===================================================================
@@ -36,13 +36,14 @@ (define_mode_iterator VEC_A [V16QI V8HI
(define_mode_iterator VEC_K [V16QI V8HI V4SI V4SF])
;; Vector logical modes
-(define_mode_iterator VEC_L [V16QI V8HI V4SI V2DI V4SF V2DF V1TI TI])
+(define_mode_iterator VEC_L [V16QI V8HI V4SI V2DI V4SF V2DF V1TI TI KF TF])
-;; Vector modes for moves. Don't do TImode here.
-(define_mode_iterator VEC_M [V16QI V8HI V4SI V2DI V4SF V2DF V1TI])
+;; Vector modes for moves. Don't do TImode or TFmode here, since their
+;; moves are handled elsewhere.
+(define_mode_iterator VEC_M [V16QI V8HI V4SI V2DI V4SF V2DF V1TI KF])
;; Vector modes for types that don't need a realignment under VSX
-(define_mode_iterator VEC_N [V4SI V4SF V2DI V2DF V1TI])
+(define_mode_iterator VEC_N [V4SI V4SF V2DI V2DF V1TI KF TF])
;; Vector comparison modes
(define_mode_iterator VEC_C [V16QI V8HI V4SI V2DI V4SF V2DF])
@@ -95,12 +96,19 @@ (define_expand "mov<mode>"
{
if (can_create_pseudo_p ())
{
- if (CONSTANT_P (operands[1])
- && !easy_vector_constant (operands[1], <MODE>mode))
- operands[1] = force_const_mem (<MODE>mode, operands[1]);
+ if (CONSTANT_P (operands[1]))
+ {
+ if (FLOAT128_VECTOR_P (<MODE>mode))
+ {
+ if (!easy_fp_constant (operands[1], <MODE>mode))
+ operands[1] = force_const_mem (<MODE>mode, operands[1]);
+ }
+ else if (!easy_vector_constant (operands[1], <MODE>mode))
+ operands[1] = force_const_mem (<MODE>mode, operands[1]);
+ }
- else if (!vlogical_operand (operands[0], <MODE>mode)
- && !vlogical_operand (operands[1], <MODE>mode))
+ if (!vlogical_operand (operands[0], <MODE>mode)
+ && !vlogical_operand (operands[1], <MODE>mode))
operands[1] = force_reg (<MODE>mode, operands[1]);
}
if (!BYTES_BIG_ENDIAN
===================================================================
@@ -56,12 +56,16 @@ (define_register_constraint "z" "CA_REGS
(define_register_constraint "wa" "rs6000_constraints[RS6000_CONSTRAINT_wa]"
"Any VSX register if the -mvsx option was used or NO_REGS.")
+;; wb is not currently used
+
;; NOTE: For compatibility, "wc" is reserved to represent individual CR bits.
;; It is currently used for that purpose in LLVM.
(define_register_constraint "wd" "rs6000_constraints[RS6000_CONSTRAINT_wd]"
"VSX vector register to hold vector double data or NO_REGS.")
+;; we is not currently used
+
(define_register_constraint "wf" "rs6000_constraints[RS6000_CONSTRAINT_wf]"
"VSX vector register to hold vector float data or NO_REGS.")
@@ -93,6 +97,14 @@ (define_register_constraint "wm" "rs6000
;; There is a mode_attr that resolves to wm for SDmode and wn for SFmode
(define_register_constraint "wn" "NO_REGS" "No register (NO_REGS).")
+;; wo is not currently used
+
+(define_register_constraint "wp" "rs6000_constraints[RS6000_CONSTRAINT_wp]"
+ "VSX register to use for IEEE 128-bit fp TFmode, or NO_REGS.")
+
+(define_register_constraint "wq" "rs6000_constraints[RS6000_CONSTRAINT_wq]"
+ "VSX register to use for IEEE 128-bit fp KFmode, or NO_REGS.")
+
(define_register_constraint "wr" "rs6000_constraints[RS6000_CONSTRAINT_wr]"
"General purpose register if 64-bit instructions are enabled or NO_REGS.")
===================================================================
@@ -460,6 +460,8 @@ (define_predicate "easy_fp_constant"
switch (mode)
{
+ case KFmode:
+ case IFmode:
case TFmode:
case DFmode:
case SFmode:
@@ -486,6 +488,12 @@ (define_predicate "easy_vector_constant"
if (TARGET_PAIRED_FLOAT)
return false;
+ /* Because IEEE 128-bit floating point is considered a vector type
+ in order to pass it in VSX registers, it might use this function
+ instead of easy_fp_constant. */
+ if (FLOAT128_VECTOR_P (mode))
+ return easy_fp_constant (op, mode);
+
if (VECTOR_MEM_ALTIVEC_OR_VSX_P (mode))
{
if (zero_constant (op, mode))
===================================================================
@@ -2167,6 +2167,8 @@ rs6000_debug_reg_global (void)
"wk reg_class = %s\n"
"wl reg_class = %s\n"
"wm reg_class = %s\n"
+ "wp reg_class = %s\n"
+ "wq reg_class = %s\n"
"wr reg_class = %s\n"
"ws reg_class = %s\n"
"wt reg_class = %s\n"
@@ -2190,6 +2192,8 @@ rs6000_debug_reg_global (void)
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wk]],
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wl]],
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wm]],
+ reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wp]],
+ reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wq]],
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wr]],
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_ws]],
reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wt]],
@@ -2856,6 +2860,13 @@ rs6000_init_hard_regno_mode_ok (bool glo
if (TARGET_LFIWZX)
rs6000_constraints[RS6000_CONSTRAINT_wz] = FLOAT_REGS; /* DImode */
+ if (TARGET_FLOAT128)
+ {
+ rs6000_constraints[RS6000_CONSTRAINT_wq] = VSX_REGS; /* KFmode */
+ if (rs6000_ieeequad)
+ rs6000_constraints[RS6000_CONSTRAINT_wp] = VSX_REGS; /* TFmode */
+ }
+
/* Set up the reload helper and direct move functions. */
if (TARGET_VSX || TARGET_ALTIVEC)
{
===================================================================
@@ -31,6 +31,11 @@ (define_mode_iterator VSX_LE [V2DF
V1TI
(TI "VECTOR_MEM_VSX_P (TImode)")])
+;; Mode iterator to handle swapping words on little endian for the 128-bit
+;; types that goes in a single vector register.
+(define_mode_iterator VSX_LE_128 [(KF "FLOAT128_VECTOR_P (KFmode)")
+ (TF "FLOAT128_VECTOR_P (TFmode)")])
+
;; Iterator for the 2 32-bit vector types
(define_mode_iterator VSX_W [V4SF V4SI])
@@ -41,11 +46,31 @@ (define_mode_iterator VSX_DF [V2DF DF])
(define_mode_iterator VSX_F [V4SF V2DF])
;; Iterator for logical types supported by VSX
-(define_mode_iterator VSX_L [V16QI V8HI V4SI V2DI V4SF V2DF V1TI TI])
+;; Note, IFmode won't actually be used since it isn't a VSX type, but it simplifies
+;; the code by using 128-bit iterators for floating point.
+(define_mode_iterator VSX_L [V16QI
+ V8HI
+ V4SI
+ V2DI
+ V4SF
+ V2DF
+ V1TI
+ TI
+ (KF "FLOAT128_VECTOR_P (KFmode)")
+ (TF "FLOAT128_VECTOR_P (TFmode)")
+ (IF "FLOAT128_VECTOR_P (IFmode)")])
;; Iterator for memory move. Handle TImode specially to allow
;; it to use gprs as well as vsx registers.
-(define_mode_iterator VSX_M [V16QI V8HI V4SI V2DI V4SF V2DF V1TI])
+(define_mode_iterator VSX_M [V16QI
+ V8HI
+ V4SI
+ V2DI
+ V4SF
+ V2DF
+ V1TI
+ (KF "FLOAT128_VECTOR_P (KFmode)")
+ (TF "FLOAT128_VECTOR_P (TFmode)")])
(define_mode_iterator VSX_M2 [V16QI
V8HI
@@ -54,6 +79,8 @@ (define_mode_iterator VSX_M2 [V16QI
V4SF
V2DF
V1TI
+ (KF "FLOAT128_VECTOR_P (KFmode)")
+ (TF "FLOAT128_VECTOR_P (TFmode)")
(TI "TARGET_VSX_TIMODE")])
;; Map into the appropriate load/store name based on the type
@@ -64,6 +91,8 @@ (define_mode_attr VSm [(V16QI "vw4")
(V2DF "vd2")
(V2DI "vd2")
(DF "d")
+ (TF "vd2")
+ (KF "vd2")
(V1TI "vd2")
(TI "vd2")])
@@ -76,6 +105,8 @@ (define_mode_attr VSs [(V16QI "sp")
(V2DI "dp")
(DF "dp")
(SF "sp")
+ (TF "dp")
+ (KF "dp")
(V1TI "dp")
(TI "dp")])
@@ -89,6 +120,8 @@ (define_mode_attr VSr [(V16QI "v")
(DI "wi")
(DF "ws")
(SF "ww")
+ (TF "wp")
+ (KF "wq")
(V1TI "v")
(TI "wt")])
@@ -132,7 +165,9 @@ (define_mode_attr VSa [(V16QI "wa")
(DF "ws")
(SF "ww")
(V1TI "wa")
- (TI "wt")])
+ (TI "wt")
+ (TF "wp")
+ (KF "wq")])
;; Same size integer type for floating point data
(define_mode_attr VSi [(V4SF "v4si")
@@ -157,7 +192,8 @@ (define_mode_attr VSv [(V16QI "v")
(V2DI "v")
(V2DF "v")
(V1TI "v")
- (DF "s")])
+ (DF "s")
+ (KF "v")])
;; Appropriate type for add ops (and other simple FP ops)
(define_mode_attr VStype_simple [(V2DF "vecdouble")
@@ -623,6 +659,105 @@ (define_split
(const_int 6) (const_int 7)])))]
"")
+;; Little endian word swapping for 128-bit types that are either scalars or the
+;; special V1TI container class, which it is not appropriate to use vec_select
+;; for the type.
+(define_insn "*vsx_le_permute_<mode>"
+ [(set (match_operand:VSX_LE_128 0 "nonimmediate_operand" "=<VSa>,<VSa>,Z")
+ (rotate:VSX_LE_128
+ (match_operand:VSX_LE_128 1 "input_operand" "<VSa>,Z,<VSa>")
+ (const_int 64)))]
+ "!BYTES_BIG_ENDIAN && TARGET_VSX"
+ "@
+ xxpermdi %x0,%x1,%x1,2
+ lxvd2x %x0,%y1
+ stxvd2x %x1,%y0"
+ [(set_attr "length" "4")
+ (set_attr "type" "vecperm,vecload,vecstore")])
+
+(define_insn_and_split "*vsx_le_undo_permute_<mode>"
+ [(set (match_operand:VSX_LE_128 0 "vsx_register_operand" "=<VSa>,<VSa>")
+ (rotate:VSX_LE_128
+ (rotate:VSX_LE_128
+ (match_operand:VSX_LE_128 1 "vsx_register_operand" "0,<VSa>")
+ (const_int 64))
+ (const_int 64)))]
+ "!BYTES_BIG_ENDIAN && TARGET_VSX"
+ "@
+ #
+ xxlor %x0,%x1"
+ ""
+ [(set (match_dup 0) (match_dup 1))]
+{
+ if (reload_completed && REGNO (operands[0]) == REGNO (operands[1]))
+ {
+ emit_note (NOTE_INSN_DELETED);
+ DONE;
+ }
+}
+ [(set_attr "length" "0,4")
+ (set_attr "type" "vecsimple")])
+
+(define_insn_and_split "*vsx_le_perm_load_<mode>"
+ [(set (match_operand:VSX_LE_128 0 "vsx_register_operand" "=<VSa>")
+ (match_operand:VSX_LE_128 1 "memory_operand" "Z"))]
+ "!BYTES_BIG_ENDIAN && TARGET_VSX"
+ "#"
+ "!BYTES_BIG_ENDIAN && TARGET_VSX"
+ [(set (match_dup 2)
+ (rotate:VSX_LE_128 (match_dup 1)
+ (const_int 64)))
+ (set (match_dup 0)
+ (rotate:VSX_LE_128 (match_dup 2)
+ (const_int 64)))]
+ "
+{
+ operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[0])
+ : operands[0];
+}
+ "
+ [(set_attr "type" "vecload")
+ (set_attr "length" "8")])
+
+(define_insn "*vsx_le_perm_store_<mode>"
+ [(set (match_operand:VSX_LE_128 0 "memory_operand" "=Z")
+ (match_operand:VSX_LE_128 1 "vsx_register_operand" "+<VSa>"))]
+ "!BYTES_BIG_ENDIAN && TARGET_VSX"
+ "#"
+ [(set_attr "type" "vecstore")
+ (set_attr "length" "12")])
+
+(define_split
+ [(set (match_operand:VSX_LE_128 0 "memory_operand" "")
+ (match_operand:VSX_LE_128 1 "vsx_register_operand" ""))]
+ "!BYTES_BIG_ENDIAN && TARGET_VSX && !reload_completed"
+ [(set (match_dup 2)
+ (rotate:VSX_LE_128 (match_dup 1)
+ (const_int 64)))
+ (set (match_dup 0)
+ (rotate:VSX_LE_128 (match_dup 2)
+ (const_int 64)))]
+{
+ operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[0])
+ : operands[0];
+})
+
+;; The post-reload split requires that we re-permute the source
+;; register in case it is still live.
+(define_split
+ [(set (match_operand:VSX_LE_128 0 "memory_operand" "")
+ (match_operand:VSX_LE_128 1 "vsx_register_operand" ""))]
+ "!BYTES_BIG_ENDIAN && TARGET_VSX && reload_completed"
+ [(set (match_dup 1)
+ (rotate:VSX_LE_128 (match_dup 1)
+ (const_int 64)))
+ (set (match_dup 0)
+ (rotate:VSX_LE_128 (match_dup 1)
+ (const_int 64)))
+ (set (match_dup 1)
+ (rotate:VSX_LE_128 (match_dup 1)
+ (const_int 64)))]
+ "")
(define_insn "*vsx_mov<mode>"
[(set (match_operand:VSX_M 0 "nonimmediate_operand" "=Z,<VSr>,<VSr>,?Z,?<VSa>,?<VSa>,wQ,?&r,??Y,??r,??r,<VSr>,?<VSa>,*r,v,wZ, v")
===================================================================
@@ -1496,6 +1496,8 @@ enum r6000_reg_class_enum {
RS6000_CONSTRAINT_wk, /* FPR/VSX register for DFmode direct moves. */
RS6000_CONSTRAINT_wl, /* FPR register for LFIWAX */
RS6000_CONSTRAINT_wm, /* VSX register for direct move */
+ RS6000_CONSTRAINT_wp, /* VSX reg for IEEE 128-bit fp TFmode. */
+ RS6000_CONSTRAINT_wq, /* VSX reg for IEEE 128-bit fp KFmode. */
RS6000_CONSTRAINT_wr, /* GPR register if 64-bit */
RS6000_CONSTRAINT_ws, /* VSX register for DF */
RS6000_CONSTRAINT_wt, /* VSX register for TImode */
===================================================================
@@ -167,10 +167,27 @@ (define_mode_iterator VF [V4SF])
(define_mode_iterator V [V4SI V8HI V16QI V4SF])
;; Vec modes for move/logical/permute ops, include vector types for move not
;; otherwise handled by altivec (v2df, v2di, ti)
-(define_mode_iterator VM [V4SI V8HI V16QI V4SF V2DF V2DI V1TI TI])
+(define_mode_iterator VM [V4SI
+ V8HI
+ V16QI
+ V4SF
+ V2DF
+ V2DI
+ V1TI
+ TI
+ (KF "FLOAT128_VECTOR_P (KFmode)")
+ (TF "FLOAT128_VECTOR_P (TFmode)")])
;; Like VM, except don't do TImode
-(define_mode_iterator VM2 [V4SI V8HI V16QI V4SF V2DF V2DI V1TI])
+(define_mode_iterator VM2 [V4SI
+ V8HI
+ V16QI
+ V4SF
+ V2DF
+ V2DI
+ V1TI
+ (KF "FLOAT128_VECTOR_P (KFmode)")
+ (TF "FLOAT128_VECTOR_P (TFmode)")])
(define_mode_attr VI_char [(V2DI "d") (V4SI "w") (V8HI "h") (V16QI "b")])
(define_mode_attr VI_scalar [(V2DI "DI") (V4SI "SI") (V8HI "HI") (V16QI "QI")])
===================================================================
@@ -3087,12 +3087,13 @@ Any VSX register if the -mvsx option was
When using any of the register constraints (@code{wa}, @code{wd},
@code{wf}, @code{wg}, @code{wh}, @code{wi}, @code{wj}, @code{wk},
-@code{wl}, @code{wm}, @code{ws}, @code{wt}, @code{wu}, @code{wv},
-@code{ww}, or @code{wy}) that take VSX registers, you must use
-@code{%x<n>} in the template so that the correct register is used.
-Otherwise the register number output in the assembly file will be
-incorrect if an Altivec register is an operand of a VSX instruction
-that expects VSX register numbering.
+@code{wl}, @code{wm}, @code{wp}, @code{wq}, @code{ws}, @code{wt},
+@code{wu}, @code{wv}, @code{ww}, or @code{wy})
+that take VSX registers, you must use @code{%x<n>} in the template so
+that the correct register is used. Otherwise the register number
+output in the assembly file will be incorrect if an Altivec register
+is an operand of a VSX instruction that expects VSX register
+numbering.
@smallexample
asm ("xvadddp %x0,%x1,%x2" : "=wa" (v1) : "wa" (v2), "wa" (v3));
@@ -3136,6 +3137,12 @@ VSX register if direct move instructions
@item wn
No register (NO_REGS).
+@item wp
+VSX register to use for IEEE 128-bit floating point TFmode, or NO_REGS.
+
+@item wq
+VSX register to use for IEEE 128-bit floating point, or NO_REGS.
+
@item wr
General purpose register if 64-bit instructions are enabled or NO_REGS.