[PATCH 04/18] rs6000: Handle some recent MMA builtin changes

[Bill Schmidt <wschmidt@linux.ibm.com>]

Peter Bergner recently added two new builtins __builtin_vsx_lxvp and
__builtin_vsx_stxvp.  These happened to break a pattern in MMA builtins that
I had been using to automate gimple folding of MMA builtins.  Previously,
every MMA function that could be folded had an associated internal function
that it was folded into.  The LXVP/STXVP builtins are just folded directly
into memory operations.

Instead of relying on this pattern, this patch adds a new attribute to
builtins called "mmaint," which is set for all MMA builtins that have an
associated internal builtin.  The naming convention that adds _INTERNAL to
the builtin index name remains.

The rest of the patch is just duplicating Peter's patch, using the new
builtin infrastructure.

2021-08-23  Bill Schmidt  <wschmidt@linux.ibm.com>

gcc/
	* config/rs6000/rs6000-builtin-new.def (ASSEMBLE_ACC): Add mmaint flag.
	(ASSEMBLE_PAIR): Likewise.
	(BUILD_ACC): Likewise.
	(DISASSEMBLE_ACC): Likewise.
	(DISASSEMBLE_PAIR): Likewise.
	(PMXVBF16GER2): Likewise.
	(PMXVBF16GER2NN): Likewise.
	(PMXVBF16GER2NP): Likewise.
	(PMXVBF16GER2PN): Likewise.
	(PMXVBF16GER2PP): Likewise.
	(PMXVF16GER2): Likewise.
	(PMXVF16GER2NN): Likewise.
	(PMXVF16GER2NP): Likewise.
	(PMXVF16GER2PN): Likewise.
	(PMXVF16GER2PP): Likewise.
	(PMXVF32GER): Likewise.
	(PMXVF32GERNN): Likewise.
	(PMXVF32GERNP): Likewise.
	(PMXVF32GERPN): Likewise.
	(PMXVF32GERPP): Likewise.
	(PMXVF64GER): Likewise.
	(PMXVF64GERNN): Likewise.
	(PMXVF64GERNP): Likewise.
	(PMXVF64GERPN): Likewise.
	(PMXVF64GERPP): Likewise.
	(PMXVI16GER2): Likewise.
	(PMXVI16GER2PP): Likewise.
	(PMXVI16GER2S): Likewise.
	(PMXVI16GER2SPP): Likewise.
	(PMXVI4GER8): Likewise.
	(PMXVI4GER8PP): Likewise.
	(PMXVI8GER4): Likewise.
	(PMXVI8GER4PP): Likewise.
	(PMXVI8GER4SPP): Likewise.
	(XVBF16GER2): Likewise.
	(XVBF16GER2NN): Likewise.
	(XVBF16GER2NP): Likewise.
	(XVBF16GER2PN): Likewise.
	(XVBF16GER2PP): Likewise.
	(XVF16GER2): Likewise.
	(XVF16GER2NN): Likewise.
	(XVF16GER2NP): Likewise.
	(XVF16GER2PN): Likewise.
	(XVF16GER2PP): Likewise.
	(XVF32GER): Likewise.
	(XVF32GERNN): Likewise.
	(XVF32GERNP): Likewise.
	(XVF32GERPN): Likewise.
	(XVF32GERPP): Likewise.
	(XVF64GER): Likewise.
	(XVF64GERNN): Likewise.
	(XVF64GERNP): Likewise.
	(XVF64GERPN): Likewise.
	(XVF64GERPP): Likewise.
	(XVI16GER2): Likewise.
	(XVI16GER2PP): Likewise.
	(XVI16GER2S): Likewise.
	(XVI16GER2SPP): Likewise.
	(XVI4GER8): Likewise.
	(XVI4GER8PP): Likewise.
	(XVI8GER4): Likewise.
	(XVI8GER4PP): Likewise.
	(XVI8GER4SPP): Likewise.
	(XXMFACC): Likewise.
	(XXMTACC): Likewise.
	(XXSETACCZ): Likewise.
	(ASSEMBLE_PAIR_V): Likewise.
	(BUILD_PAIR): Likewise.
	(DISASSEMBLE_PAIR_V): Likewise.
	(LXVP): New.
	(STXVP): New.
	* config/rs6000/rs6000-call.c
	(rs6000_gimple_fold_new_mma_builtin): Handle RS6000_BIF_LXVP and
	RS6000_BIF_STXVP.
	* config/rs6000/rs6000-gen-builtins.c (attrinfo): Add ismmaint.
	(parse_bif_attrs): Handle ismmaint.
	(write_decls): Add bif_mmaint_bit and bif_is_mmaint.
	(write_bif_static_init): Handle ismmaint.
---
 gcc/config/rs6000/rs6000-builtin-new.def | 145 ++++++++++++-----------
 gcc/config/rs6000/rs6000-call.c          |  38 +++++-
 gcc/config/rs6000/rs6000-gen-builtins.c  |  38 +++---
 3 files changed, 135 insertions(+), 86 deletions(-)

diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def
index a8c6b9e988f..1966516551e 100644
--- a/gcc/config/rs6000/rs6000-builtin-new.def
+++ b/gcc/config/rs6000/rs6000-builtin-new.def
@@ -129,6 +129,7 @@
 ;   mma      Needs special handling for MMA
 ;   quad     MMA instruction using a register quad as an input operand
 ;   pair     MMA instruction using a register pair as an input operand
+;   mmaint   MMA instruction expanding to internal call at GIMPLE time
 ;   no32bit  Not valid for TARGET_32BIT
 ;   32bit    Requires different handling for TARGET_32BIT
 ;   cpu      This is a "cpu_is" or "cpu_supports" builtin
@@ -3584,415 +3585,421 @@
 
 [mma]
   void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc);
-    ASSEMBLE_ACC nothing {mma}
+    ASSEMBLE_ACC nothing {mma,mmaint}
 
   v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc);
     ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma}
 
   void __builtin_mma_assemble_pair (v256 *, vuc, vuc);
-    ASSEMBLE_PAIR nothing {mma}
+    ASSEMBLE_PAIR nothing {mma,mmaint}
 
   v256 __builtin_mma_assemble_pair_internal (vuc, vuc);
     ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma}
 
   void __builtin_mma_build_acc (v512 *, vuc, vuc, vuc, vuc);
-    BUILD_ACC nothing {mma}
+    BUILD_ACC nothing {mma,mmaint}
 
   v512 __builtin_mma_build_acc_internal (vuc, vuc, vuc, vuc);
     BUILD_ACC_INTERNAL mma_assemble_acc {mma}
 
   void __builtin_mma_disassemble_acc (void *, v512 *);
-    DISASSEMBLE_ACC nothing {mma,quad}
+    DISASSEMBLE_ACC nothing {mma,quad,mmaint}
 
   vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>);
     DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma}
 
   void __builtin_mma_disassemble_pair (void *, v256 *);
-    DISASSEMBLE_PAIR nothing {mma,pair}
+    DISASSEMBLE_PAIR nothing {mma,pair,mmaint}
 
   vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>);
     DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma}
 
   void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVBF16GER2 nothing {mma}
+    PMXVBF16GER2 nothing {mma,mmaint}
 
   v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma}
 
   void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVBF16GER2NN nothing {mma,quad}
+    PMXVBF16GER2NN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad}
 
   void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVBF16GER2NP nothing {mma,quad}
+    PMXVBF16GER2NP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad}
 
   void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVBF16GER2PN nothing {mma,quad}
+    PMXVBF16GER2PN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad}
 
   void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVBF16GER2PP nothing {mma,quad}
+    PMXVBF16GER2PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad}
 
   void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVF16GER2 nothing {mma}
+    PMXVF16GER2 nothing {mma,mmaint}
 
   v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma}
 
   void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVF16GER2NN nothing {mma,quad}
+    PMXVF16GER2NN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad}
 
   void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVF16GER2NP nothing {mma,quad}
+    PMXVF16GER2NP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad}
 
   void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVF16GER2PN nothing {mma,quad}
+    PMXVF16GER2PN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad}
 
   void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVF16GER2PP nothing {mma,quad}
+    PMXVF16GER2PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad}
 
   void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>);
-    PMXVF32GER nothing {mma}
+    PMXVF32GER nothing {mma,mmaint}
 
   v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>);
     PMXVF32GER_INTERNAL mma_pmxvf32ger {mma}
 
   void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>);
-    PMXVF32GERNN nothing {mma,quad}
+    PMXVF32GERNN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>);
     PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad}
 
   void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>);
-    PMXVF32GERNP nothing {mma,quad}
+    PMXVF32GERNP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>);
     PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad}
 
   void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>);
-    PMXVF32GERPN nothing {mma,quad}
+    PMXVF32GERPN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>);
     PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad}
 
   void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>);
-    PMXVF32GERPP nothing {mma,quad}
+    PMXVF32GERPP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>);
     PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad}
 
   void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>);
-    PMXVF64GER nothing {mma,pair}
+    PMXVF64GER nothing {mma,pair,mmaint}
 
   v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>);
     PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair}
 
   void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>);
-    PMXVF64GERNN nothing {mma,pair,quad}
+    PMXVF64GERNN nothing {mma,pair,quad,mmaint}
 
   v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>);
     PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad}
 
   void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>);
-    PMXVF64GERNP nothing {mma,pair,quad}
+    PMXVF64GERNP nothing {mma,pair,quad,mmaint}
 
   v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>);
     PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad}
 
   void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>);
-    PMXVF64GERPN nothing {mma,pair,quad}
+    PMXVF64GERPN nothing {mma,pair,quad,mmaint}
 
   v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>);
     PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad}
 
   void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>);
-    PMXVF64GERPP nothing {mma,pair,quad}
+    PMXVF64GERPP nothing {mma,pair,quad,mmaint}
 
   v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>);
     PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad}
 
   void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVI16GER2 nothing {mma}
+    PMXVI16GER2 nothing {mma,mmaint}
 
   v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma}
 
   void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVI16GER2PP nothing {mma,quad}
+    PMXVI16GER2PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad}
 
   void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVI16GER2S nothing {mma}
+    PMXVI16GER2S nothing {mma,mmaint}
 
   v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma}
 
   void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>);
-    PMXVI16GER2SPP nothing {mma,quad}
+    PMXVI16GER2SPP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>);
     PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad}
 
   void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>);
-    PMXVI4GER8 nothing {mma}
+    PMXVI4GER8 nothing {mma,mmaint}
 
   v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>);
     PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma}
 
   void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
-    PMXVI4GER8PP nothing {mma,quad}
+    PMXVI4GER8PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
     PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad}
 
   void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
-    PMXVI8GER4 nothing {mma}
+    PMXVI8GER4 nothing {mma,mmaint}
 
   v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>);
     PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma}
 
   void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
-    PMXVI8GER4PP nothing {mma,quad}
+    PMXVI8GER4PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
     PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad}
 
   void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>);
-    PMXVI8GER4SPP nothing {mma,quad}
+    PMXVI8GER4SPP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>);
     PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad}
 
   void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc);
-    XVBF16GER2 nothing {mma}
+    XVBF16GER2 nothing {mma,mmaint}
 
   v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc);
     XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma}
 
   void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc);
-    XVBF16GER2NN nothing {mma,quad}
+    XVBF16GER2NN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc);
     XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad}
 
   void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc);
-    XVBF16GER2NP nothing {mma,quad}
+    XVBF16GER2NP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc);
     XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad}
 
   void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc);
-    XVBF16GER2PN nothing {mma,quad}
+    XVBF16GER2PN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc);
     XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad}
 
   void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc);
-    XVBF16GER2PP nothing {mma,quad}
+    XVBF16GER2PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc);
     XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad}
 
   void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc);
-    XVF16GER2 nothing {mma}
+    XVF16GER2 nothing {mma,mmaint}
 
   v512 __builtin_mma_xvf16ger2_internal (vuc, vuc);
     XVF16GER2_INTERNAL mma_xvf16ger2 {mma}
 
   void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc);
-    XVF16GER2NN nothing {mma,quad}
+    XVF16GER2NN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc);
     XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad}
 
   void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc);
-    XVF16GER2NP nothing {mma,quad}
+    XVF16GER2NP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc);
     XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad}
 
   void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc);
-    XVF16GER2PN nothing {mma,quad}
+    XVF16GER2PN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc);
     XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad}
 
   void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc);
-    XVF16GER2PP nothing {mma,quad}
+    XVF16GER2PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc);
     XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad}
 
   void __builtin_mma_xvf32ger (v512 *, vuc, vuc);
-    XVF32GER nothing {mma}
+    XVF32GER nothing {mma,mmaint}
 
   v512 __builtin_mma_xvf32ger_internal (vuc, vuc);
     XVF32GER_INTERNAL mma_xvf32ger {mma}
 
   void __builtin_mma_xvf32gernn (v512 *, vuc, vuc);
-    XVF32GERNN nothing {mma,quad}
+    XVF32GERNN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc);
     XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad}
 
   void __builtin_mma_xvf32gernp (v512 *, vuc, vuc);
-    XVF32GERNP nothing {mma,quad}
+    XVF32GERNP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc);
     XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad}
 
   void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc);
-    XVF32GERPN nothing {mma,quad}
+    XVF32GERPN nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc);
     XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad}
 
   void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc);
-    XVF32GERPP nothing {mma,quad}
+    XVF32GERPP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc);
     XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad}
 
   void __builtin_mma_xvf64ger (v512 *, v256, vuc);
-    XVF64GER nothing {mma,pair}
+    XVF64GER nothing {mma,pair,mmaint}
 
   v512 __builtin_mma_xvf64ger_internal (v256, vuc);
     XVF64GER_INTERNAL mma_xvf64ger {mma,pair}
 
   void __builtin_mma_xvf64gernn (v512 *, v256, vuc);
-    XVF64GERNN nothing {mma,pair,quad}
+    XVF64GERNN nothing {mma,pair,quad,mmaint}
 
   v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc);
     XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad}
 
   void __builtin_mma_xvf64gernp (v512 *, v256, vuc);
-    XVF64GERNP nothing {mma,pair,quad}
+    XVF64GERNP nothing {mma,pair,quad,mmaint}
 
   v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc);
     XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad}
 
   void __builtin_mma_xvf64gerpn (v512 *, v256, vuc);
-    XVF64GERPN nothing {mma,pair,quad}
+    XVF64GERPN nothing {mma,pair,quad,mmaint}
 
   v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc);
     XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad}
 
   void __builtin_mma_xvf64gerpp (v512 *, v256, vuc);
-    XVF64GERPP nothing {mma,pair,quad}
+    XVF64GERPP nothing {mma,pair,quad,mmaint}
 
   v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc);
     XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad}
 
   void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc);
-    XVI16GER2 nothing {mma}
+    XVI16GER2 nothing {mma,mmaint}
 
   v512 __builtin_mma_xvi16ger2_internal (vuc, vuc);
     XVI16GER2_INTERNAL mma_xvi16ger2 {mma}
 
   void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc);
-    XVI16GER2PP nothing {mma,quad}
+    XVI16GER2PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc);
     XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad}
 
   void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc);
-    XVI16GER2S nothing {mma}
+    XVI16GER2S nothing {mma,mmaint}
 
   v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc);
     XVI16GER2S_INTERNAL mma_xvi16ger2s {mma}
 
   void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc);
-    XVI16GER2SPP nothing {mma,quad}
+    XVI16GER2SPP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc);
     XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad}
 
   void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc);
-    XVI4GER8 nothing {mma}
+    XVI4GER8 nothing {mma,mmaint}
 
   v512 __builtin_mma_xvi4ger8_internal (vuc, vuc);
     XVI4GER8_INTERNAL mma_xvi4ger8 {mma}
 
   void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc);
-    XVI4GER8PP nothing {mma,quad}
+    XVI4GER8PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc);
     XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad}
 
   void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc);
-    XVI8GER4 nothing {mma}
+    XVI8GER4 nothing {mma,mmaint}
 
   v512 __builtin_mma_xvi8ger4_internal (vuc, vuc);
     XVI8GER4_INTERNAL mma_xvi8ger4 {mma}
 
   void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc);
-    XVI8GER4PP nothing {mma,quad}
+    XVI8GER4PP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc);
     XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad}
 
   void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc);
-    XVI8GER4SPP nothing {mma,quad}
+    XVI8GER4SPP nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc);
     XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad}
 
   void __builtin_mma_xxmfacc (v512 *);
-    XXMFACC nothing {mma,quad}
+    XXMFACC nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xxmfacc_internal (v512);
     XXMFACC_INTERNAL mma_xxmfacc {mma,quad}
 
   void __builtin_mma_xxmtacc (v512 *);
-    XXMTACC nothing {mma,quad}
+    XXMTACC nothing {mma,quad,mmaint}
 
   v512 __builtin_mma_xxmtacc_internal (v512);
     XXMTACC_INTERNAL mma_xxmtacc {mma,quad}
 
   void __builtin_mma_xxsetaccz (v512 *);
-    XXSETACCZ nothing {mma}
+    XXSETACCZ nothing {mma,mmaint}
 
   v512 __builtin_mma_xxsetaccz_internal ();
     XXSETACCZ_INTERNAL mma_xxsetaccz {mma}
 
   void __builtin_vsx_assemble_pair (v256 *, vuc, vuc);
-    ASSEMBLE_PAIR_V nothing {mma}
+    ASSEMBLE_PAIR_V nothing {mma,mmaint}
 
   v256 __builtin_vsx_assemble_pair_internal (vuc, vuc);
     ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma}
 
   void __builtin_vsx_build_pair (v256 *, vuc, vuc);
-    BUILD_PAIR nothing {mma}
+    BUILD_PAIR nothing {mma,mmaint}
 
   v256 __builtin_vsx_build_pair_internal (vuc, vuc);
     BUILD_PAIR_INTERNAL vsx_assemble_pair {mma}
 
   void __builtin_vsx_disassemble_pair (void *, v256 *);
-    DISASSEMBLE_PAIR_V nothing {mma,pair}
+    DISASSEMBLE_PAIR_V nothing {mma,pair,mmaint}
 
   vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>);
     DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}
+
+  v256 __builtin_vsx_lxvp (unsigned long, const v256 *);
+    LXVP nothing {mma}
+
+  void __builtin_vsx_stxvp (v256, unsigned long, const v256 *);
+    STXVP nothing {mma,pair}
diff --git a/gcc/config/rs6000/rs6000-call.c b/gcc/config/rs6000/rs6000-call.c
index eae4e15df1e..558f06cfd6c 100644
--- a/gcc/config/rs6000/rs6000-call.c
+++ b/gcc/config/rs6000/rs6000-call.c
@@ -13072,8 +13072,10 @@ rs6000_gimple_fold_new_mma_builtin (gimple_stmt_iterator *gsi,
 
   /* Each call that can be gimple-expanded has an associated built-in
      function that it will expand into.  If this one doesn't, we have
-     already expanded it!  */
-  if (rs6000_builtin_info_x[fncode].assoc_bif == RS6000_BIF_NONE)
+     already expanded it!  Exceptions: lxvp and stxvp.  */
+  if (rs6000_builtin_info_x[fncode].assoc_bif == RS6000_BIF_NONE
+      && fncode != RS6000_BIF_LXVP
+      && fncode != RS6000_BIF_STXVP)
     return false;
 
   bifdata *bd = &rs6000_builtin_info_x[fncode];
@@ -13150,6 +13152,38 @@ rs6000_gimple_fold_new_mma_builtin (gimple_stmt_iterator *gsi,
       gsi_replace_with_seq (gsi, new_seq, true);
       return true;
     }
+  else if (fncode == RS6000_BIF_LXVP)
+    {
+      push_gimplify_context (true);
+      tree offset = gimple_call_arg (stmt, 0);
+      tree ptr = gimple_call_arg (stmt, 1);
+      tree lhs = gimple_call_lhs (stmt);
+      if (TREE_TYPE (TREE_TYPE (ptr)) != vector_pair_type_node)
+	ptr = build1 (VIEW_CONVERT_EXPR,
+		      build_pointer_type (vector_pair_type_node), ptr);
+      tree mem = build_simple_mem_ref (build2 (POINTER_PLUS_EXPR,
+					       TREE_TYPE (ptr), ptr, offset));
+      gimplify_assign (lhs, mem, &new_seq);
+      pop_gimplify_context (NULL);
+      gsi_replace_with_seq (gsi, new_seq, true);
+      return true;
+    }
+  else if (fncode == RS6000_BIF_STXVP)
+    {
+      push_gimplify_context (true);
+      tree src = gimple_call_arg (stmt, 0);
+      tree offset = gimple_call_arg (stmt, 1);
+      tree ptr = gimple_call_arg (stmt, 2);
+      if (TREE_TYPE (TREE_TYPE (ptr)) != vector_pair_type_node)
+	ptr = build1 (VIEW_CONVERT_EXPR,
+		      build_pointer_type (vector_pair_type_node), ptr);
+      tree mem = build_simple_mem_ref (build2 (POINTER_PLUS_EXPR,
+					       TREE_TYPE (ptr), ptr, offset));
+      gimplify_assign (mem, src, &new_seq);
+      pop_gimplify_context (NULL);
+      gsi_replace_with_seq (gsi, new_seq, true);
+      return true;
+    }
 
   /* Convert this built-in into an internal version that uses pass-by-value
      arguments.  The internal built-in is found in the assoc_bif field.  */
diff --git a/gcc/config/rs6000/rs6000-gen-builtins.c b/gcc/config/rs6000/rs6000-gen-builtins.c
index f65932e1cd5..7f711210aff 100644
--- a/gcc/config/rs6000/rs6000-gen-builtins.c
+++ b/gcc/config/rs6000/rs6000-gen-builtins.c
@@ -84,6 +84,7 @@ along with GCC; see the file COPYING3.  If not see
      mma      Needs special handling for MMA instructions
      quad     MMA instruction using a register quad as an input operand
      pair     MMA instruction using a register pair as an input operand
+     mmaint   MMA instruction expanding to internal call at GIMPLE time
      no32bit  Not valid for TARGET_32BIT
      32bit    Requires different handling for TARGET_32BIT
      cpu      This is a "cpu_is" or "cpu_supports" builtin
@@ -369,6 +370,7 @@ struct attrinfo
   bool ismma;
   bool isquad;
   bool ispair;
+  bool ismmaint;
   bool isno32bit;
   bool is32bit;
   bool iscpu;
@@ -1363,6 +1365,8 @@ parse_bif_attrs (attrinfo *attrptr)
 	  attrptr->isquad = 1;
 	else if (!strcmp (attrname, "pair"))
 	  attrptr->ispair = 1;
+	else if (!strcmp (attrname, "mmaint"))
+	  attrptr->ismmaint = 1;
 	else if (!strcmp (attrname, "no32bit"))
 	  attrptr->isno32bit = 1;
 	else if (!strcmp (attrname, "32bit"))
@@ -1409,15 +1413,15 @@ parse_bif_attrs (attrinfo *attrptr)
   (*diag) ("attribute set: init = %d, set = %d, extract = %d, nosoft = %d, "
 	   "ldvec = %d, stvec = %d, reve = %d, pred = %d, htm = %d, "
 	   "htmspr = %d, htmcr = %d, mma = %d, quad = %d, pair = %d, "
-	   "no32bit = %d, 32bit = %d, cpu = %d, ldstmask = %d, lxvrse = %d, "
-	   "lxvrze = %d, endian = %d.\n",
+	   "mmaint = %d, no32bit = %d, 32bit = %d, cpu = %d, ldstmask = %d, "
+	   "lxvrse = %d, lxvrze = %d, endian = %d.\n",
 	   attrptr->isinit, attrptr->isset, attrptr->isextract,
 	   attrptr->isnosoft, attrptr->isldvec, attrptr->isstvec,
 	   attrptr->isreve, attrptr->ispred, attrptr->ishtm, attrptr->ishtmspr,
 	   attrptr->ishtmcr, attrptr->ismma, attrptr->isquad, attrptr->ispair,
-	   attrptr->isno32bit, attrptr->is32bit, attrptr->iscpu,
-	   attrptr->isldstmask, attrptr->islxvrse, attrptr->islxvrze,
-	   attrptr->isendian);
+	   attrptr->ismmaint, attrptr->isno32bit, attrptr->is32bit,
+	   attrptr->iscpu, attrptr->isldstmask, attrptr->islxvrse,
+	   attrptr->islxvrze, attrptr->isendian);
 #endif
 
   return PC_OK;
@@ -2223,13 +2227,14 @@ write_decls (void)
   fprintf (header_file, "#define bif_mma_bit\t\t(0x00000800)\n");
   fprintf (header_file, "#define bif_quad_bit\t\t(0x00001000)\n");
   fprintf (header_file, "#define bif_pair_bit\t\t(0x00002000)\n");
-  fprintf (header_file, "#define bif_no32bit_bit\t\t(0x00004000)\n");
-  fprintf (header_file, "#define bif_32bit_bit\t\t(0x00008000)\n");
-  fprintf (header_file, "#define bif_cpu_bit\t\t(0x00010000)\n");
-  fprintf (header_file, "#define bif_ldstmask_bit\t(0x00020000)\n");
-  fprintf (header_file, "#define bif_lxvrse_bit\t\t(0x00040000)\n");
-  fprintf (header_file, "#define bif_lxvrze_bit\t\t(0x00080000)\n");
-  fprintf (header_file, "#define bif_endian_bit\t\t(0x00100000)\n");
+  fprintf (header_file, "#define bif_mmaint_bit\t\t(0x00004000)\n");
+  fprintf (header_file, "#define bif_no32bit_bit\t\t(0x00008000)\n");
+  fprintf (header_file, "#define bif_32bit_bit\t\t(0x00010000)\n");
+  fprintf (header_file, "#define bif_cpu_bit\t\t(0x00020000)\n");
+  fprintf (header_file, "#define bif_ldstmask_bit\t(0x00040000)\n");
+  fprintf (header_file, "#define bif_lxvrse_bit\t\t(0x00080000)\n");
+  fprintf (header_file, "#define bif_lxvrze_bit\t\t(0x00100000)\n");
+  fprintf (header_file, "#define bif_endian_bit\t\t(0x00200000)\n");
   fprintf (header_file, "\n");
   fprintf (header_file,
 	   "#define bif_is_init(x)\t\t((x).bifattrs & bif_init_bit)\n");
@@ -2259,6 +2264,8 @@ write_decls (void)
 	   "#define bif_is_quad(x)\t\t((x).bifattrs & bif_quad_bit)\n");
   fprintf (header_file,
 	   "#define bif_is_pair(x)\t\t((x).bifattrs & bif_pair_bit)\n");
+  fprintf (header_file,
+	   "#define bif_is_mmaint(x)\t\t((x).bifattrs & bif_mmaint_bit)\n");
   fprintf (header_file,
 	   "#define bif_is_no32bit(x)\t((x).bifattrs & bif_no32bit_bit)\n");
   fprintf (header_file,
@@ -2491,6 +2498,8 @@ write_bif_static_init (void)
 	fprintf (init_file, " | bif_quad_bit");
       if (bifp->attrs.ispair)
 	fprintf (init_file, " | bif_pair_bit");
+      if (bifp->attrs.ismmaint)
+	fprintf (init_file, " | bif_mmaint_bit");
       if (bifp->attrs.isno32bit)
 	fprintf (init_file, " | bif_no32bit_bit");
       if (bifp->attrs.is32bit)
@@ -2537,10 +2546,9 @@ write_bif_static_init (void)
 		: (bifp->kind == FNK_PURE ? "= pure"
 		   : (bifp->kind == FNK_FPMATH ? "= fp, const"
 		      : ""))));
-      bool no_icode = !strcmp (bifp->patname, "nothing");
       fprintf (init_file, "      /* assoc_bif */\tRS6000_BIF_%s%s\n",
-	       bifp->attrs.ismma && no_icode ? bifp->idname : "NONE",
-	       bifp->attrs.ismma && no_icode ? "_INTERNAL" : "");
+	       bifp->attrs.ismmaint ? bifp->idname : "NONE",
+	       bifp->attrs.ismmaint ? "_INTERNAL" : "");
       fprintf (init_file, "    },\n");
     }
   fprintf (init_file, "  };\n\n");
-- 
2.27.0