rs6000: Disable optimizing multiple xxsetaccz instructions into one xxsetaccz

Fwprop will happily optimize two xxsetaccz instructions into one xxsetaccz
by propagating the results of the first to the uses of the second.
We really don't want that to happen given the late priming/depriming of
accumulators.  I fixed this by making the xxsetaccz source operand an
unspec volatile.  I also removed the mma_xxsetaccz define_expand and
define_insn_and_split and replaced it with a simple define_insn.
The expand and splitter patterns were leftovers from the pre opaque mode
code when the xxsetaccz code was part of the movpxi pattern, and we don't
need them now.

Rather than a new test case, I was able to just modify the current test case
to add another __builtin_mma_xxsetaccz call which shows the bad code gen
with unpatched compilers.

2021-09-14  Peter Bergner  <bergner@linux.ibm.com>

gcc/
	* config/rs6000/mma.md (unspec): Delete UNSPEC_MMA_XXSETACCZ.
	(unspecv): Add UNSPECV_MMA_XXSETACCZ.
	(*mma_xxsetaccz): Delete.
	(mma_xxsetaccz): Change to define_insn.  Remove operand 1.
	Use UNSPECV_MMA_XXSETACCZ.  Update comment.
	* config/rs6000/rs6000.c (rs6000_rtx_costs): Use UNSPECV_MMA_XXSETACCZ.

gcc/testsuite/
	* gcc.target/powerpc/mma-builtin-6.c: Add second call to xxsetacc
	built-in.  Update instruction counts.

(cherry picked from commit f80b9be083e0e7d49e7744b7e531b9aa52acd563)

diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index 1f6fc03d2ac26f1def1aa0c428a6e79dd088e312..1990a2183f6c96f8f1dac95bc50c8cf64c31aee8 100644 (file)
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -91,7 +91,10 @@
    UNSPEC_MMA_XVI8GER4SPP
    UNSPEC_MMA_XXMFACC
    UNSPEC_MMA_XXMTACC
-   UNSPEC_MMA_XXSETACCZ
+  ])
+
+(define_c_enum "unspecv"
+  [UNSPECV_MMA_XXSETACCZ
   ])
 
 ;; MMA instructions with 1 accumulator argument
@@ -467,30 +470,16 @@
   "<acc> %A0"
   [(set_attr "type" "mma")])
 
-;; We can't have integer constants in XOmode so we wrap this in an UNSPEC.
-
-(define_expand "mma_xxsetaccz"
-  [(set (match_operand:XO 0 "fpr_reg_operand")
-       (const_int 0))]
-  "TARGET_MMA"
-{
-  rtx xo0 = gen_rtx_UNSPEC (XOmode, gen_rtvec (1, const0_rtx),
-                           UNSPEC_MMA_XXSETACCZ);
-  emit_insn (gen_rtx_SET (operands[0], xo0));
-  DONE;
-})
+;; We can't have integer constants in XOmode so we wrap this in an
+;; UNSPEC_VOLATILE.
 
-(define_insn_and_split "*mma_xxsetaccz"
+(define_insn "mma_xxsetaccz"
   [(set (match_operand:XO 0 "fpr_reg_operand" "=d")
-       (unspec:XO [(match_operand 1 "const_0_to_1_operand" "O")]
-        UNSPEC_MMA_XXSETACCZ))]
+       (unspec_volatile:XO [(const_int 0)]
+                           UNSPECV_MMA_XXSETACCZ))]
   "TARGET_MMA"
   "xxsetaccz %A0"
-  "&& reload_completed"
-  [(set (match_dup 0) (unspec:XO [(match_dup 1)] UNSPEC_MMA_XXSETACCZ))]
-  ""
-  [(set_attr "type" "mma")
-   (set_attr "length" "4")])
+  [(set_attr "type" "mma")])
 
 (define_insn "mma_<vv>"
   [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")

diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 8cdb9369ee00f5b5b15fe85141c98b27094ed187..3bd9643409e84734bc466f932f7c5a2f1aecb32f 100644 (file)
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -21939,7 +21939,7 @@ rs6000_rtx_costs (rtx x, machine_mode mode, int outer_code,
       break;
 
     case UNSPEC:
-      if (XINT (x, 1) == UNSPEC_MMA_XXSETACCZ)
+      if (XINT (x, 1) == UNSPECV_MMA_XXSETACCZ)
        {
          *total = 0;
          return true;

diff --git a/gcc/testsuite/gcc.target/powerpc/mma-builtin-6.c b/gcc/testsuite/gcc.target/powerpc/mma-builtin-6.c
index 0c6517211e3b32702258e6b8e743ba79891cc90d..715b28138e9eff4cc491f01a813e1c2614466e32 100644 (file)
--- a/gcc/testsuite/gcc.target/powerpc/mma-builtin-6.c
+++ b/gcc/testsuite/gcc.target/powerpc/mma-builtin-6.c
@@ -5,14 +5,16 @@
 void
 foo (__vector_quad *dst)
 {
-  __vector_quad acc;
-  __builtin_mma_xxsetaccz (&acc);
-  *dst = acc;
+  __vector_quad acc0, acc1;
+  __builtin_mma_xxsetaccz (&acc0);
+  __builtin_mma_xxsetaccz (&acc1);
+  dst[0] = acc0;
+  dst[1] = acc1;
 }
 
 /* { dg-final { scan-assembler-not {\mlxv\M} } } */
 /* { dg-final { scan-assembler-not {\mlxvp\M} } } */
 /* { dg-final { scan-assembler-not {\mxxmtacc\M} } } */
-/* { dg-final { scan-assembler-times {\mxxsetaccz\M} 1 } } */
-/* { dg-final { scan-assembler-times {\mxxmfacc\M} 1 } } */
-/* { dg-final { scan-assembler-times {\mstxvp\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxsetaccz\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxmfacc\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mstxvp\M} 4 } } */