[gcc(refs/users/meissner/heads/work085)] Generate vadduqm and vsubuqm for TImode add/subtract

[gcc(refs/users/meissner/heads/work085)] Generate vadduqm and vsubuqm for TImode add/subtract

[Michael Meissner]

https://gcc.gnu.org/g:822907b7b5fcc8f3a7d2da66899909ebe9e0960c

commit 822907b7b5fcc8f3a7d2da66899909ebe9e0960c
Author: Michael Meissner <meissner@linux.ibm.com>
Date:   Thu Apr 14 16:17:03 2022 -0400

    Generate vadduqm and vsubuqm for TImode add/subtract
    
    If the TImode variable is in an Altivec register instead of a GPR
    register, then generate vadduqm and vsubuqm instead of having to move the
    value to the GPR registers and doing the add and subtract with carry
    instructions.  To do this, we have to delay the splitting of the addition
    and subtraction until after register allocation.
    
    2022-04-14   Michael Meissner  <meissner@linux.ibm.com>
    
    gcc/
            * config/rs6000/rs6000.md (addti3): Generate vadduqm if we are
            using the Altivec registers.
            (subti3): Generate vsubuqm if we using the Altivec registers.
            (negti3): New insn.
    
    gcc/testsuite/
            * gcc.target/powerpc/vadduqm-vsubuqm.c: New test.

Diff:
---
 gcc/config/rs6000/rs6000.md                        | 82 ++++++++++++++++------
 gcc/testsuite/gcc.target/powerpc/vadduqm-vsubuqm.c | 22 ++++++
 2 files changed, 83 insertions(+), 21 deletions(-)

diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index be907ab3518..da924e3c738 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -7148,15 +7148,22 @@
 ;;
 ;; Addti3/subti3 are define_insn_and_splits instead of define_expand, to allow
 ;; for combine to make things like multiply and add with extend operations.
+;;
+;; Also add support in case the 128-bit integer happens to be an Altivec
+;; register.
 
 (define_insn_and_split "addti3"
-  [(set (match_operand:TI 0 "gpc_reg_operand"               "=&r,r,r")
-	(plus:TI (match_operand:TI 1 "gpc_reg_operand"       "r, 0,r")
-		 (match_operand:TI 2 "reg_or_short_operand"  "rI,r,0")))
+  [(set (match_operand:TI 0 "gpc_reg_operand"              "=&r, r,r,v")
+	(plus:TI (match_operand:TI 1 "gpc_reg_operand"       "r, 0,r,v")
+		 (match_operand:TI 2 "reg_or_short_operand"  "rI,r,0,v")))
    (clobber (reg:DI CA_REGNO))]
   "TARGET_64BIT"
-  "#"
-  "&& 1"
+  "@
+   #
+   #
+   #
+   vadduqm %0,%1,%2"
+  "&& reload_completed && int_reg_operand (operands[0], TImode)"
   [(pc)]
 {
   rtx lo0 = gen_lowpart (DImode, operands[0]);
@@ -7166,27 +7173,27 @@
   rtx hi1 = gen_highpart (DImode, operands[1]);
   rtx hi2 = gen_highpart_mode (DImode, TImode, operands[2]);
 
-  if (!reg_or_short_operand (lo2, DImode))
-    lo2 = force_reg (DImode, lo2);
-  if (!adde_operand (hi2, DImode))
-    hi2 = force_reg (DImode, hi2);
-
   emit_insn (gen_adddi3_carry (lo0, lo1, lo2));
   emit_insn (gen_adddi3_carry_in (hi0, hi1, hi2));
   DONE;
 }
-  [(set_attr "length" "8")
+  [(set_attr "length" "8,8,8,*")
+   (set_attr "isa"    "*,*,*,p8v")
    (set_attr "type"   "add")
    (set_attr "size"   "128")])
 
 (define_insn_and_split "subti3"
-  [(set (match_operand:TI 0 "gpc_reg_operand"                "=&r,r,r")
-	(minus:TI (match_operand:TI 1 "reg_or_short_operand" "rI,0,r")
-		  (match_operand:TI 2 "gpc_reg_operand"      "r, r,0")))
+  [(set (match_operand:TI 0 "gpc_reg_operand"                "=&r, r,r,v")
+	(minus:TI (match_operand:TI 1 "reg_or_short_operand"  "rI,0,r,v")
+		  (match_operand:TI 2 "gpc_reg_operand"       "r, r,0,v")))
    (clobber (reg:DI CA_REGNO))]
   "TARGET_64BIT"
-  "#"
-  "&& 1"
+  "@
+   #
+   #
+   #
+   vsubuqm %0,%1,%2"
+  "&& reload_completed && int_reg_operand (operands[0], TImode)"
   [(pc)]
 {
   rtx lo0 = gen_lowpart (DImode, operands[0]);
@@ -7196,16 +7203,49 @@
   rtx hi1 = gen_highpart_mode (DImode, TImode, operands[1]);
   rtx hi2 = gen_highpart (DImode, operands[2]);
 
-  if (!reg_or_short_operand (lo1, DImode))
-    lo1 = force_reg (DImode, lo1);
-  if (!adde_operand (hi1, DImode))
-    hi1 = force_reg (DImode, hi1);
-
   emit_insn (gen_subfdi3_carry (lo0, lo2, lo1));
   emit_insn (gen_subfdi3_carry_in (hi0, hi2, hi1));
   DONE;
+}
+  [(set_attr "length" "8,8,8,*")
+   (set_attr "isa"    "*,*,*,p8v")
+   (set_attr "type"   "add")
+   (set_attr "size"   "128")])
+
+;; 128-bit integer negation, normally use GPRs.  If we are using Altivec
+;; registers, create a 0 and do a vsubuqm.
+(define_insn_and_split "negti3"
+  [(set (match_operand:TI 0 "gpc_reg_operand"         "=&r,&v")
+	(neg:TI (match_operand:TI 1 "gpc_reg_operand"   "r,v")))
+   (clobber (reg:DI CA_REGNO))]
+  "TARGET_64BIT"
+  "#"
+  "&& reload_completed"
+  [(pc)]
+{
+  rtx dest = operands[0];
+  rtx src = operands[1];
+
+  if (altivec_register_operand (dest, TImode))
+    {
+      emit_move_insn (dest, const0_rtx);
+      emit_insn (gen_subti3 (dest, dest, src));
+      DONE;
+    }
+  else
+    {
+      rtx dest_lo = gen_lowpart (DImode, dest);
+      rtx dest_hi = gen_highpart (DImode, dest);
+      rtx src_lo = gen_lowpart (DImode, src);
+      rtx src_hi = gen_highpart (DImode, src);
+
+      emit_insn (gen_subfdi3_carry (dest_lo, src_lo, const0_rtx));
+      emit_insn (gen_subfdi3_carry_in (dest_hi, src_hi, const0_rtx));
+      DONE;
+    }
 }
   [(set_attr "length" "8")
+   (set_attr "isa"    "*,p8v")
    (set_attr "type"   "add")
    (set_attr "size"   "128")])
 \f
diff --git a/gcc/testsuite/gcc.target/powerpc/vadduqm-vsubuqm.c b/gcc/testsuite/gcc.target/powerpc/vadduqm-vsubuqm.c
new file mode 100644
index 00000000000..5cb2fe37e9c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vadduqm-vsubuqm.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target int128 } */
+/* { dg-options "-O2 -mdejagnu-cpu=power10" } */
+/* { dg-require-effective-target power10_ok } */
+
+/* Test that we generate vadduqm and vsubuqm for 128-bit integer add and
+   subtracts if the value is in an Altivec register.  We use 128-bit divide to
+   force the register selection to be in an altivec register.  */
+
+void
+test (__int128_t *p,
+      __int128_t *q,
+      __int128_t *r,
+      __int128_t *s,
+      __int128_t *t)
+{
+  *p = (*q + *r) / (*s - *t);	/* vadduqm, vsubuqm, vdivsq.  */
+}
+
+/* { dg-final { scan-assembler {\mvadduqm\M} } } */
+/* { dg-final { scan-assembler {\mvdivsq\M}  } } */
+/* { dg-final { scan-assembler {\mvsubuqm\M} } } */