y,!?y,m ,!y ,*x,x,x ,m,r ,Yi")
(match_operand:MMXMODEI8 1 "vector_move_operand"
- "Cr ,m,C ,!y,m ,!?y,*Y2,!y ,C,xm,x,Yi,r"))]
+ "Cr ,m,C ,!y,m ,!?y,*x,!y ,C,xm,x,Yi,r"))]
"TARGET_64BIT && TARGET_MMX
&& !(MEM_P (operands[0]) && MEM_P (operands[1]))"
"@
(define_insn "*mov<mode>_internal"
[(set (match_operand:MMXMODEI8 0 "nonimmediate_operand"
- "=!?y,!y,!?y,m ,!y ,*Y2,*Y2,*Y2 ,m ,*x,*x,*x,m ,r ,m")
+ "=!?y,!y,!?y,m ,!y,*x,*x,*x ,m ,*x,*x,*x,m ,r ,m")
(match_operand:MMXMODEI8 1 "vector_move_operand"
- "C ,!y,m ,!?y,*Y2,!y ,C ,*Y2m,*Y2,C ,*x,m ,*x,irm,r"))]
+ "C ,!y,m ,!?y,*x,!y,C ,*xm,*x,C ,*x,m ,*x,irm,r"))]
"!TARGET_64BIT && TARGET_MMX
&& !(MEM_P (operands[0]) && MEM_P (operands[1]))"
"@
#
#"
[(set (attr "isa")
- (if_then_else (eq_attr "alternative" "9,10,11,12")
- (const_string "noavx")
- (const_string "*")))
+ (cond [(eq_attr "alternative" "4,5,6,7,8")
+ (const_string "sse2")
+ (eq_attr "alternative" "9,10,11,12")
+ (const_string "noavx")
+ ]
+ (const_string "*")))
(set (attr "type")
(cond [(eq_attr "alternative" "0")
(const_string "mmx")
;; movd instead of movq is required to handle broken assemblers.
(define_insn "*movv2sf_internal_rex64"
[(set (match_operand:V2SF 0 "nonimmediate_operand"
- "=rm,r,!?y,!y,!?y,m ,!y ,*Y2,x,x,x,m,r ,Yi")
+ "=rm,r,!?y,!y,!?y,m ,!y,*x,x,x,x,m,r ,Yi")
(match_operand:V2SF 1 "vector_move_operand"
- "Cr ,m,C ,!y,m ,!?y,*Y2,!y ,C,x,m,x,Yi,r"))]
+ "Cr ,m,C ,!y,m ,!?y,*x,!y,C,x,m,x,Yi,r"))]
"TARGET_64BIT && TARGET_MMX
&& !(MEM_P (operands[0]) && MEM_P (operands[1]))"
"@
(define_insn "*movv2sf_internal"
[(set (match_operand:V2SF 0 "nonimmediate_operand"
- "=!?y,!y,!?y,m ,!y ,*Y2,*x,*x,*x,m ,r ,m")
+ "=!?y,!y,!?y,m ,!y,*x,*x,*x,*x,m ,r ,m")
(match_operand:V2SF 1 "vector_move_operand"
- "C ,!y,m ,!?y,*Y2,!y ,C ,*x,m ,*x,irm,r"))]
+ "C ,!y,m ,!?y,*x,!y,C ,*x,m ,*x,irm,r"))]
"!TARGET_64BIT && TARGET_MMX
&& !(MEM_P (operands[0]) && MEM_P (operands[1]))"
"@
%vmovlps\t{%1, %0|%0, %1}
#
#"
- [(set (attr "type")
+ [(set (attr "isa")
+ (if_then_else (eq_attr "alternative" "4,5")
+ (const_string "sse2")
+ (const_string "*")))
+ (set (attr "type")
(cond [(eq_attr "alternative" "0")
(const_string "mmx")
(eq_attr "alternative" "1,2,3")
;; Avoid combining registers from different units in a single alternative,
;; see comment above inline_secondary_memory_needed function in i386.c
(define_insn "*vec_extractv2si_1"
- [(set (match_operand:SI 0 "nonimmediate_operand" "=y,Y2,Y2,x,y,x,r")
+ [(set (match_operand:SI 0 "nonimmediate_operand" "=y,x,x,x,y,x,r")
(vec_select:SI
- (match_operand:V2SI 1 "nonimmediate_operand" " 0,0 ,Y2,0,o,o,o")
+ (match_operand:V2SI 1 "nonimmediate_operand" " 0,0,x,0,o,o,o")
(parallel [(const_int 1)])))]
"TARGET_MMX && !(MEM_P (operands[0]) && MEM_P (operands[1]))"
"@
#
#
#"
- [(set_attr "type" "mmxcvt,sselog1,sselog1,sselog1,mmxmov,ssemov,imov")
+ [(set (attr "isa")
+ (if_then_else (eq_attr "alternative" "1,2")
+ (const_string "sse2")
+ (const_string "*")))
+ (set_attr "type" "mmxcvt,sselog1,sselog1,sselog1,mmxmov,ssemov,imov")
(set_attr "length_immediate" "*,*,1,*,*,*,*")
(set_attr "mode" "DI,TI,TI,V4SF,SI,SI,SI")])
;; see comment above inline_secondary_memory_needed function in i386.c
(define_insn "vec_set<mode>_0"
[(set (match_operand:VI4F_128 0 "nonimmediate_operand"
- "=Y4,Y2,Y2,x,x,x,Y4 ,x ,m,m ,m")
+ "=x,x,x ,x,x,x,x ,x ,m,m ,m")
(vec_merge:VI4F_128
(vec_duplicate:VI4F_128
(match_operand:<ssescalarmode> 2 "general_operand"
- " Y4,m ,*r,m,x,x,*rm,*rm,x,fF,*r"))
+ " x,m,*r,m,x,x,*rm,*rm,x,fF,*r"))
(match_operand:VI4F_128 1 "vector_move_operand"
- " C ,C ,C ,C,0,x,0 ,x ,0,0 ,0")
+ " C,C,C ,C,0,x,0 ,x ,0,0 ,0")
(const_int 1)))]
"TARGET_SSE"
"@
#
#
#"
- [(set_attr "isa" "*,*,*,noavx,noavx,avx,noavx,avx,*,*,*")
+ [(set_attr "isa" "sse4,sse2,sse2,noavx,noavx,avx,sse4_noavx,avx,*,*,*")
(set (attr "type")
(cond [(eq_attr "alternative" "0,6,7")
(const_string "sselog")
})
(define_insn "*vec_interleave_highv2df"
- [(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,x,Y3,x,x,m")
+ [(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,x,x,x,x,m")
(vec_select:V2DF
(vec_concat:V4DF
- (match_operand:V2DF 1 "nonimmediate_operand" " 0,x,o ,o,o,x")
- (match_operand:V2DF 2 "nonimmediate_operand" " x,x,1 ,0,x,0"))
+ (match_operand:V2DF 1 "nonimmediate_operand" " 0,x,o,o,o,x")
+ (match_operand:V2DF 2 "nonimmediate_operand" " x,x,1,0,x,0"))
(parallel [(const_int 1)
(const_int 3)])))]
"TARGET_SSE2 && ix86_vec_interleave_v2df_operator_ok (operands, 1)"
movlpd\t{%H1, %0|%0, %H1}
vmovlpd\t{%H1, %2, %0|%0, %2, %H1}
%vmovhpd\t{%1, %0|%0, %1}"
- [(set_attr "isa" "noavx,avx,*,noavx,avx,*")
+ [(set_attr "isa" "noavx,avx,sse3,noavx,avx,*")
(set_attr "type" "sselog,sselog,sselog,ssemov,ssemov,ssemov")
(set_attr "prefix_data16" "*,*,*,1,*,1")
(set_attr "prefix" "orig,vex,maybe_vex,orig,vex,maybe_vex")
})
(define_insn "*vec_interleave_lowv2df"
- [(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,x,Y3,x,x,o")
+ [(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,x,x,x,x,o")
(vec_select:V2DF
(vec_concat:V4DF
- (match_operand:V2DF 1 "nonimmediate_operand" " 0,x,m ,0,x,0")
- (match_operand:V2DF 2 "nonimmediate_operand" " x,x,1 ,m,m,x"))
+ (match_operand:V2DF 1 "nonimmediate_operand" " 0,x,m,0,x,0")
+ (match_operand:V2DF 2 "nonimmediate_operand" " x,x,1,m,m,x"))
(parallel [(const_int 0)
(const_int 2)])))]
"TARGET_SSE2 && ix86_vec_interleave_v2df_operator_ok (operands, 0)"
movhpd\t{%2, %0|%0, %2}
vmovhpd\t{%2, %1, %0|%0, %1, %2}
%vmovlpd\t{%2, %H0|%H0, %2}"
- [(set_attr "isa" "noavx,avx,*,noavx,avx,*")
+ [(set_attr "isa" "noavx,avx,sse3,noavx,avx,*")
(set_attr "type" "sselog,sselog,sselog,ssemov,ssemov,ssemov")
(set_attr "prefix_data16" "*,*,*,1,*,1")
(set_attr "prefix" "orig,vex,maybe_vex,orig,vex,maybe_vex")
(set_attr "mode" "DF")])
(define_insn "*vec_concatv2df"
- [(set (match_operand:V2DF 0 "register_operand" "=Y2,x,Y2,x,Y2,x,x")
+ [(set (match_operand:V2DF 0 "register_operand" "=x,x,x,x,x,x,x")
(vec_concat:V2DF
- (match_operand:DF 1 "nonimmediate_operand" " 0 ,x,0 ,x,m ,0,0")
- (match_operand:DF 2 "vector_move_operand" " Y2,x,m ,m,C ,x,m")))]
+ (match_operand:DF 1 "nonimmediate_operand" " 0,x,0,x,m,0,0")
+ (match_operand:DF 2 "vector_move_operand" " x,x,m,m,C,x,m")))]
"TARGET_SSE"
"@
unpcklpd\t{%2, %0|%0, %2}
%vmovsd\t{%1, %0|%0, %1}
movlhps\t{%2, %0|%0, %2}
movhps\t{%2, %0|%0, %2}"
- [(set_attr "isa" "noavx,avx,noavx,avx,*,noavx,noavx")
+ [(set_attr "isa" "sse2_noavx,avx,sse2_noavx,avx,sse2,noavx,noavx")
(set (attr "type")
(if_then_else
(eq_attr "alternative" "0,1")
"operands[2] = CONST0_RTX (V4SImode);")
(define_insn "sse2_loadld"
- [(set (match_operand:V4SI 0 "register_operand" "=Y2,Yi,x,x,x")
+ [(set (match_operand:V4SI 0 "register_operand" "=x,Yi,x,x,x")
(vec_merge:V4SI
(vec_duplicate:V4SI
- (match_operand:SI 2 "nonimmediate_operand" "m ,r ,m,x,x"))
- (match_operand:V4SI 1 "reg_or_0_operand" "C ,C ,C,0,x")
+ (match_operand:SI 2 "nonimmediate_operand" "m ,r ,m,x,x"))
+ (match_operand:V4SI 1 "reg_or_0_operand" "C ,C ,C,0,x")
(const_int 1)))]
"TARGET_SSE"
"@
movss\t{%2, %0|%0, %2}
movss\t{%2, %0|%0, %2}
vmovss\t{%2, %1, %0|%0, %1, %2}"
- [(set_attr "isa" "*,*,noavx,noavx,avx")
+ [(set_attr "isa" "sse2,*,noavx,noavx,avx")
(set_attr "type" "ssemov")
(set_attr "prefix" "maybe_vex,maybe_vex,orig,orig,vex")
(set_attr "mode" "TI,TI,V4SF,SF,SF")])
(set_attr "mode" "V2SF,TI,TI,TI,DI")])
(define_insn "*vec_extractv2di_1"
- [(set (match_operand:DI 0 "nonimmediate_operand" "=m,Y2,Y2,Y2,x,x")
+ [(set (match_operand:DI 0 "nonimmediate_operand" "=m,x,x,x,x,x")
(vec_select:DI
- (match_operand:V2DI 1 "nonimmediate_operand" " x,0 ,Y2,o ,x,o")
+ (match_operand:V2DI 1 "nonimmediate_operand" " x,0,x,o,x,o")
(parallel [(const_int 1)])))]
"!TARGET_64BIT && TARGET_SSE
&& !(MEM_P (operands[0]) && MEM_P (operands[1]))"
%vmovq\t{%H1, %0|%0, %H1}
movhlps\t{%1, %0|%0, %1}
movlps\t{%H1, %0|%0, %H1}"
- [(set_attr "isa" "*,noavx,avx,*,noavx,noavx")
+ [(set_attr "isa" "*,sse2_noavx,avx,sse2,noavx,noavx")
(set_attr "type" "ssemov,sseishft1,sseishft1,ssemov,ssemov,ssemov")
(set_attr "length_immediate" "*,1,1,*,*,*")
(set_attr "memory" "*,none,none,*,*,*")
(set_attr "mode" "TI,V4SF")])
(define_insn "*vec_dupv4si"
- [(set (match_operand:V4SI 0 "register_operand" "=Y2,x")
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x")
(vec_duplicate:V4SI
- (match_operand:SI 1 "register_operand" " Y2,0")))]
+ (match_operand:SI 1 "register_operand" " x,0")))]
"TARGET_SSE"
"@
pshufd\t{$0, %1, %0|%0, %1, 0}
shufps\t{$0, %0, %0|%0, %0, 0}"
- [(set_attr "type" "sselog1")
+ [(set_attr "isa" "sse2,*")
+ (set_attr "type" "sselog1")
(set_attr "length_immediate" "1")
(set_attr "mode" "TI,V4SF")])
(set_attr "mode" "TI,TI,DF")])
(define_insn "*vec_dupv2di"
- [(set (match_operand:V2DI 0 "register_operand" "=Y2,x")
+ [(set (match_operand:V2DI 0 "register_operand" "=x,x")
(vec_duplicate:V2DI
- (match_operand:DI 1 "register_operand" " 0 ,0")))]
+ (match_operand:DI 1 "register_operand" " 0,0")))]
"TARGET_SSE"
"@
punpcklqdq\t%0, %0
movlhps\t%0, %0"
- [(set_attr "type" "sselog1,ssemov")
+ [(set_attr "isa" "sse2,*")
+ (set_attr "type" "sselog1,ssemov")
(set_attr "mode" "TI,V4SF")])
(define_insn "*vec_concatv2si_sse4_1"
(set_attr "mode" "V4SF,V4SF,DI,DI")])
(define_insn "*vec_concatv4si"
- [(set (match_operand:V4SI 0 "register_operand" "=Y2,x,x,x,x")
+ [(set (match_operand:V4SI 0 "register_operand" "=x,x,x,x,x")
(vec_concat:V4SI
- (match_operand:V2SI 1 "register_operand" " 0 ,x,0,0,x")
- (match_operand:V2SI 2 "nonimmediate_operand" " Y2,x,x,m,m")))]
+ (match_operand:V2SI 1 "register_operand" " 0,x,0,0,x")
+ (match_operand:V2SI 2 "nonimmediate_operand" " x,x,x,m,m")))]
"TARGET_SSE"
"@
punpcklqdq\t{%2, %0|%0, %2}
movlhps\t{%2, %0|%0, %2}
movhps\t{%2, %0|%0, %2}
vmovhps\t{%2, %1, %0|%0, %1, %2}"
- [(set_attr "isa" "noavx,avx,noavx,noavx,avx")
+ [(set_attr "isa" "sse2_noavx,avx,noavx,noavx,avx")
(set_attr "type" "sselog,sselog,ssemov,ssemov,ssemov")
(set_attr "prefix" "orig,vex,orig,orig,vex")
(set_attr "mode" "TI,TI,V4SF,V2SF,V2SF")])
;; movd instead of movq is required to handle broken assemblers.
(define_insn "*vec_concatv2di_rex64"
[(set (match_operand:V2DI 0 "register_operand"
- "=Y4,x ,x ,Yi,!x,x,x,x,x")
+ "=x,x ,x ,Yi,!x,x,x,x,x")
(vec_concat:V2DI
(match_operand:DI 1 "nonimmediate_operand"
- " 0 ,x ,xm,r ,*y,0,x,0,x")
+ " 0,x ,xm,r ,*y,0,x,0,x")
(match_operand:DI 2 "vector_move_operand"
- " rm,rm,C ,C ,C ,x,x,m,m")))]
+ "rm,rm,C ,C ,C ,x,x,m,m")))]
"TARGET_64BIT"
"@
pinsrq\t{$1, %2, %0|%0, %2, 1}
vpunpcklqdq\t{%2, %1, %0|%0, %1, %2}
movhps\t{%2, %0|%0, %2}
vmovhps\t{%2, %1, %0|%0, %1, %2}"
- [(set_attr "isa" "noavx,avx,*,*,*,noavx,avx,noavx,avx")
+ [(set_attr "isa" "sse4_noavx,avx,*,*,*,noavx,avx,noavx,avx")
(set (attr "type")
(if_then_else
(eq_attr "alternative" "0,1,5,6")
(set_attr "mode" "TI,TI,TI,TI,TI,TI,TI,V2SF,V2SF")])
(define_insn "vec_concatv2di"
- [(set (match_operand:V2DI 0 "register_operand" "=Y2,?Y2,Y2,x,x,x,x")
+ [(set (match_operand:V2DI 0 "register_operand" "=x,?x,x,x,x,x,x")
(vec_concat:V2DI
- (match_operand:DI 1 "nonimmediate_operand" "Y2m,*y , 0,x,0,0,x")
- (match_operand:DI 2 "vector_move_operand" " C , C ,Y2,x,x,m,m")))]
+ (match_operand:DI 1 "nonimmediate_operand" "xm,*y,0,x,0,0,x")
+ (match_operand:DI 2 "vector_move_operand" " C, C,x,x,x,m,m")))]
"!TARGET_64BIT && TARGET_SSE"
"@
%vmovq\t{%1, %0|%0, %1}
movlhps\t{%2, %0|%0, %2}
movhps\t{%2, %0|%0, %2}
vmovhps\t{%2, %1, %0|%0, %1, %2}"
- [(set_attr "isa" "*,*,noavx,avx,noavx,noavx,avx")
+ [(set_attr "isa" "sse2,sse2,sse2_noavx,avx,noavx,noavx,avx")
(set_attr "type" "ssemov,ssemov,sselog,sselog,ssemov,ssemov,ssemov")
(set_attr "prefix" "maybe_vex,orig,orig,vex,orig,orig,vex")
(set_attr "mode" "TI,TI,TI,TI,V4SF,V2SF,V2SF")])
projects / gcc.git / commitdiff