diff mbox series

[2/6] Add wD constraint.

Message ID Zx_n7IyG7yYYHk0R@cowardly-lion.the-meissners.org
State New
Headers show
Series PowerPC Future support (Dense Math Registers) | expand

Commit Message

Michael Meissner Oct. 28, 2024, 7:37 p.m. UTC 
This patch adds a new constraint ('wD') that matches the accumulator registers
that overlap with VSX registers 0..31 on power10.  Future patches will add the
support for a separate accumulator register class that will be used when the
support for dense math registes is added.

2024-10-22   Michael Meissner  <meissner@linux.ibm.com>

	* config/rs6000/constraints.md (wD): New constraint.
	* config/rs6000/mma.md (mma_<acc>): Prepare for alternate accumulator
	registers.  Use wD constraint instead of 'd' constraint.  Use
	accumulator_operand instead of fpr_reg_operand.
	(mma_<vv>): Likewise.
	(mma_<avv>): Likewise.
	(mma_<pv>): Likewise.
	(mma_<apv>): Likewise.
	(mma_<vvi4i4i8>): Likewise.
	(mma_<avvi4i4i8>): Likewise.
	(mma_<vvi4i4i2>): Likewise.
	(mma_<avvi4i4i2>): Likewise.
	(mma_<vvi4i4>): Likewise.
	(mma_<avvi4i4>): Likewise.
	(mma_<pvi4i2): Likewise.
	(mma_<apvi4i2>): Likewise.
	(mma_<vvi4i4i4>): Likewise.
	(mma_<avvi4i4i4): Likewise.
	* config/rs6000/predicates.md (accumulator_operand): New predicate.
	* config/rs6000/rs6000.cc (rs6000_debug_reg_global): Print the register
	class for the 'wD' constraint.
	(rs6000_init_hard_regno_mode_ok): Set up the 'wD' register constraint
	class.
	* config/rs6000/rs6000.h (enum r6000_reg_class_enum): Add element for
	the 'wD' constraint.
	* doc/md.texi (PowerPC constraints): Document the 'wD' constraint.
---
 gcc/config/rs6000/constraints.md |  3 +++
 gcc/config/rs6000/mma.md         | 46 ++++++++++++++++----------------
 gcc/config/rs6000/predicates.md  | 15 +++++++++++
 gcc/config/rs6000/rs6000.cc      |  7 ++++-
 gcc/config/rs6000/rs6000.h       |  1 +
 gcc/doc/md.texi                  |  5 ++++
 6 files changed, 53 insertions(+), 24 deletions(-)
diff mbox series

Patch

diff --git a/gcc/config/rs6000/constraints.md b/gcc/config/rs6000/constraints.md
index 369a7b75042..277a30a8245 100644
--- a/gcc/config/rs6000/constraints.md
+++ b/gcc/config/rs6000/constraints.md
@@ -107,6 +107,9 @@  (define_constraint "wB"
        (match_test "TARGET_P8_VECTOR")
        (match_operand 0 "s5bit_cint_operand")))
 
+(define_register_constraint "wD" "rs6000_constraints[RS6000_CONSTRAINT_wD]"
+  "Accumulator register.")
+
 (define_constraint "wE"
   "@internal Vector constant that can be loaded with the XXSPLTIB instruction."
   (match_test "xxspltib_constant_nosplit (op, mode)"))
diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index 04e2d0066df..e051239df57 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -504,8 +504,8 @@  (define_insn_and_split "*mma_disassemble_acc"
 ;; the accumulator.  We enforce this by marking the output as early clobber.
 
 (define_insn "mma_<acc>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
-	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0")]
 		    MMA_ACC))]
   "TARGET_MMA"
   "<acc> %A0"
@@ -523,7 +523,7 @@  (define_insn "mma_xxsetaccz"
   [(set_attr "type" "mma")])
 
 (define_insn "mma_<vv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
 	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
 		    MMA_VV))]
@@ -532,8 +532,8 @@  (define_insn "mma_<vv>"
   [(set_attr "type" "mma")])
 
 (define_insn "mma_<avv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
 		    MMA_AVV))]
@@ -542,7 +542,7 @@  (define_insn "mma_<avv>"
   [(set_attr "type" "mma")])
 
 (define_insn "mma_<pv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
 	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
 		    MMA_PV))]
@@ -551,8 +551,8 @@  (define_insn "mma_<pv>"
   [(set_attr "type" "mma")])
 
 (define_insn "mma_<apv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0")
 		    (match_operand:OO 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
 		    MMA_APV))]
@@ -561,7 +561,7 @@  (define_insn "mma_<apv>"
   [(set_attr "type" "mma")])
 
 (define_insn "mma_<vvi4i4i8>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
 	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 3 "const_0_to_15_operand" "n,n")
@@ -574,8 +574,8 @@  (define_insn "mma_<vvi4i4i8>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<avvi4i4i8>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
@@ -588,7 +588,7 @@  (define_insn "mma_<avvi4i4i8>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<vvi4i4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
 	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 3 "const_0_to_15_operand" "n,n")
@@ -601,8 +601,8 @@  (define_insn "mma_<vvi4i4i2>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<avvi4i4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
@@ -615,7 +615,7 @@  (define_insn "mma_<avvi4i4i2>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<vvi4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
 	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 3 "const_0_to_15_operand" "n,n")
@@ -627,8 +627,8 @@  (define_insn "mma_<vvi4i4>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<avvi4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
@@ -640,7 +640,7 @@  (define_insn "mma_<avvi4i4>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<pvi4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
 	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 3 "const_0_to_15_operand" "n,n")
@@ -652,8 +652,8 @@  (define_insn "mma_<pvi4i2>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<apvi4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0")
 		    (match_operand:OO 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
@@ -665,7 +665,7 @@  (define_insn "mma_<apvi4i2>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<vvi4i4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
 	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 3 "const_0_to_15_operand" "n,n")
@@ -678,8 +678,8 @@  (define_insn "mma_<vvi4i4i4>"
    (set_attr "prefixed" "yes")])
 
 (define_insn "mma_<avvi4i4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0,0")
+  [(set (match_operand:XO 0 "accumulator_operand" "=&wD,&wD")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0")
 		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
 		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")
 		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 0b78901e94b..1827647b7c1 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -186,6 +186,21 @@  (define_predicate "vlogical_operand"
   return VLOGICAL_REGNO_P (REGNO (op));
 })
 
+;; Return 1 if op is an accumulator.  On power10 systems, the accumulators
+;; overlap with the FPRs.
+(define_predicate "accumulator_operand"
+  (match_operand 0 "register_operand")
+{
+  if (!REG_P (op))
+    return 0;
+
+  if (!HARD_REGISTER_P (op))
+    return 1;
+
+  int r = REGNO (op);
+  return FP_REGNO_P (r) && (r & 3) == 0;
+})
+
 ;; Return 1 if op is the carry register.
 (define_predicate "ca_operand"
   (match_operand 0 "register_operand")
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index aa67e7256bb..9e9342d4793 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -2411,6 +2411,7 @@  rs6000_debug_reg_global (void)
 	   "wr reg_class = %s\n"
 	   "wx reg_class = %s\n"
 	   "wA reg_class = %s\n"
+	   "wD reg_class = %s\n"
 	   "\n",
 	   reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_d]],
 	   reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_v]],
@@ -2418,7 +2419,8 @@  rs6000_debug_reg_global (void)
 	   reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_we]],
 	   reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wr]],
 	   reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wx]],
-	   reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wA]]);
+	   reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wA]],
+	   reg_class_names[rs6000_constraints[RS6000_CONSTRAINT_wD]]);
 
   nl = "\n";
   for (m = 0; m < NUM_MACHINE_MODES; ++m)
@@ -3081,6 +3083,9 @@  rs6000_init_hard_regno_mode_ok (bool global_init_p)
   if (TARGET_DIRECT_MOVE_128)
     rs6000_constraints[RS6000_CONSTRAINT_we] = VSX_REGS;
 
+  if (TARGET_MMA)
+    rs6000_constraints[RS6000_CONSTRAINT_wD] = FLOAT_REGS;
+
   /* Set up the reload helper and direct move functions.  */
   if (TARGET_VSX || TARGET_ALTIVEC)
     {
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index 8cfd9faf77d..07a372b8902 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -1203,6 +1203,7 @@  enum r6000_reg_class_enum {
   RS6000_CONSTRAINT_wr,		/* GPR register if 64-bit  */
   RS6000_CONSTRAINT_wx,		/* FPR register for STFIWX */
   RS6000_CONSTRAINT_wA,		/* BASE_REGS if 64-bit.  */
+  RS6000_CONSTRAINT_wD,		/* Accumulator regs if MMA/Dense Math.  */
   RS6000_CONSTRAINT_MAX
 };
 
diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index 6d9c8643739..569172031fd 100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -3440,6 +3440,11 @@  Like @code{d}, if @option{-mpowerpc-gfxopt} is used; otherwise, @code{NO_REGS}.
 @item wA
 Like @code{b}, if @option{-mpowerpc64} is used; otherwise, @code{NO_REGS}.
 
+@item wD
+Accumulator register if @option{-mma} is used; otherwise,
+@code{NO_REGS}.  For @option{-mcpu=power10} the accumulator registers
+overlap with VSX vector registers 0..31.
+
 @item wB
 Signed 5-bit constant integer that can be loaded into an Altivec register.