https://gcc.gnu.org/g:67fa78e3953c481018d73fb7258d938a9c67eb4e
commit 67fa78e3953c481018d73fb7258d938a9c67eb4e
Author: Michael Meissner <meiss...@linux.ibm.com>
Date: Mon Dec 2 15:34:47 2024 -0500
RFC2653-Add wD constraint.
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.
2024-12-02 Michael Meissner <meiss...@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.
Diff:
---
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 --git a/gcc/config/rs6000/constraints.md b/gcc/config/rs6000/constraints.md
index 369a7b75042d..277a30a82458 100644
--- a/gcc/config/rs6000/constraints.md
+++ b/gcc/config/rs6000/constraints.md
@@ -107,6 +107,9 @@
(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 04e2d0066df2..e051239df57b 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -504,8 +504,8 @@
;; 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 @@
[(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 @@
[(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 @@
[(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 @@
[(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 @@
[(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 @@
(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 @@
(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 @@
(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 @@
(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 @@
(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 @@
(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 @@
(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 @@
(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 @@
(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 0b78901e94be..1827647b7c1e 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -186,6 +186,21 @@
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 0878929de224..3047a9e9a9b0 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -2412,6 +2412,7 @@ 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]],
@@ -2419,7 +2420,8 @@ 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)
@@ -3082,6 +3084,9 @@ 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 392ca858fc40..69519851326e 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -1197,6 +1197,7 @@ 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 69605bf75c0f..5ceccc9b97f3 100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -3379,6 +3379,11 @@ 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.
