public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc(refs/users/meissner/heads/dmf007)] PowerPC: Make MMA insns support DMR registers.
@ 2023-01-21  2:54 Michael Meissner
  0 siblings, 0 replies; 3+ messages in thread
From: Michael Meissner @ 2023-01-21  2:54 UTC (permalink / raw)
  To: gcc-cvs

https://gcc.gnu.org/g:58d22b7e011893e6bc81f95dc621b7ddcf0ab625

commit 58d22b7e011893e6bc81f95dc621b7ddcf0ab625
Author: Michael Meissner <meissner@linux.ibm.com>
Date:   Fri Jan 20 19:29:18 2023 -0500

    PowerPC: Make MMA insns support DMR registers.
    
    This patch changes the MMA instructions to use either FPR registers
    (-mcpu=power10) or DMRs (-mcpu=future).  In this patch, the existing MMA
    instruction names are used.
    
    A macro (__PPC_DMR__) is defined if the MMA instructions use the DMRs.
    
    The patches have been tested on the following platforms.  I added the patches
    for PR target/107299 that I submitted on November 2nd before doing the builds so
    that GCC would build on systems using IEEE 128-bit long double.
        *   https://gcc.gnu.org/pipermail/gcc-patches/2022-November/604834.html
    
    There were no regressions with doing bootstrap builds and running the regression
    tests:
    
        1)  Power10 LE using --with-cpu=power10 --with-long-double-format=ieee;
        2)  Power10 LE using --with-cpu=power10 --with-long-double-format=ibm;
        3)  Power9 LE using --with-cpu=power9 --with-long-double-format=ibm; and
        4)  Power8 BE using --with-cpu=power8 (both 32-bit & 64-bit tested).
    
    Can I check this patch into the GCC 13 master branch?
    
    2023-01-20   Michael Meissner  <meissner@linux.ibm.com>
    
    gcc/
    
            * config/rs6000/mma.md (mma_<acc>): New define_expand to handle
            mma_<acc> for dense math and non dense math.
            (mma_<acc> insn): Restrict to non dense math.
            (mma_xxsetaccz): Convert to define_expand to handle non dense math and
            dense math.
            (mma_xxsetaccz_p10): Rename from mma_xxsetaccz and restrict usage to non
            dense math.
            (mma_xxsetaccz_dm): Dense math version of mma_xxsetaccz.
            (mma_<vv>): Add support for dense math.
            (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/rs6000-c.cc (rs6000_target_modify_macros): Define
            __PPC_DMR__ if we have dense math instructions.
            * config/rs6000/rs6000.cc (print_operand): Make %A handle only DMRs if
            dense math and only FPRs if not dense math.
            (rs6000_split_multireg_move): Do not generate accumulator prime or
            de-prime instructions if dense math.

Diff:
---
 gcc/config/rs6000/mma.md      | 247 ++++++++++++++++++++++++++----------------
 gcc/config/rs6000/rs6000-c.cc |   3 +
 gcc/config/rs6000/rs6000.cc   |  35 +++---
 3 files changed, 176 insertions(+), 109 deletions(-)

diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index c15543a1608..ba6eb71578e 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -551,190 +551,249 @@
   "dmxxextfdmr256 %0,%1,2"
   [(set_attr "type" "mma")])
 
-(define_insn "mma_<acc>"
+;; MMA instructions that do not use their accumulators as an input, still must
+;; not allow their vector operands to overlap the registers used by the
+;; accumulator.  We enforce this by marking the output as early clobber.  If we
+;; have dense math, we don't need the whole prime/de-prime action, so just make
+;; thse instructions be NOPs.
+
+(define_expand "mma_<acc>"
+  [(set (match_operand:XO 0 "register_operand")
+	(unspec:XO [(match_operand:XO 1 "register_operand")]
+		   MMA_ACC))]
+  "TARGET_MMA"
+{
+  if (TARGET_DENSE_MATH)
+    {
+      if (!rtx_equal_p (operands[0], operands[1]))
+	emit_move_insn (operands[0], operands[1]);
+      DONE;
+    }
+
+  /* Generate the prime/de-prime code.  */
+})
+
+(define_insn "*mma_<acc>"
   [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
 	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")]
 		    MMA_ACC))]
-  "TARGET_MMA"
+  "TARGET_MMA && !TARGET_DENSE_MATH"
   "<acc> %A0"
   [(set_attr "type" "mma")])
 
 ;; We can't have integer constants in XOmode so we wrap this in an
-;; UNSPEC_VOLATILE.
+;; UNSPEC_VOLATILE for the non-dense math case.  For dense math, we don't need
+;; to disable optimization and we can do a normal UNSPEC.
 
-(define_insn "mma_xxsetaccz"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=d")
+(define_expand "mma_xxsetaccz"
+  [(set (match_operand:XO 0 "register_operand")
 	(unspec_volatile:XO [(const_int 0)]
 			    UNSPECV_MMA_XXSETACCZ))]
   "TARGET_MMA"
+{
+  if (TARGET_DENSE_MATH)
+    {
+      emit_insn (gen_mma_xxsetaccz_dm (operands[0]));
+      DONE;
+    }
+})
+
+(define_insn "*mma_xxsetaccz_p10"
+  [(set (match_operand:XO 0 "fpr_reg_operand" "=d")
+	(unspec_volatile:XO [(const_int 0)]
+			    UNSPECV_MMA_XXSETACCZ))]
+  "TARGET_MMA && !TARGET_DENSE_MATH"
   "xxsetaccz %A0"
   [(set_attr "type" "mma")])
 
+
+(define_insn "mma_xxsetaccz_dm"
+  [(set (match_operand:XO 0 "dmr_operand" "=wD")
+	(unspec:XO [(const_int 0)]
+		   UNSPECV_MMA_XXSETACCZ))]
+  "TARGET_DENSE_MATH"
+  "dmsetdmrz %0"
+  [(set_attr "type" "mma")])
+
 (define_insn "mma_<vv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_VV))]
   "TARGET_MMA"
   "<vv> %A0,%x1,%x2"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_AVV))]
   "TARGET_MMA"
   "<avv> %A0,%x2,%x3"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<pv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_PV))]
   "TARGET_MMA"
   "<pv> %A0,%x1,%x2"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (match_operand:OO 2 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_APV))]
   "TARGET_MMA"
   "<apv> %A0,%x2,%x3"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i8>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "u8bit_cint_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "u8bit_cint_operand" "n,n,n")]
 		    MMA_VVI4I4I8))]
   "TARGET_MMA"
   "<vvi4i4i8> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "u8bit_cint_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "u8bit_cint_operand" "n,n,n")]
 		    MMA_AVVI4I4I8))]
   "TARGET_MMA"
   "<avvi4i4i8> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
 		    MMA_VVI4I4I2))]
   "TARGET_MMA"
   "<vvi4i4i2> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "const_0_to_3_operand" "n,n,n")]
 		    MMA_AVVI4I4I2))]
   "TARGET_MMA"
   "<avvi4i4i2> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")]
 		    MMA_VVI4I4))]
   "TARGET_MMA"
   "<vvi4i4> %A0,%x1,%x2,%3,%4"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
 		    MMA_AVVI4I4))]
   "TARGET_MMA"
   "<avvi4i4> %A0,%x2,%x3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<pvi4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_3_operand" "n,n,n")]
 		    MMA_PVI4I2))]
   "TARGET_MMA"
   "<pvi4i2> %A0,%x1,%x2,%3,%4"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
 		    MMA_APVI4I2))]
   "TARGET_MMA"
   "<apvi4i2> %A0,%x2,%x3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
 		    MMA_VVI4I4I4))]
   "TARGET_MMA"
   "<vvi4i4i4> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "const_0_to_15_operand" "n,n,n")]
 		    MMA_AVVI4I4I4))]
   "TARGET_MMA"
   "<avvi4i4i4> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
diff --git a/gcc/config/rs6000/rs6000-c.cc b/gcc/config/rs6000/rs6000-c.cc
index 2803014f2b6..baf1f4dc92b 100644
--- a/gcc/config/rs6000/rs6000-c.cc
+++ b/gcc/config/rs6000/rs6000-c.cc
@@ -600,6 +600,9 @@ rs6000_target_modify_macros (bool define_p, HOST_WIDE_INT flags)
   /* Tell the user if we support the MMA instructions.  */
   if ((flags & OPTION_MASK_MMA) != 0)
     rs6000_define_or_undefine_macro (define_p, "__MMA__");
+  /* Tell the user if we support the dense math instructions.  */
+  if ((flags & OPTION_MASK_DENSE_MATH) != 0)
+    rs6000_define_or_undefine_macro (define_p, "__PPC_DMR__");
   /* Whether pc-relative code is being generated.  */
   if ((flags & OPTION_MASK_PCREL) != 0)
     rs6000_define_or_undefine_macro (define_p, "__PCREL__");
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 807485f5890..9dac183b9fe 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -13891,8 +13891,13 @@ print_operand (FILE *file, rtx x, int code)
 	 overlapping with the FPR registers.  */
       if (!REG_P (x))
 	output_operand_lossage ("invalid %%A value");
-      else if (TARGET_DENSE_MATH && DMR_REGNO_P (REGNO (x)))
-	fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
+      else if (TARGET_DENSE_MATH)
+	{
+	  if (DMR_REGNO_P (REGNO (x)))
+	    fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
+	  else
+	    output_operand_lossage ("%%A operand is not a DMR");
+	}
       else if (!FP_REGNO_P (REGNO (x)) || (REGNO (x) % 4) != 0)
 	output_operand_lossage ("invalid %%A value");
       else
@@ -27335,7 +27340,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
 	  /* If we are reading an accumulator register, we have to
 	     deprime it before we can access it.  */
-	  if (TARGET_MMA
+	  if (TARGET_MMA && !TARGET_DENSE_MATH
 	      && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	    emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27367,9 +27372,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 	      emit_insn (gen_rtx_SET (dst2, src2));
 	    }
 
-	  /* If we are writing an accumulator register, we have to
-	     prime it after we've written it.  */
-	  if (TARGET_MMA
+	  /* If we are writing an accumulator register that overlaps with the
+	     FPR registers, we have to prime it after we've written it.  */
+	  if (TARGET_MMA && !TARGET_DENSE_MATH
 	      && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	    emit_insn (gen_mma_xxmtacc (dst, dst));
 
@@ -27438,9 +27443,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 	      emit_insn (gen_rtx_SET (dst_i, op));
 	    }
 
-	  /* We are writing an accumulator register, so we have to
-	     prime it after we've written it.  */
-	  if (GET_MODE (src) == XOmode)
+	  /* On systems without dense math where accumulators overlap with the
+	     vector registers, we have to prime it after we've written it.  */
+	  if (GET_MODE (src) == XOmode && !TARGET_DENSE_MATH)
 	    emit_insn (gen_mma_xxmtacc (dst, dst));
 
 	  return;
@@ -27451,9 +27456,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
   if (REG_P (src) && REG_P (dst) && (REGNO (src) < REGNO (dst)))
     {
-      /* If we are reading an accumulator register, we have to
-	 deprime it before we can access it.  */
-      if (TARGET_MMA
+      /* If we are reading an accumulator register and we don't have dense
+	 math, we have to deprime it before we can access it.  */
+      if (TARGET_MMA && !TARGET_DENSE_MATH
 	  && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27481,7 +27486,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are writing an accumulator register, we have to
 	 prime it after we've written it.  */
-      if (TARGET_MMA
+      if (TARGET_MMA && !TARGET_DENSE_MATH
 	  && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	emit_insn (gen_mma_xxmtacc (dst, dst));
     }
@@ -27618,7 +27623,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are reading an accumulator register, we have to
 	 deprime it before we can access it.  */
-      if (TARGET_MMA && REG_P (src)
+      if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (src)
 	  && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27650,7 +27655,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are writing an accumulator register, we have to
 	 prime it after we've written it.  */
-      if (TARGET_MMA && REG_P (dst)
+      if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (dst)
 	  && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	emit_insn (gen_mma_xxmtacc (dst, dst));

^ permalink raw reply	[flat|nested] 3+ messages in thread

* [gcc(refs/users/meissner/heads/dmf007)] PowerPC: Make MMA insns support DMR registers.
@ 2023-01-28  2:08 Michael Meissner
  0 siblings, 0 replies; 3+ messages in thread
From: Michael Meissner @ 2023-01-28  2:08 UTC (permalink / raw)
  To: gcc-cvs

https://gcc.gnu.org/g:95818dbb1709301fd93fe96aa51634060263c3b8

commit 95818dbb1709301fd93fe96aa51634060263c3b8
Author: Michael Meissner <meissner@linux.ibm.com>
Date:   Fri Jan 27 21:04:13 2023 -0500

    PowerPC: Make MMA insns support DMR registers.
    
    This patch changes the MMA instructions to use either FPR registers
    (-mcpu=power10) or DMRs (-mcpu=future).  In this patch, the existing MMA
    instruction names are used.
    
    A macro (__PPC_DMR__) is defined if the MMA instructions use the DMRs.
    
    The patches have been tested on the following platforms.  I added the patches
    for PR target/107299 that I submitted on November 2nd before doing the builds so
    that GCC would build on systems using IEEE 128-bit long double.
        *   https://gcc.gnu.org/pipermail/gcc-patches/2022-November/604834.html
    
    There were no regressions with doing bootstrap builds and running the regression
    tests:
    
        1)  Power10 LE using --with-cpu=power10 --with-long-double-format=ieee;
        2)  Power10 LE using --with-cpu=power10 --with-long-double-format=ibm;
        3)  Power9 LE using --with-cpu=power9 --with-long-double-format=ibm; and
        4)  Power8 BE using --with-cpu=power8 (both 32-bit & 64-bit tested).
    
    Can I check this patch into the GCC 13 master branch?
    
    2023-01-27   Michael Meissner  <meissner@linux.ibm.com>
    
    gcc/
    
            * config/rs6000/mma.md (mma_<acc>): New define_expand to handle
            mma_<acc> for dense math and non dense math.
            (mma_<acc> insn): Restrict to non dense math.
            (mma_xxsetaccz): Convert to define_expand to handle non dense math and
            dense math.
            (mma_xxsetaccz_p10): Rename from mma_xxsetaccz and restrict usage to non
            dense math.
            (mma_xxsetaccz_dm): Dense math version of mma_xxsetaccz.
            (mma_<vv>): Add support for dense math.
            (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/rs6000-c.cc (rs6000_target_modify_macros): Define
            __PPC_DMR__ if we have dense math instructions.
            * config/rs6000/rs6000.cc (print_operand): Make %A handle only DMRs if
            dense math and only FPRs if not dense math.
            (rs6000_split_multireg_move): Do not generate the xxmtacc instruction to
            prime the DMR registers or the xxmfacc instruction to de-prime
            instructions if we have dense math register support.

Diff:
---
 gcc/config/rs6000/mma.md      | 247 ++++++++++++++++++++++++++----------------
 gcc/config/rs6000/rs6000-c.cc |   3 +
 gcc/config/rs6000/rs6000.cc   |  35 +++---
 3 files changed, 176 insertions(+), 109 deletions(-)

diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index 59ca6835f7c..27fa89e12c2 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -552,190 +552,249 @@
   "dmxxextfdmr256 %0,%1,2"
   [(set_attr "type" "mma")])
 
-(define_insn "mma_<acc>"
+;; MMA instructions that do not use their accumulators as an input, still must
+;; not allow their vector operands to overlap the registers used by the
+;; accumulator.  We enforce this by marking the output as early clobber.  If we
+;; have dense math, we don't need the whole prime/de-prime action, so just make
+;; thse instructions be NOPs.
+
+(define_expand "mma_<acc>"
+  [(set (match_operand:XO 0 "register_operand")
+	(unspec:XO [(match_operand:XO 1 "register_operand")]
+		   MMA_ACC))]
+  "TARGET_MMA"
+{
+  if (TARGET_DENSE_MATH)
+    {
+      if (!rtx_equal_p (operands[0], operands[1]))
+	emit_move_insn (operands[0], operands[1]);
+      DONE;
+    }
+
+  /* Generate the prime/de-prime code.  */
+})
+
+(define_insn "*mma_<acc>"
   [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
 	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")]
 		    MMA_ACC))]
-  "TARGET_MMA"
+  "TARGET_MMA && !TARGET_DENSE_MATH"
   "<acc> %A0"
   [(set_attr "type" "mma")])
 
 ;; We can't have integer constants in XOmode so we wrap this in an
-;; UNSPEC_VOLATILE.
+;; UNSPEC_VOLATILE for the non-dense math case.  For dense math, we don't need
+;; to disable optimization and we can do a normal UNSPEC.
 
-(define_insn "mma_xxsetaccz"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=d")
+(define_expand "mma_xxsetaccz"
+  [(set (match_operand:XO 0 "register_operand")
 	(unspec_volatile:XO [(const_int 0)]
 			    UNSPECV_MMA_XXSETACCZ))]
   "TARGET_MMA"
+{
+  if (TARGET_DENSE_MATH)
+    {
+      emit_insn (gen_mma_xxsetaccz_dm (operands[0]));
+      DONE;
+    }
+})
+
+(define_insn "*mma_xxsetaccz_p10"
+  [(set (match_operand:XO 0 "fpr_reg_operand" "=d")
+	(unspec_volatile:XO [(const_int 0)]
+			    UNSPECV_MMA_XXSETACCZ))]
+  "TARGET_MMA && !TARGET_DENSE_MATH"
   "xxsetaccz %A0"
   [(set_attr "type" "mma")])
 
+
+(define_insn "mma_xxsetaccz_dm"
+  [(set (match_operand:XO 0 "dmr_operand" "=wD")
+	(unspec:XO [(const_int 0)]
+		   UNSPECV_MMA_XXSETACCZ))]
+  "TARGET_DENSE_MATH"
+  "dmsetdmrz %0"
+  [(set_attr "type" "mma")])
+
 (define_insn "mma_<vv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_VV))]
   "TARGET_MMA"
   "<vv> %A0,%x1,%x2"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_AVV))]
   "TARGET_MMA"
   "<avv> %A0,%x2,%x3"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<pv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_PV))]
   "TARGET_MMA"
   "<pv> %A0,%x1,%x2"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (match_operand:OO 2 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_APV))]
   "TARGET_MMA"
   "<apv> %A0,%x2,%x3"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i8>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "u8bit_cint_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "u8bit_cint_operand" "n,n,n")]
 		    MMA_VVI4I4I8))]
   "TARGET_MMA"
   "<vvi4i4i8> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "u8bit_cint_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "u8bit_cint_operand" "n,n,n")]
 		    MMA_AVVI4I4I8))]
   "TARGET_MMA"
   "<avvi4i4i8> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
 		    MMA_VVI4I4I2))]
   "TARGET_MMA"
   "<vvi4i4i2> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "const_0_to_3_operand" "n,n,n")]
 		    MMA_AVVI4I4I2))]
   "TARGET_MMA"
   "<avvi4i4i2> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")]
 		    MMA_VVI4I4))]
   "TARGET_MMA"
   "<vvi4i4> %A0,%x1,%x2,%3,%4"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
 		    MMA_AVVI4I4))]
   "TARGET_MMA"
   "<avvi4i4> %A0,%x2,%x3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<pvi4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_3_operand" "n,n,n")]
 		    MMA_PVI4I2))]
   "TARGET_MMA"
   "<pvi4i2> %A0,%x1,%x2,%3,%4"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
 		    MMA_APVI4I2))]
   "TARGET_MMA"
   "<apvi4i2> %A0,%x2,%x3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
 		    MMA_VVI4I4I4))]
   "TARGET_MMA"
   "<vvi4i4i4> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "const_0_to_15_operand" "n,n,n")]
 		    MMA_AVVI4I4I4))]
   "TARGET_MMA"
   "<avvi4i4i4> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
diff --git a/gcc/config/rs6000/rs6000-c.cc b/gcc/config/rs6000/rs6000-c.cc
index 2803014f2b6..baf1f4dc92b 100644
--- a/gcc/config/rs6000/rs6000-c.cc
+++ b/gcc/config/rs6000/rs6000-c.cc
@@ -600,6 +600,9 @@ rs6000_target_modify_macros (bool define_p, HOST_WIDE_INT flags)
   /* Tell the user if we support the MMA instructions.  */
   if ((flags & OPTION_MASK_MMA) != 0)
     rs6000_define_or_undefine_macro (define_p, "__MMA__");
+  /* Tell the user if we support the dense math instructions.  */
+  if ((flags & OPTION_MASK_DENSE_MATH) != 0)
+    rs6000_define_or_undefine_macro (define_p, "__PPC_DMR__");
   /* Whether pc-relative code is being generated.  */
   if ((flags & OPTION_MASK_PCREL) != 0)
     rs6000_define_or_undefine_macro (define_p, "__PCREL__");
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 5bf06afcdeb..908d0642a68 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -13909,8 +13909,13 @@ print_operand (FILE *file, rtx x, int code)
 	 overlapping with the FPR registers.  */
       if (!REG_P (x))
 	output_operand_lossage ("invalid %%A value");
-      else if (TARGET_DENSE_MATH && DMR_REGNO_P (REGNO (x)))
-	fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
+      else if (TARGET_DENSE_MATH)
+	{
+	  if (DMR_REGNO_P (REGNO (x)))
+	    fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
+	  else
+	    output_operand_lossage ("%%A operand is not a DMR");
+	}
       else if (!FP_REGNO_P (REGNO (x)) || (REGNO (x) % 4) != 0)
 	output_operand_lossage ("invalid %%A value");
       else
@@ -27355,7 +27360,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
 	  /* If we are reading an accumulator register, we have to
 	     deprime it before we can access it.  */
-	  if (TARGET_MMA
+	  if (TARGET_MMA && !TARGET_DENSE_MATH
 	      && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	    emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27387,9 +27392,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 	      emit_insn (gen_rtx_SET (dst2, src2));
 	    }
 
-	  /* If we are writing an accumulator register, we have to
-	     prime it after we've written it.  */
-	  if (TARGET_MMA
+	  /* If we are writing an accumulator register that overlaps with the
+	     FPR registers, we have to prime it after we've written it.  */
+	  if (TARGET_MMA && !TARGET_DENSE_MATH
 	      && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	    emit_insn (gen_mma_xxmtacc (dst, dst));
 
@@ -27458,9 +27463,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 	      emit_insn (gen_rtx_SET (dst_i, op));
 	    }
 
-	  /* We are writing an accumulator register, so we have to
-	     prime it after we've written it.  */
-	  if (GET_MODE (src) == XOmode)
+	  /* On systems without dense math where accumulators overlap with the
+	     vector registers, we have to prime it after we've written it.  */
+	  if (GET_MODE (src) == XOmode && !TARGET_DENSE_MATH)
 	    emit_insn (gen_mma_xxmtacc (dst, dst));
 
 	  return;
@@ -27471,9 +27476,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
   if (REG_P (src) && REG_P (dst) && (REGNO (src) < REGNO (dst)))
     {
-      /* If we are reading an accumulator register, we have to
-	 deprime it before we can access it.  */
-      if (TARGET_MMA
+      /* If we are reading an accumulator register and we don't have dense
+	 math, we have to deprime it before we can access it.  */
+      if (TARGET_MMA && !TARGET_DENSE_MATH
 	  && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27501,7 +27506,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are writing an accumulator register, we have to
 	 prime it after we've written it.  */
-      if (TARGET_MMA
+      if (TARGET_MMA && !TARGET_DENSE_MATH
 	  && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	emit_insn (gen_mma_xxmtacc (dst, dst));
     }
@@ -27638,7 +27643,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are reading an accumulator register, we have to
 	 deprime it before we can access it.  */
-      if (TARGET_MMA && REG_P (src)
+      if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (src)
 	  && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27670,7 +27675,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are writing an accumulator register, we have to
 	 prime it after we've written it.  */
-      if (TARGET_MMA && REG_P (dst)
+      if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (dst)
 	  && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	emit_insn (gen_mma_xxmtacc (dst, dst));

^ permalink raw reply	[flat|nested] 3+ messages in thread

* [gcc(refs/users/meissner/heads/dmf007)] PowerPC: Make MMA insns support DMR registers.
@ 2023-01-23 21:18 Michael Meissner
  0 siblings, 0 replies; 3+ messages in thread
From: Michael Meissner @ 2023-01-23 21:18 UTC (permalink / raw)
  To: gcc-cvs

https://gcc.gnu.org/g:57d5ad31d19a7f453bbc1c520f1635e0dd5b7a48

commit 57d5ad31d19a7f453bbc1c520f1635e0dd5b7a48
Author: Michael Meissner <meissner@linux.ibm.com>
Date:   Fri Jan 20 19:29:18 2023 -0500

    PowerPC: Make MMA insns support DMR registers.
    
    This patch changes the MMA instructions to use either FPR registers
    (-mcpu=power10) or DMRs (-mcpu=future).  In this patch, the existing MMA
    instruction names are used.
    
    A macro (__PPC_DMR__) is defined if the MMA instructions use the DMRs.
    
    The patches have been tested on the following platforms.  I added the patches
    for PR target/107299 that I submitted on November 2nd before doing the builds so
    that GCC would build on systems using IEEE 128-bit long double.
        *   https://gcc.gnu.org/pipermail/gcc-patches/2022-November/604834.html
    
    There were no regressions with doing bootstrap builds and running the regression
    tests:
    
        1)  Power10 LE using --with-cpu=power10 --with-long-double-format=ieee;
        2)  Power10 LE using --with-cpu=power10 --with-long-double-format=ibm;
        3)  Power9 LE using --with-cpu=power9 --with-long-double-format=ibm; and
        4)  Power8 BE using --with-cpu=power8 (both 32-bit & 64-bit tested).
    
    Can I check this patch into the GCC 13 master branch?
    
    2023-01-20   Michael Meissner  <meissner@linux.ibm.com>
    
    gcc/
    
            * config/rs6000/mma.md (mma_<acc>): New define_expand to handle
            mma_<acc> for dense math and non dense math.
            (mma_<acc> insn): Restrict to non dense math.
            (mma_xxsetaccz): Convert to define_expand to handle non dense math and
            dense math.
            (mma_xxsetaccz_p10): Rename from mma_xxsetaccz and restrict usage to non
            dense math.
            (mma_xxsetaccz_dm): Dense math version of mma_xxsetaccz.
            (mma_<vv>): Add support for dense math.
            (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/rs6000-c.cc (rs6000_target_modify_macros): Define
            __PPC_DMR__ if we have dense math instructions.
            * config/rs6000/rs6000.cc (print_operand): Make %A handle only DMRs if
            dense math and only FPRs if not dense math.
            (rs6000_split_multireg_move): Do not generate accumulator prime or
            de-prime instructions if dense math.

Diff:
---
 gcc/config/rs6000/mma.md      | 247 ++++++++++++++++++++++++++----------------
 gcc/config/rs6000/rs6000-c.cc |   3 +
 gcc/config/rs6000/rs6000.cc   |  35 +++---
 3 files changed, 176 insertions(+), 109 deletions(-)

diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index c15543a1608..ba6eb71578e 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -551,190 +551,249 @@
   "dmxxextfdmr256 %0,%1,2"
   [(set_attr "type" "mma")])
 
-(define_insn "mma_<acc>"
+;; MMA instructions that do not use their accumulators as an input, still must
+;; not allow their vector operands to overlap the registers used by the
+;; accumulator.  We enforce this by marking the output as early clobber.  If we
+;; have dense math, we don't need the whole prime/de-prime action, so just make
+;; thse instructions be NOPs.
+
+(define_expand "mma_<acc>"
+  [(set (match_operand:XO 0 "register_operand")
+	(unspec:XO [(match_operand:XO 1 "register_operand")]
+		   MMA_ACC))]
+  "TARGET_MMA"
+{
+  if (TARGET_DENSE_MATH)
+    {
+      if (!rtx_equal_p (operands[0], operands[1]))
+	emit_move_insn (operands[0], operands[1]);
+      DONE;
+    }
+
+  /* Generate the prime/de-prime code.  */
+})
+
+(define_insn "*mma_<acc>"
   [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
 	(unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")]
 		    MMA_ACC))]
-  "TARGET_MMA"
+  "TARGET_MMA && !TARGET_DENSE_MATH"
   "<acc> %A0"
   [(set_attr "type" "mma")])
 
 ;; We can't have integer constants in XOmode so we wrap this in an
-;; UNSPEC_VOLATILE.
+;; UNSPEC_VOLATILE for the non-dense math case.  For dense math, we don't need
+;; to disable optimization and we can do a normal UNSPEC.
 
-(define_insn "mma_xxsetaccz"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=d")
+(define_expand "mma_xxsetaccz"
+  [(set (match_operand:XO 0 "register_operand")
 	(unspec_volatile:XO [(const_int 0)]
 			    UNSPECV_MMA_XXSETACCZ))]
   "TARGET_MMA"
+{
+  if (TARGET_DENSE_MATH)
+    {
+      emit_insn (gen_mma_xxsetaccz_dm (operands[0]));
+      DONE;
+    }
+})
+
+(define_insn "*mma_xxsetaccz_p10"
+  [(set (match_operand:XO 0 "fpr_reg_operand" "=d")
+	(unspec_volatile:XO [(const_int 0)]
+			    UNSPECV_MMA_XXSETACCZ))]
+  "TARGET_MMA && !TARGET_DENSE_MATH"
   "xxsetaccz %A0"
   [(set_attr "type" "mma")])
 
+
+(define_insn "mma_xxsetaccz_dm"
+  [(set (match_operand:XO 0 "dmr_operand" "=wD")
+	(unspec:XO [(const_int 0)]
+		   UNSPECV_MMA_XXSETACCZ))]
+  "TARGET_DENSE_MATH"
+  "dmsetdmrz %0"
+  [(set_attr "type" "mma")])
+
 (define_insn "mma_<vv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_VV))]
   "TARGET_MMA"
   "<vv> %A0,%x1,%x2"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_AVV))]
   "TARGET_MMA"
   "<avv> %A0,%x2,%x3"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<pv>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 2 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_PV))]
   "TARGET_MMA"
   "<pv> %A0,%x1,%x2"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (match_operand:OO 2 "vsx_register_operand" "v,?wa")
-		    (match_operand:V16QI 3 "vsx_register_operand" "v,?wa")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")]
 		    MMA_APV))]
   "TARGET_MMA"
   "<apv> %A0,%x2,%x3"
-  [(set_attr "type" "mma")])
+  [(set_attr "type" "mma")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i8>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "u8bit_cint_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "u8bit_cint_operand" "n,n,n")]
 		    MMA_VVI4I4I8))]
   "TARGET_MMA"
   "<vvi4i4i8> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "u8bit_cint_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "u8bit_cint_operand" "n,n,n")]
 		    MMA_AVVI4I4I8))]
   "TARGET_MMA"
   "<avvi4i4i8> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
 		    MMA_VVI4I4I2))]
   "TARGET_MMA"
   "<vvi4i4i2> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "const_0_to_3_operand" "n,n,n")]
 		    MMA_AVVI4I4I2))]
   "TARGET_MMA"
   "<avvi4i4i2> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")]
 		    MMA_VVI4I4))]
   "TARGET_MMA"
   "<vvi4i4> %A0,%x1,%x2,%3,%4"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
 		    MMA_AVVI4I4))]
   "TARGET_MMA"
   "<avvi4i4> %A0,%x2,%x3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<pvi4i2>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_3_operand" "n,n,n")]
 		    MMA_PVI4I2))]
   "TARGET_MMA"
   "<pvi4i2> %A0,%x1,%x2,%3,%4"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_3_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:OO 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_3_operand" "n,n,n")]
 		    MMA_APVI4I2))]
   "TARGET_MMA"
   "<apvi4i2> %A0,%x2,%x3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (define_insn "mma_<vvi4i4i4>"
-  [(set (match_operand:XO 0 "fpr_reg_operand" "=&d,&d")
-	(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")
-		    (match_operand:SI 4 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 3 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")]
 		    MMA_VVI4I4I4))]
   "TARGET_MMA"
   "<vvi4i4i4> %A0,%x1,%x2,%3,%4,%5"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
 
 (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")
-		    (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")
-		    (match_operand:SI 5 "const_0_to_15_operand" "n,n")
-		    (match_operand:SI 6 "const_0_to_15_operand" "n,n")]
+  [(set (match_operand:XO 0 "accumulator_operand" "=wD,&d,&d")
+	(unspec:XO [(match_operand:XO 1 "accumulator_operand" "0,0,0")
+		    (match_operand:V16QI 2 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:V16QI 3 "vsx_register_operand" "wa,v,?wa")
+		    (match_operand:SI 4 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 5 "const_0_to_15_operand" "n,n,n")
+		    (match_operand:SI 6 "const_0_to_15_operand" "n,n,n")]
 		    MMA_AVVI4I4I4))]
   "TARGET_MMA"
   "<avvi4i4i4> %A0,%x2,%x3,%4,%5,%6"
   [(set_attr "type" "mma")
-   (set_attr "prefixed" "yes")])
+   (set_attr "prefixed" "yes")
+   (set_attr "isa" "dm,not_dm,not_dm")])
diff --git a/gcc/config/rs6000/rs6000-c.cc b/gcc/config/rs6000/rs6000-c.cc
index 2803014f2b6..baf1f4dc92b 100644
--- a/gcc/config/rs6000/rs6000-c.cc
+++ b/gcc/config/rs6000/rs6000-c.cc
@@ -600,6 +600,9 @@ rs6000_target_modify_macros (bool define_p, HOST_WIDE_INT flags)
   /* Tell the user if we support the MMA instructions.  */
   if ((flags & OPTION_MASK_MMA) != 0)
     rs6000_define_or_undefine_macro (define_p, "__MMA__");
+  /* Tell the user if we support the dense math instructions.  */
+  if ((flags & OPTION_MASK_DENSE_MATH) != 0)
+    rs6000_define_or_undefine_macro (define_p, "__PPC_DMR__");
   /* Whether pc-relative code is being generated.  */
   if ((flags & OPTION_MASK_PCREL) != 0)
     rs6000_define_or_undefine_macro (define_p, "__PCREL__");
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 807485f5890..9dac183b9fe 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -13891,8 +13891,13 @@ print_operand (FILE *file, rtx x, int code)
 	 overlapping with the FPR registers.  */
       if (!REG_P (x))
 	output_operand_lossage ("invalid %%A value");
-      else if (TARGET_DENSE_MATH && DMR_REGNO_P (REGNO (x)))
-	fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
+      else if (TARGET_DENSE_MATH)
+	{
+	  if (DMR_REGNO_P (REGNO (x)))
+	    fprintf (file, "%d", REGNO (x) - FIRST_DMR_REGNO);
+	  else
+	    output_operand_lossage ("%%A operand is not a DMR");
+	}
       else if (!FP_REGNO_P (REGNO (x)) || (REGNO (x) % 4) != 0)
 	output_operand_lossage ("invalid %%A value");
       else
@@ -27335,7 +27340,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
 	  /* If we are reading an accumulator register, we have to
 	     deprime it before we can access it.  */
-	  if (TARGET_MMA
+	  if (TARGET_MMA && !TARGET_DENSE_MATH
 	      && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	    emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27367,9 +27372,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 	      emit_insn (gen_rtx_SET (dst2, src2));
 	    }
 
-	  /* If we are writing an accumulator register, we have to
-	     prime it after we've written it.  */
-	  if (TARGET_MMA
+	  /* If we are writing an accumulator register that overlaps with the
+	     FPR registers, we have to prime it after we've written it.  */
+	  if (TARGET_MMA && !TARGET_DENSE_MATH
 	      && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	    emit_insn (gen_mma_xxmtacc (dst, dst));
 
@@ -27438,9 +27443,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 	      emit_insn (gen_rtx_SET (dst_i, op));
 	    }
 
-	  /* We are writing an accumulator register, so we have to
-	     prime it after we've written it.  */
-	  if (GET_MODE (src) == XOmode)
+	  /* On systems without dense math where accumulators overlap with the
+	     vector registers, we have to prime it after we've written it.  */
+	  if (GET_MODE (src) == XOmode && !TARGET_DENSE_MATH)
 	    emit_insn (gen_mma_xxmtacc (dst, dst));
 
 	  return;
@@ -27451,9 +27456,9 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
   if (REG_P (src) && REG_P (dst) && (REGNO (src) < REGNO (dst)))
     {
-      /* If we are reading an accumulator register, we have to
-	 deprime it before we can access it.  */
-      if (TARGET_MMA
+      /* If we are reading an accumulator register and we don't have dense
+	 math, we have to deprime it before we can access it.  */
+      if (TARGET_MMA && !TARGET_DENSE_MATH
 	  && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27481,7 +27486,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are writing an accumulator register, we have to
 	 prime it after we've written it.  */
-      if (TARGET_MMA
+      if (TARGET_MMA && !TARGET_DENSE_MATH
 	  && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	emit_insn (gen_mma_xxmtacc (dst, dst));
     }
@@ -27618,7 +27623,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are reading an accumulator register, we have to
 	 deprime it before we can access it.  */
-      if (TARGET_MMA && REG_P (src)
+      if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (src)
 	  && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
 	emit_insn (gen_mma_xxmfacc (src, src));
 
@@ -27650,7 +27655,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
 
       /* If we are writing an accumulator register, we have to
 	 prime it after we've written it.  */
-      if (TARGET_MMA && REG_P (dst)
+      if (TARGET_MMA && !TARGET_DENSE_MATH && REG_P (dst)
 	  && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
 	emit_insn (gen_mma_xxmtacc (dst, dst));

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2023-01-28  2:08 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-01-21  2:54 [gcc(refs/users/meissner/heads/dmf007)] PowerPC: Make MMA insns support DMR registers Michael Meissner
2023-01-23 21:18 Michael Meissner
2023-01-28  2:08 Michael Meissner

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).