[2/3] rs6000: Add MMA built-in function definitions

diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index c3f460face2..4e37ce35c5d 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -1119,6 +1119,12 @@  (define_predicate "splat_input_operand"
   return gpc_reg_operand (op, mode);
 })
 
+;; Return 1 if this operand is valid for a MMA assemble accumulator insn.
+(define_special_predicate "mma_input_operand"
+  (match_test "(mode == PXImode
+		&& (GET_MODE (op) == V16QImode)
+		&& (vsx_register_operand (op, GET_MODE (op)) || MEM_P (op)))"))
+
 ;; Return true if operand is an operator used in rotate-and-mask instructions.
 (define_predicate "rotate_mask_operator"
   (match_code "rotate,ashift,lshiftrt"))
diff --git a/gcc/config/rs6000/rs6000-builtin.def b/gcc/config/rs6000/rs6000-builtin.def
index 8b1ddb00045..968c46cc36f 100644
--- a/gcc/config/rs6000/rs6000-builtin.def
+++ b/gcc/config/rs6000/rs6000-builtin.def
@@ -32,6 +32,7 @@ 
    RS6000_BUILTIN_A -- ABS builtins
    RS6000_BUILTIN_D -- DST builtins
    RS6000_BUILTIN_H -- HTM builtins
+   RS6000_BUILTIN_M -- MMA builtins
    RS6000_BUILTIN_P -- Altivec, VSX, ISA 2.07 vector predicate builtins
    RS6000_BUILTIN_X -- special builtins
 
@@ -74,6 +75,10 @@ 
   #error "RS6000_BUILTIN_H is not defined."
 #endif
 
+#ifndef RS6000_BUILTIN_M
+  #error "RS6000_BUILTIN_M is not defined."
+#endif
+
 #ifndef RS6000_BUILTIN_P
   #error "RS6000_BUILTIN_P is not defined."
 #endif
@@ -329,6 +334,82 @@ 
 		     | RS6000_BTC_SPECIAL),				\
 		    CODE_FOR_nothing)			/* ICODE */
 
+/* MMA convenience macros.  */
+
+#define BU_MMA_1(ENUM, NAME, ATTR, ICODE)				\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM,		/* ENUM */	\
+		    "__builtin_mma_" NAME,		/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_UNARY					\
+		     | RS6000_BTC_VOID					\
+		     | RS6000_BTC_GIMPLE),				\
+		    CODE_FOR_nothing)			/* ICODE */	\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM ## _INTERNAL,	/* ENUM */	\
+		    "__builtin_mma_" NAME "_internal",	/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_UNARY),				\
+		    CODE_FOR_ ## ICODE)			/* ICODE */
+
+#define BU_MMA_V2(ENUM, NAME, ATTR, ICODE)				\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM,		/* ENUM */	\
+		    "__builtin_mma_" NAME,		/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_BINARY				\
+		     | RS6000_BTC_VOID					\
+		     | RS6000_BTC_GIMPLE),				\
+		    CODE_FOR_nothing)			/* ICODE */
+
+#define BU_MMA_3(ENUM, NAME, ATTR, ICODE)				\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM,		/* ENUM */	\
+		    "__builtin_mma_" NAME,		/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_TERNARY				\
+		     | RS6000_BTC_VOID					\
+		     | RS6000_BTC_GIMPLE),				\
+		    CODE_FOR_nothing)			/* ICODE */	\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM ## _INTERNAL,	/* ENUM */	\
+		    "__builtin_mma_" NAME "_internal",	/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_TERNARY),				\
+		    CODE_FOR_ ## ICODE)			/* ICODE */
+
+#define BU_MMA_5(ENUM, NAME, ATTR, ICODE)				\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM,		/* ENUM */	\
+		    "__builtin_mma_" NAME,		/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_QUINARY				\
+		     | RS6000_BTC_VOID					\
+		     | RS6000_BTC_GIMPLE),				\
+		    CODE_FOR_nothing)			/* ICODE */	\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM ## _INTERNAL,	/* ENUM */	\
+		    "__builtin_mma_" NAME "_internal",	/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_QUINARY),				\
+		    CODE_FOR_ ## ICODE)			/* ICODE */
+
+#define BU_MMA_6(ENUM, NAME, ATTR, ICODE)				\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM,		/* ENUM */	\
+		    "__builtin_mma_" NAME,		/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_SENARY				\
+		     | RS6000_BTC_VOID					\
+		     | RS6000_BTC_GIMPLE),				\
+		    CODE_FOR_nothing)			/* ICODE */	\
+  RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM ## _INTERNAL,	/* ENUM */	\
+		    "__builtin_mma_" NAME "_internal",	/* NAME */	\
+		    RS6000_BTM_MMA,			/* MASK */	\
+		    (RS6000_BTC_ ## ATTR		/* ATTR */	\
+		     | RS6000_BTC_SENARY),				\
+		    CODE_FOR_ ## ICODE)			/* ICODE */
+
 /* ISA 2.05 (power6) convenience macros. */
 /* For functions that depend on the CMPB instruction */
 #define BU_P6_2(ENUM, NAME, ATTR, ICODE)				\
@@ -2785,3 +2866,77 @@  BU_SPECIAL_X (RS6000_BUILTIN_CPU_SUPPORTS, "__builtin_cpu_supports",
 /* Darwin CfString builtin.  */
 BU_SPECIAL_X (RS6000_BUILTIN_CFSTRING, "__builtin_cfstring", RS6000_BTM_ALWAYS,
 	      RS6000_BTC_MISC)
+
+/* FUTURE MMA builtins.  */
+BU_VSX_1 (XVCVBF16SP,	    "xvcvbf16sp",	MISC, vsx_xvcvbf16sp)
+BU_VSX_1 (XVCVSPBF16,	    "xvcvspbf16",	MISC, vsx_xvcvspbf16)
+
+BU_MMA_1 (XXMFACC,	    "xxmfacc",		QUAD, mma_xxmfacc)
+BU_MMA_1 (XXMTACC,	    "xxmtacc",		QUAD, mma_xxmtacc)
+BU_MMA_1 (XXSETACCZ,	    "xxsetaccz",	MISC, mma_xxsetaccz)
+
+BU_MMA_V2 (DISASSEMBLE_ACC, "disassemble_acc",  QUAD, nothing)
+BU_MMA_V2 (DISASSEMBLE_PAIR,"disassemble_pair", PAIR, nothing)
+
+BU_MMA_3 (ASSEMBLE_PAIR,    "assemble_pair",	MISC, mma_assemble_pair)
+BU_MMA_3 (XVBF16GER2,	    "xvbf16ger2",	MISC, mma_xvbf16ger2)
+BU_MMA_3 (XVF16GER2,	    "xvf16ger2",	MISC, mma_xvf16ger2)
+BU_MMA_3 (XVF32GER,	    "xvf32ger",		MISC, mma_xvf32ger)
+BU_MMA_3 (XVF64GER,	    "xvf64ger",		PAIR, mma_xvf64ger)
+BU_MMA_3 (XVI4GER8,	    "xvi4ger8",		MISC, mma_xvi4ger8)
+BU_MMA_3 (XVI8GER4,	    "xvi8ger4",		MISC, mma_xvi8ger4)
+BU_MMA_3 (XVI16GER2,	    "xvi16ger2",	MISC, mma_xvi16ger2)
+BU_MMA_3 (XVI16GER2S,	    "xvi16ger2s",	MISC, mma_xvi16ger2s)
+BU_MMA_3 (XVBF16GER2NN,	    "xvbf16ger2nn",     QUAD, mma_xvbf16ger2nn)
+BU_MMA_3 (XVBF16GER2NP,	    "xvbf16ger2np",     QUAD, mma_xvbf16ger2np)
+BU_MMA_3 (XVBF16GER2PN,	    "xvbf16ger2pn",     QUAD, mma_xvbf16ger2pn)
+BU_MMA_3 (XVBF16GER2PP,	    "xvbf16ger2pp",     QUAD, mma_xvbf16ger2pp)
+BU_MMA_3 (XVF16GER2NN,	    "xvf16ger2nn",      QUAD, mma_xvf16ger2nn)
+BU_MMA_3 (XVF16GER2NP,	    "xvf16ger2np",      QUAD, mma_xvf16ger2np)
+BU_MMA_3 (XVF16GER2PN,	    "xvf16ger2pn",      QUAD, mma_xvf16ger2pn)
+BU_MMA_3 (XVF16GER2PP,	    "xvf16ger2pp",      QUAD, mma_xvf16ger2pp)
+BU_MMA_3 (XVF32GERNN,	    "xvf32gernn",       QUAD, mma_xvf32gernn)
+BU_MMA_3 (XVF32GERNP,	    "xvf32gernp",       QUAD, mma_xvf32gernp)
+BU_MMA_3 (XVF32GERPN,	    "xvf32gerpn",       QUAD, mma_xvf32gerpn)
+BU_MMA_3 (XVF32GERPP,	    "xvf32gerpp",       QUAD, mma_xvf32gerpp)
+BU_MMA_3 (XVF64GERNN,	    "xvf64gernn",       QUADPAIR, mma_xvf64gernn)
+BU_MMA_3 (XVF64GERNP,	    "xvf64gernp",       QUADPAIR, mma_xvf64gernp)
+BU_MMA_3 (XVF64GERPN,	    "xvf64gerpn",       QUADPAIR, mma_xvf64gerpn)
+BU_MMA_3 (XVF64GERPP,	    "xvf64gerpp",       QUADPAIR, mma_xvf64gerpp)
+BU_MMA_3 (XVI4GER8PP,	    "xvi4ger8pp",	QUAD, mma_xvi4ger8pp)
+BU_MMA_3 (XVI8GER4PP,	    "xvi8ger4pp",       QUAD, mma_xvi8ger4pp)
+BU_MMA_3 (XVI8GER4SPP,	    "xvi8ger4spp",      QUAD, mma_xvi8ger4spp)
+BU_MMA_3 (XVI16GER2PP,	    "xvi16ger2pp",      QUAD, mma_xvi16ger2pp)
+BU_MMA_3 (XVI16GER2SPP,	    "xvi16ger2spp",     QUAD, mma_xvi16ger2spp)
+
+BU_MMA_5 (ASSEMBLE_ACC,     "assemble_acc",	MISC, mma_assemble_acc)
+BU_MMA_5 (PMXVF32GER,	    "pmxvf32ger",       MISC, mma_pmxvf32ger)
+BU_MMA_5 (PMXVF64GER,	    "pmxvf64ger",       PAIR, mma_pmxvf64ger)
+BU_MMA_5 (PMXVF32GERNN,	    "pmxvf32gernn",     QUAD, mma_pmxvf32gernn)
+BU_MMA_5 (PMXVF32GERNP,	    "pmxvf32gernp",     QUAD, mma_pmxvf32gernp)
+BU_MMA_5 (PMXVF32GERPN,	    "pmxvf32gerpn",     QUAD, mma_pmxvf32gerpn)
+BU_MMA_5 (PMXVF32GERPP,	    "pmxvf32gerpp",     QUAD, mma_pmxvf32gerpp)
+BU_MMA_5 (PMXVF64GERNN,	    "pmxvf64gernn",     QUADPAIR, mma_pmxvf64gernn)
+BU_MMA_5 (PMXVF64GERNP,	    "pmxvf64gernp",     QUADPAIR, mma_pmxvf64gernp)
+BU_MMA_5 (PMXVF64GERPN,	    "pmxvf64gerpn",     QUADPAIR, mma_pmxvf64gerpn)
+BU_MMA_5 (PMXVF64GERPP,	    "pmxvf64gerpp",     QUADPAIR, mma_pmxvf64gerpp)
+
+BU_MMA_6 (PMXVBF16GER2,	    "pmxvbf16ger2",     MISC, mma_pmxvbf16ger2)
+BU_MMA_6 (PMXVF16GER2,	    "pmxvf16ger2",      MISC, mma_pmxvf16ger2)
+BU_MMA_6 (PMXVI4GER8,	    "pmxvi4ger8",       MISC, mma_pmxvi4ger8)
+BU_MMA_6 (PMXVI8GER4,	    "pmxvi8ger4",	MISC, mma_pmxvi8ger4)
+BU_MMA_6 (PMXVI16GER2,	    "pmxvi16ger2",      MISC, mma_pmxvi16ger2)
+BU_MMA_6 (PMXVI16GER2S,	    "pmxvi16ger2s",     MISC, mma_pmxvi16ger2s)
+BU_MMA_6 (PMXVBF16GER2NN,   "pmxvbf16ger2nn",   QUAD, mma_pmxvbf16ger2nn)
+BU_MMA_6 (PMXVBF16GER2NP,   "pmxvbf16ger2np",   QUAD, mma_pmxvbf16ger2np)
+BU_MMA_6 (PMXVBF16GER2PN,   "pmxvbf16ger2pn",   QUAD, mma_pmxvbf16ger2pn)
+BU_MMA_6 (PMXVBF16GER2PP,   "pmxvbf16ger2pp",   QUAD, mma_pmxvbf16ger2pp)
+BU_MMA_6 (PMXVF16GER2NN,    "pmxvf16ger2nn",    QUAD, mma_pmxvf16ger2nn)
+BU_MMA_6 (PMXVF16GER2NP,    "pmxvf16ger2np",    QUAD, mma_pmxvf16ger2np)
+BU_MMA_6 (PMXVF16GER2PN,    "pmxvf16ger2pn",    QUAD, mma_pmxvf16ger2pn)
+BU_MMA_6 (PMXVF16GER2PP,    "pmxvf16ger2pp",    QUAD, mma_pmxvf16ger2pp)
+BU_MMA_6 (PMXVI4GER8PP,	    "pmxvi4ger8pp",     QUAD, mma_pmxvi4ger8pp)
+BU_MMA_6 (PMXVI8GER4PP,	    "pmxvi8ger4pp",	QUAD, mma_pmxvi8ger4pp)
+BU_MMA_6 (PMXVI8GER4SPP,    "pmxvi8ger4spp",	QUAD, mma_pmxvi8ger4spp)
+BU_MMA_6 (PMXVI16GER2PP,    "pmxvi16ger2pp",    QUAD, mma_pmxvi16ger2pp)
+BU_MMA_6 (PMXVI16GER2SPP,   "pmxvi16ger2spp",   QUAD, mma_pmxvi16ger2spp)
diff --git a/gcc/config/rs6000/rs6000-call.c b/gcc/config/rs6000/rs6000-call.c
index eeb20e5200d..d47c3a3aeb0 100644
--- a/gcc/config/rs6000/rs6000-call.c
+++ b/gcc/config/rs6000/rs6000-call.c
@@ -183,6 +183,7 @@  static tree builtin_function_type (machine_mode, machine_mode,
 				   enum rs6000_builtins, const char *name);
 static void rs6000_common_init_builtins (void);
 static void htm_init_builtins (void);
+static void mma_init_builtins (void);
 
 
 /* Hash table to keep track of the argument types for builtin functions.  */
@@ -243,6 +244,7 @@  builtin_hasher::equal (builtin_hash_struct *p1, builtin_hash_struct *p2)
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -270,6 +272,9 @@  builtin_hasher::equal (builtin_hash_struct *p1, builtin_hash_struct *p2)
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)  \
   { NAME, ICODE, MASK, ATTR },
 
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)  \
+  { NAME, ICODE, MASK, ATTR },
+
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)  \
   { NAME, ICODE, MASK, ATTR },
 
@@ -296,6 +301,7 @@  static const struct rs6000_builtin_info_type rs6000_builtin_info[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8354,6 +8360,9 @@  def_builtin (const char *name, tree type, enum rs6000_builtins code)
 	  attr_string = ", fp, const";
 	}
     }
+  else if ((classify & (RS6000_BTC_QUAD | RS6000_BTC_PAIR)) != 0)
+    /* The function uses a register quad and/or pair.  Nothing to do.  */
+    ;
   else if ((classify & RS6000_BTC_ATTR_MASK) != 0)
     gcc_unreachable ();
 
@@ -8372,6 +8381,7 @@  def_builtin (const char *name, tree type, enum rs6000_builtins code)
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8385,6 +8395,7 @@  def_builtin (const char *name, tree type, enum rs6000_builtins code)
 #define RS6000_BUILTIN_A(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
 
@@ -8403,6 +8414,7 @@  static const struct builtin_description bdesc_3arg[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8416,6 +8428,7 @@  static const struct builtin_description bdesc_3arg[] =
 #define RS6000_BUILTIN_A(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
 
@@ -8434,6 +8447,7 @@  static const struct builtin_description bdesc_4arg[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8447,6 +8461,7 @@  static const struct builtin_description bdesc_4arg[] =
   { MASK, ICODE, NAME, ENUM },
 
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
 
@@ -8465,6 +8480,7 @@  static const struct builtin_description bdesc_dst[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8478,6 +8494,7 @@  static const struct builtin_description bdesc_dst[] =
 #define RS6000_BUILTIN_A(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
 
@@ -8494,6 +8511,7 @@  static const struct builtin_description bdesc_2arg[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8505,6 +8523,7 @@  static const struct builtin_description bdesc_2arg[] =
 #define RS6000_BUILTIN_A(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE) \
   { MASK, ICODE, NAME, ENUM },
 
@@ -8527,6 +8546,7 @@  static const struct builtin_description bdesc_altivec_preds[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8540,6 +8560,7 @@  static const struct builtin_description bdesc_altivec_preds[] =
 
 #define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
 
@@ -8559,6 +8580,7 @@  static const struct builtin_description bdesc_abs[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8572,6 +8594,7 @@  static const struct builtin_description bdesc_abs[] =
 #define RS6000_BUILTIN_A(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
 
@@ -8590,6 +8613,7 @@  static const struct builtin_description bdesc_1arg[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8603,6 +8627,7 @@  static const struct builtin_description bdesc_1arg[] =
 #define RS6000_BUILTIN_A(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
 
@@ -8620,6 +8645,7 @@  static const struct builtin_description bdesc_0arg[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -8633,6 +8659,7 @@  static const struct builtin_description bdesc_0arg[] =
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE) \
   { MASK, ICODE, NAME, ENUM },
 
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
 
@@ -8641,6 +8668,7 @@  static const struct builtin_description bdesc_htm[] =
 #include "rs6000-builtin.def"
 };
 
+/* MMA builtins.  */
 #undef RS6000_BUILTIN_0
 #undef RS6000_BUILTIN_1
 #undef RS6000_BUILTIN_2
@@ -8649,7 +8677,40 @@  static const struct builtin_description bdesc_htm[] =
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
+#undef RS6000_BUILTIN_X
+
+#define RS6000_BUILTIN_0(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_1(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_2(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_3(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_4(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_A(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE) \
+  { MASK, ICODE, NAME, ENUM },
+
+#define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE)
+#define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE)
+
+static const struct builtin_description bdesc_mma[] =
+{
+#include "rs6000-builtin.def"
+};
+
+#undef RS6000_BUILTIN_0
+#undef RS6000_BUILTIN_1
+#undef RS6000_BUILTIN_2
+#undef RS6000_BUILTIN_3
+#undef RS6000_BUILTIN_4
+#undef RS6000_BUILTIN_A
+#undef RS6000_BUILTIN_D
+#undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
+#undef RS6000_BUILTIN_P
+#undef RS6000_BUILTIN_X
 
 /* Return true if a builtin function is overloaded.  */
 bool
@@ -9393,6 +9454,133 @@  altivec_expand_stv_builtin (enum insn_code icode, tree exp)
   return NULL_RTX;
 }
 
+/* Expand the MMA built-in in EXP.
+   Store true in *EXPANDEDP if we found a built-in to expand.  */
+
+static rtx
+mma_expand_builtin (tree exp, rtx target, bool *expandedp)
+{
+  unsigned i;
+  tree fndecl = TREE_OPERAND (CALL_EXPR_FN (exp), 0);
+  enum rs6000_builtins fcode
+    = (enum rs6000_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+  const struct builtin_description *d = bdesc_mma;
+
+  /* Expand the MMA built-in.  */
+  for (i = 0; i < ARRAY_SIZE (bdesc_mma); i++, d++)
+    if (d->code == fcode)
+      break;
+
+  if (i >= ARRAY_SIZE (bdesc_mma))
+    {
+      *expandedp = false;
+      return NULL_RTX;
+    }
+
+  *expandedp = true;
+
+  tree arg;
+  call_expr_arg_iterator iter;
+  enum insn_code icode = d->icode;
+  const struct insn_operand_data *insn_op;
+  rtx op[MAX_MMA_OPERANDS];
+  unsigned nopnds = 0;
+  unsigned attr = rs6000_builtin_info[fcode].attr;
+  bool void_func = (attr & RS6000_BTC_VOID);
+  machine_mode tmode = VOIDmode;
+
+  if (TREE_TYPE (TREE_TYPE (fndecl)) != void_type_node)
+    {
+      tmode = insn_data[icode].operand[0].mode;
+      if (!target
+	  || GET_MODE (target) != tmode
+	  || !(*insn_data[icode].operand[0].predicate) (target, tmode))
+	target = gen_reg_rtx (tmode);
+      op[nopnds++] = target;
+    }
+  else
+    target = const0_rtx;
+
+  FOR_EACH_CALL_EXPR_ARG (arg, iter, exp)
+    {
+      if (arg == error_mark_node)
+	return const0_rtx;
+
+      rtx opnd;
+      insn_op = &insn_data[icode].operand[nopnds];
+      if (TREE_CODE (arg) == ADDR_EXPR
+	  && MEM_P (DECL_RTL (TREE_OPERAND (arg, 0))))
+	opnd = DECL_RTL (TREE_OPERAND (arg, 0));
+      else
+	opnd = expand_normal (arg);
+
+      if (!(*insn_op->predicate) (opnd, insn_op->mode))
+	{
+	  if (!strcmp (insn_op->constraint, "n"))
+	    {
+	      if (!CONST_INT_P (opnd))
+		error ("argument %d must be an unsigned literal", nopnds);
+	      else
+		error ("argument %d is an unsigned literal that is "
+		       "out of range", nopnds);
+	      return const0_rtx;
+	    }
+	  opnd = copy_to_mode_reg (insn_op->mode, opnd);
+	}
+
+      /* Some MMA instructions have INOUT accumulator operands, so force
+	 their target register to be the same as their input register.  */
+      if (!void_func
+	  && nopnds == 1
+	  && !strcmp (insn_op->constraint, "0")
+	  && insn_op->mode == tmode
+	  && REG_P (opnd)
+	  && (*insn_data[icode].operand[0].predicate) (opnd, tmode))
+	target = op[0] = opnd;
+
+      op[nopnds++] = opnd;
+    }
+
+  unsigned attr_args = attr & RS6000_BTC_OPND_MASK;
+  if (attr & RS6000_BTC_QUAD)
+    attr_args++;
+
+  gcc_assert (nopnds == attr_args);
+
+  rtx pat;
+  switch (nopnds)
+    {
+    case 1:
+      pat = GEN_FCN (icode) (op[0]);
+      break;
+    case 2:
+      pat = GEN_FCN (icode) (op[0], op[1]);
+      break;
+    case 3:
+      pat = GEN_FCN (icode) (op[0], op[1], op[2]);
+      break;
+    case 4:
+      pat = GEN_FCN (icode) (op[0], op[1], op[2], op[3]);
+      break;
+    case 5:
+      pat = GEN_FCN (icode) (op[0], op[1], op[2], op[3], op[4]);
+      break;
+    case 6:
+      pat = GEN_FCN (icode) (op[0], op[1], op[2], op[3], op[4], op[5]);
+      break;
+    case 7:
+      pat = GEN_FCN (icode) (op[0], op[1], op[2], op[3], op[4], op[5], op[6]);
+      break;
+    default:
+      gcc_unreachable ();
+    }
+  if (!pat)
+    return NULL_RTX;
+  emit_insn (pat);
+
+  return target;
+}
+
 /* Return the appropriate SPR number associated with the given builtin.  */
 static inline HOST_WIDE_INT
 htm_spr_num (enum rs6000_builtins code)
@@ -9539,11 +9727,11 @@  htm_expand_builtin (tree exp, rtx target, bool * expandedp)
 	if (flag_checking)
 	  {
 	    int expected_nopnds = 0;
-	    if ((attr & RS6000_BTC_TYPE_MASK) == RS6000_BTC_UNARY)
+	    if ((attr & RS6000_BTC_OPND_MASK) == RS6000_BTC_UNARY)
 	      expected_nopnds = 1;
-	    else if ((attr & RS6000_BTC_TYPE_MASK) == RS6000_BTC_BINARY)
+	    else if ((attr & RS6000_BTC_OPND_MASK) == RS6000_BTC_BINARY)
 	      expected_nopnds = 2;
-	    else if ((attr & RS6000_BTC_TYPE_MASK) == RS6000_BTC_TERNARY)
+	    else if ((attr & RS6000_BTC_OPND_MASK) == RS6000_BTC_TERNARY)
 	      expected_nopnds = 3;
 	    else if ((attr & RS6000_BTC_TYPE_MASK) == RS6000_BTC_QUATERNARY)
 	      expected_nopnds = 4;
@@ -10647,6 +10835,10 @@  rs6000_invalid_builtin (enum rs6000_builtins fncode)
 	   "-m64");
   else if ((fnmask & RS6000_BTM_P9_MISC) == RS6000_BTM_P9_MISC)
     error ("%qs requires the %qs option", name, "-mcpu=power9");
+  else if ((fnmask & RS6000_BTM_FUTURE) != 0)
+    error ("%qs requires the %qs option", name, "-mcpu=future");
+  else if ((fnmask & RS6000_BTM_MMA) != 0)
+    error ("%qs requires the %qs option", name, "-mmma");
   else if ((fnmask & RS6000_BTM_LDBL128) == RS6000_BTM_LDBL128)
     {
       if (!TARGET_HARD_FLOAT)
@@ -10690,6 +10882,10 @@  rs6000_fold_builtin (tree fndecl ATTRIBUTE_UNUSED,
 static bool
 rs6000_builtin_valid_without_lhs (enum rs6000_builtins fn_code)
 {
+  /* Check for built-ins explicitly marked as a void function.  */
+  if (rs6000_builtin_info[fn_code].attr & RS6000_BTC_VOID)
+    return true;
+
   switch (fn_code)
     {
     case ALTIVEC_BUILTIN_STVX_V16QI:
@@ -10833,6 +11029,156 @@  fold_mergeeo_helper (gimple_stmt_iterator *gsi, gimple *stmt, int use_odd)
   gsi_replace (gsi, g, true);
 }
 
+/* Expand the MMA built-ins early, so that we can convert the pass-by-reference
+   __vector_quad arguments into pass-by-value arguments, leading to more
+   efficient code generation.  */
+
+bool
+rs6000_gimple_fold_mma_builtin (gimple_stmt_iterator *gsi)
+{
+  gimple *stmt = gsi_stmt (*gsi);
+  tree fndecl = gimple_call_fndecl (stmt);
+  enum rs6000_builtins fncode
+    = (enum rs6000_builtins) DECL_MD_FUNCTION_CODE (fndecl);
+  unsigned attr = rs6000_builtin_info[fncode].attr;
+
+  if ((attr & RS6000_BTC_GIMPLE) == 0)
+    return false;
+
+  unsigned nopnds = (attr & RS6000_BTC_OPND_MASK);
+  gimple_seq new_seq = NULL;
+  gimple *new_call;
+  tree new_decl;
+
+  if (rs6000_builtin_info[fncode + 1].icode == CODE_FOR_nothing)
+    {
+      /* This is an MMA disassemble built-in function.  */
+      gcc_assert (fncode == MMA_BUILTIN_DISASSEMBLE_ACC
+		  || fncode == MMA_BUILTIN_DISASSEMBLE_PAIR);
+
+      push_gimplify_context (true);
+      tree dst_ptr = gimple_call_arg (stmt, 0);
+      tree src_ptr = gimple_call_arg (stmt, 1);
+      tree src_type = TREE_TYPE (src_ptr);
+      tree src = make_ssa_name (TREE_TYPE (src_type));
+      gimplify_assign (src, build_simple_mem_ref (src_ptr), &new_seq);
+
+      /* If we are not disassembling an accumulator or our destination is
+	 another accumulator, then just copy the entire thing as is.  */
+      if (fncode != MMA_BUILTIN_DISASSEMBLE_ACC
+	  || TREE_TYPE (TREE_TYPE (dst_ptr)) == vector_quad_type_node)
+	{
+	  tree dst = build_simple_mem_ref (build1 (VIEW_CONVERT_EXPR,
+						   src_type, dst_ptr));
+	  gimplify_assign (dst, src, &new_seq);
+	  pop_gimplify_context (NULL);
+	  gsi_replace_with_seq (gsi, new_seq, true);
+	  return true;
+	}
+
+      /* We're disassembling an accumulator into a different type, so we need
+	 to emit a xxmfacc instruction now, since we cannot do it later.  */
+      new_decl = rs6000_builtin_decls[MMA_BUILTIN_XXMFACC_INTERNAL];
+      new_call = gimple_build_call (new_decl, 1, src);
+      src = make_ssa_name (vector_quad_type_node);
+      gimple_call_set_lhs (new_call, src);
+      gimple_seq_add_stmt (&new_seq, new_call);
+
+      /* Copy the accumulator vector by vector.  */
+      tree dst_type = build_pointer_type_for_mode (unsigned_V16QI_type_node,
+						   ptr_mode, true);
+      tree dst_base = build1 (VIEW_CONVERT_EXPR, dst_type, dst_ptr);
+      tree array_type = build_array_type_nelts (unsigned_V16QI_type_node, 4);
+      tree src_array = build1 (VIEW_CONVERT_EXPR, array_type, src);
+      for (unsigned i = 0; i < 4; i++)
+	{
+	  tree ref = build4 (ARRAY_REF, unsigned_V16QI_type_node, src_array,
+			     build_int_cst (size_type_node, i),
+			     NULL_TREE, NULL_TREE);
+	  tree dst = build2 (MEM_REF, unsigned_V16QI_type_node, dst_base,
+			     build_int_cst (dst_type, i * 16));
+	  gimplify_assign (dst, ref, &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 follows immediately after this one.  */
+  new_decl = rs6000_builtin_decls[fncode + 1];
+  tree lhs, mem, op[MAX_MMA_OPERANDS];
+  tree acc = gimple_call_arg (stmt, 0);
+  if (TREE_CODE (acc) == PARM_DECL)
+    mem = build1 (INDIRECT_REF, TREE_TYPE (TREE_TYPE (acc)), acc);
+  else
+    mem = build_simple_mem_ref (acc);
+  push_gimplify_context (true);
+
+  if ((attr & RS6000_BTC_QUAD) != 0)
+    {
+      /* This built-in has a pass-by-reference accumulator input, so load it
+	 into a temporary accumulator for use as a pass-by-value input.  */
+      op[0] = make_ssa_name (vector_quad_type_node);
+      for (unsigned i = 1; i < nopnds; i++)
+	op[i] = gimple_call_arg (stmt, i);
+      gimplify_assign (op[0], mem, &new_seq);
+    }
+  else
+    {
+      /* This built-in does not use its pass-by-reference accumulator argument
+	 as an input argument, so remove it from the input list.  */
+      nopnds--;
+      for (unsigned i = 0; i < nopnds; i++)
+	op[i] = gimple_call_arg (stmt, i + 1);
+    }
+
+  switch (nopnds)
+    {
+    case 0:
+      new_call = gimple_build_call (new_decl, 0);
+      break;
+    case 1:
+      new_call = gimple_build_call (new_decl, 1, op[0]);
+      break;
+    case 2:
+      new_call = gimple_build_call (new_decl, 2, op[0], op[1]);
+      break;
+    case 3:
+      new_call = gimple_build_call (new_decl, 3, op[0], op[1], op[2]);
+      break;
+    case 4:
+      new_call = gimple_build_call (new_decl, 4, op[0], op[1], op[2], op[3]);
+      break;
+    case 5:
+      new_call = gimple_build_call (new_decl, 5, op[0], op[1], op[2], op[3],
+				    op[4]);
+      break;
+    case 6:
+      new_call = gimple_build_call (new_decl, 6, op[0], op[1], op[2], op[3],
+				    op[4], op[5]);
+      break;
+    case 7:
+      new_call = gimple_build_call (new_decl, 7, op[0], op[1], op[2], op[3],
+				    op[4], op[5], op[6]);
+      break;
+    default:
+      gcc_unreachable ();
+    }
+
+  if (fncode == MMA_BUILTIN_ASSEMBLE_PAIR)
+    lhs = make_ssa_name (vector_pair_type_node);
+  else
+    lhs = make_ssa_name (vector_quad_type_node);
+  gimple_call_set_lhs (new_call, lhs);
+  gimple_seq_add_stmt (&new_seq, new_call);
+  gimplify_assign (mem, lhs, &new_seq);
+  pop_gimplify_context (NULL);
+  gsi_replace_with_seq (gsi, new_seq, true);
+
+  return true;
+}
+
 /* Fold a machine-dependent built-in in GIMPLE.  (For folding into
    a constant, use rs6000_fold_builtin.)  */
 
@@ -10868,11 +11214,12 @@  rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
     return false;
 
   /* Don't fold invalid builtins, let rs6000_expand_builtin diagnose it.  */
-  HOST_WIDE_INT mask = rs6000_builtin_info[uns_fncode].mask;
-  bool func_valid_p = (rs6000_builtin_mask & mask) == mask;
-  if (!func_valid_p)
+  if (!rs6000_builtin_is_supported_p (fn_code))
     return false;
 
+  if (rs6000_gimple_fold_mma_builtin (gsi))
+    return true;
+
   switch (fn_code)
     {
     /* Flavors of vec_add.  We deliberately don't expand
@@ -12007,6 +12354,13 @@  rs6000_expand_builtin (tree exp, rtx target, rtx subtarget ATTRIBUTE_UNUSED,
       break;
     }
 
+  if (TARGET_MMA)
+    {
+      ret = mma_expand_builtin (exp, target, &success);
+
+      if (success)
+	return ret;
+    }
   if (TARGET_ALTIVEC)
     {
       ret = altivec_expand_builtin (exp, target, &success);
@@ -12022,7 +12376,7 @@  rs6000_expand_builtin (tree exp, rtx target, rtx subtarget ATTRIBUTE_UNUSED,
 	return ret;
     }  
 
-  unsigned attr = rs6000_builtin_info[uns_fcode].attr & RS6000_BTC_TYPE_MASK;
+  unsigned attr = rs6000_builtin_info[uns_fcode].attr & RS6000_BTC_OPND_MASK;
   /* RS6000_BTC_SPECIAL represents no-operand operators.  */
   gcc_assert (attr == RS6000_BTC_UNARY
 	      || attr == RS6000_BTC_BINARY
@@ -12205,7 +12559,7 @@  rs6000_init_builtins (void)
   else
     ieee128_float_type_node = ibm128_float_type_node = long_double_type_node;
 
-  /* Vector paired and vector quad support.  */
+  /* Vector pair and vector quad support.  */
   if (TARGET_MMA)
     {
       tree oi_uns_type = make_unsigned_type (256);
@@ -12287,6 +12641,8 @@  rs6000_init_builtins (void)
      the target attribute.  */
   if (TARGET_EXTRA_BUILTINS)
     altivec_init_builtins ();
+  if (TARGET_MMA)
+    mma_init_builtins ();
   if (TARGET_HTM)
     htm_init_builtins ();
 
@@ -13012,6 +13368,119 @@  altivec_init_builtins (void)
 
 }
 
+static void
+mma_init_builtins (void)
+{
+  const struct builtin_description *d = bdesc_mma;
+
+  for (unsigned i = 0; i < ARRAY_SIZE (bdesc_mma); i++, d++)
+    {
+      tree op[MAX_MMA_OPERANDS], type;
+      HOST_WIDE_INT mask = d->mask;
+      unsigned icode = (unsigned) d->icode;
+      unsigned attr = rs6000_builtin_info[d->code].attr;
+      int attr_args = (attr & RS6000_BTC_OPND_MASK);
+      bool gimple_func = (attr & RS6000_BTC_GIMPLE);
+      unsigned nopnds = 0;
+
+      if ((mask & rs6000_builtin_mask) != mask)
+	{
+	  if (TARGET_DEBUG_BUILTIN)
+	    fprintf (stderr, "mma_builtin, skip binary %s\n", d->name);
+	  continue;
+	}
+
+      if (d->name == 0)
+	{
+	  if (TARGET_DEBUG_BUILTIN)
+	    fprintf (stderr, "mma_builtin, bdesc_mma[%ld] no name\n",
+		     (long unsigned) i);
+	  continue;
+	}
+
+      if (gimple_func)
+	{
+	  gcc_assert (icode == CODE_FOR_nothing);
+	  op[nopnds++] = void_type_node;
+	  /* Some MMA built-ins that are expanded into gimple are converted
+	     into internal MMA built-ins that are expanded into rtl.
+	     The internal built-in follows immediately after this built-in.  */
+	  icode = d[1].icode;
+	}
+      else
+	{
+	  if ((attr & RS6000_BTC_QUAD) == 0)
+	    attr_args--;
+
+	  /* Ensure we have the correct number and type of operands.  */
+	  gcc_assert (attr_args == insn_data[icode].n_operands - 1);
+	}
+
+      if (icode == CODE_FOR_nothing)
+	{
+	  /* This is a disassemble MMA built-in function.  */
+	  gcc_assert (attr_args == RS6000_BTC_BINARY
+		      && (d->code == MMA_BUILTIN_DISASSEMBLE_ACC
+			  || d->code == MMA_BUILTIN_DISASSEMBLE_PAIR));
+	  op[nopnds++] = build_pointer_type (void_type_node);
+	  if (attr & RS6000_BTC_QUAD)
+	    op[nopnds++] = build_pointer_type (vector_quad_type_node);
+	  else
+	    op[nopnds++] = build_pointer_type (vector_pair_type_node);
+	}
+      else
+	{
+	  /* This is a normal MMA built-in function.  */
+	  unsigned j = (attr & RS6000_BTC_QUAD) ? 1 : 0;
+	  for (; j < insn_data[icode].n_operands; j++)
+	    {
+	      machine_mode mode = insn_data[icode].operand[j].mode;
+	      if (gimple_func && mode == PXImode)
+		op[nopnds++] = build_pointer_type (vector_quad_type_node);
+	      else if (gimple_func && mode == POImode
+		       && d->code == MMA_BUILTIN_ASSEMBLE_PAIR)
+		op[nopnds++] = build_pointer_type (vector_pair_type_node);
+	      else
+		/* MMA uses unsigned types.  */
+		op[nopnds++] = builtin_mode_to_type[mode][1];
+	    }
+	}
+
+      switch (nopnds)
+	{
+	case 1:
+	  type = build_function_type_list (op[0], NULL_TREE);
+	  break;
+	case 2:
+	  type = build_function_type_list (op[0], op[1], NULL_TREE);
+	  break;
+	case 3:
+	  type = build_function_type_list (op[0], op[1], op[2], NULL_TREE);
+	  break;
+	case 4:
+	  type = build_function_type_list (op[0], op[1], op[2], op[3],
+					   NULL_TREE);
+	  break;
+	case 5:
+	  type = build_function_type_list (op[0], op[1], op[2], op[3], op[4],
+					   NULL_TREE);
+	  break;
+	case 6:
+	  type = build_function_type_list (op[0], op[1], op[2], op[3], op[4],
+					   op[5], NULL_TREE);
+	  break;
+	case 7:
+	  type = build_function_type_list (op[0], op[1], op[2], op[3], op[4],
+					   op[5], op[6], NULL_TREE);
+	  break;
+	default:
+	  gcc_unreachable ();
+	}
+
+      def_builtin (d->name, type, d->code);
+    }
+}
+
 static void
 htm_init_builtins (void)
 {
@@ -13026,7 +13495,7 @@  htm_init_builtins (void)
       HOST_WIDE_INT mask = d->mask;
       unsigned attr = rs6000_builtin_info[d->code].attr;
       bool void_func = (attr & RS6000_BTC_VOID);
-      int attr_args = (attr & RS6000_BTC_TYPE_MASK);
+      int attr_args = (attr & RS6000_BTC_OPND_MASK);
       int nopnds = 0;
       tree gpr_type_node;
       tree rettype;
@@ -13192,6 +13661,8 @@  builtin_function_type (machine_mode mode_ret, machine_mode mode_arg0,
     case P8V_BUILTIN_VGBBD:
     case MISC_BUILTIN_CDTBCD:
     case MISC_BUILTIN_CBCDTD:
+    case VSX_BUILTIN_XVCVSPBF16:
+    case VSX_BUILTIN_XVCVBF16SP:
       h.uns_p[0] = 1;
       h.uns_p[1] = 1;
       break;
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 5948f63ba4c..62f05eeb975 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -9944,7 +9944,8 @@  rs6000_emit_move (rtx dest, rtx source, machine_mode mode)
 
     case E_POImode:
     case E_PXImode:
-      if (CONSTANT_P (operands[1]))
+      if (CONSTANT_P (operands[1])
+	  && INTVAL (operands[1]) != 0)
 	error ("%qs is an opaque type, and you can't set it to other values.",
 	       (mode == POImode) ? "__vector_pair" : "__vector_quad");
       break;
@@ -12856,6 +12857,14 @@  print_operand (FILE *file, rtx x, int code)
       /* %c is output_addr_const if a CONSTANT_ADDRESS_P, otherwise
 	 output_operand.  */
 
+    case 'A':
+      /* Write the MMA accumulator number associated with VSX register X.  */
+      if (!REG_P (x) || !FP_REGNO_P (REGNO (x)) || (REGNO (x) % 4) != 0)
+	output_operand_lossage ("invalid %%A value");
+      else
+	fprintf (file, "%d", (REGNO (x) - FIRST_FPR_REGNO) / 4);
+      return;
+
     case 'D':
       /* Like 'J' but get to the GT bit only.  */
       if (!REG_P (x) || !CR_REGNO_P (REGNO (x)))
@@ -15968,6 +15977,12 @@  rs6000_split_multireg_move (rtx dst, rtx src)
 	  unsigned offset = 0;
 	  unsigned size = GET_MODE_SIZE (reg_mode);
 
+	  /* If we are reading an accumulator register, we have to
+	     deprime it before we can access it.  */
+	  if (TARGET_MMA
+	      && GET_MODE (src) == PXImode && FP_REGNO_P (REGNO (src)))
+	    emit_insn (gen_mma_xxmfacc (src, src));
+
 	  for (int i = nregs - 1; i >= 0; i--)
 	    {
 	      rtx dst2 = adjust_address (dst, reg_mode, offset);
@@ -15994,6 +16009,32 @@  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
+	      && GET_MODE (dst) == PXImode && FP_REGNO_P (REGNO (dst)))
+	    emit_insn (gen_mma_xxmtacc (dst, dst));
+
+	  return;
+	}
+
+      if (GET_CODE (src) == UNSPEC)
+	{
+	  gcc_assert (REG_P (dst)
+		      && FP_REGNO_P (REGNO (dst))
+		      && XINT (src, 1) == UNSPEC_MMA_ASSEMBLE_ACC);
+
+	  reg_mode = GET_MODE (XVECEXP (src, 0, 0));
+	  for (int i = 0; i < XVECLEN (src, 0); i++)
+	    {
+	      rtx dst_i = gen_rtx_REG (reg_mode, reg + i);
+	      emit_insn (gen_rtx_SET (dst_i, XVECEXP (src, 0, i)));
+	    }
+
+	  /* We are writing an accumulator register, so we have to
+	     prime it after we've written it.  */
+	  emit_insn (gen_mma_xxmtacc (dst, dst));
+
 	  return;
 	}
 
@@ -16002,6 +16043,12 @@  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
+	  && GET_MODE (src) == PXImode && FP_REGNO_P (REGNO (src)))
+	emit_insn (gen_mma_xxmfacc (src, src));
+
       /* Move register range backwards, if we might have destructive
 	 overlap.  */
       int i;
@@ -16010,6 +16057,12 @@  rs6000_split_multireg_move (rtx dst, rtx src)
 						     i * reg_mode_size),
 				simplify_gen_subreg (reg_mode, src, mode,
 						     i * reg_mode_size)));
+
+      /* If we are writing an accumulator register, we have to
+	 prime it after we've written it.  */
+      if (TARGET_MMA
+	  && GET_MODE (dst) == PXImode && FP_REGNO_P (REGNO (dst)))
+	emit_insn (gen_mma_xxmtacc (dst, dst));
     }
   else
     {
@@ -16142,6 +16195,12 @@  rs6000_split_multireg_move (rtx dst, rtx src)
 	    gcc_assert (rs6000_offsettable_memref_p (dst, reg_mode, true));
 	}
 
+      /* If we are reading an accumulator register, we have to
+	 deprime it before we can access it.  */
+      if (TARGET_MMA && REG_P (src)
+	  && GET_MODE (src) == PXImode && FP_REGNO_P (REGNO (src)))
+	emit_insn (gen_mma_xxmfacc (src, src));
+
       for (i = 0; i < nregs; i++)
 	{
 	  /* Calculate index to next subword.  */
@@ -16159,6 +16218,13 @@  rs6000_split_multireg_move (rtx dst, rtx src)
 				  simplify_gen_subreg (reg_mode, src, mode,
 						       j * reg_mode_size)));
 	}
+
+      /* If we are writing an accumulator register, we have to
+	 prime it after we've written it.  */
+      if (TARGET_MMA && REG_P (dst)
+	  && GET_MODE (dst) == PXImode && FP_REGNO_P (REGNO (dst)))
+	emit_insn (gen_mma_xxmtacc (dst, dst));
+
       if (restore_basereg != NULL_RTX)
 	emit_insn (restore_basereg);
     }
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index 9c103bf8f7d..f3883b51255 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -2251,20 +2251,24 @@  extern int frame_pointer_needed;
    flags macros, but we've run out of bits, so we now map the options into new
    settings used here.  */
 
-/* Builtin attributes.  */
-#define RS6000_BTC_SPECIAL	0x00000000	/* Special function.  */
+/* Builtin operand count.  */
 #define RS6000_BTC_UNARY	0x00000001	/* normal unary function.  */
 #define RS6000_BTC_BINARY	0x00000002	/* normal binary function.  */
 #define RS6000_BTC_TERNARY	0x00000003	/* normal ternary function.  */
 #define RS6000_BTC_QUATERNARY	0x00000004	/* normal quaternary
 						   function. */
+#define RS6000_BTC_QUINARY	0x00000005	/* normal quinary function.  */
+#define RS6000_BTC_SENARY	0x00000006	/* normal senary function.  */
+#define RS6000_BTC_OPND_MASK	0x00000007	/* Mask to isolate operands. */
 
-#define RS6000_BTC_PREDICATE	0x00000005	/* predicate function.  */
-#define RS6000_BTC_ABS		0x00000006	/* Altivec/VSX ABS
+/* Builtin attributes.  */
+#define RS6000_BTC_SPECIAL	0x00000000	/* Special function.  */
+#define RS6000_BTC_PREDICATE	0x00000008	/* predicate function.  */
+#define RS6000_BTC_ABS		0x00000010	/* Altivec/VSX ABS
 						   function.  */
-#define RS6000_BTC_DST		0x00000007	/* Altivec DST function.  */
+#define RS6000_BTC_DST		0x00000020	/* Altivec DST function.  */
 
-#define RS6000_BTC_TYPE_MASK	0x0000000f	/* Mask to isolate types */
+#define RS6000_BTC_TYPE_MASK	0x0000003f	/* Mask to isolate types */
 
 #define RS6000_BTC_MISC		0x00000000	/* No special attributes.  */
 #define RS6000_BTC_CONST	0x00000100	/* Neither uses, nor
@@ -2273,13 +2277,18 @@  extern int frame_pointer_needed;
 						   state/mem and does
 						   not modify global state.  */
 #define RS6000_BTC_FP		0x00000400	/* depends on rounding mode.  */
-#define RS6000_BTC_ATTR_MASK	0x00000700	/* Mask of the attributes.  */
+#define RS6000_BTC_QUAD		0x00000800	/* Uses a register quad.  */
+#define RS6000_BTC_PAIR		0x00001000	/* Uses a register pair.  */
+#define RS6000_BTC_QUADPAIR	0x00001800	/* Uses a quad and a pair.  */
+#define RS6000_BTC_ATTR_MASK	0x00001f00	/* Mask of the attributes.  */
 
 /* Miscellaneous information.  */
 #define RS6000_BTC_SPR		0x01000000	/* function references SPRs.  */
 #define RS6000_BTC_VOID		0x02000000	/* function has no return value.  */
 #define RS6000_BTC_CR		0x04000000	/* function references a CR.  */
 #define RS6000_BTC_OVERLOADED	0x08000000	/* function is overloaded.  */
+#define RS6000_BTC_GIMPLE	0x10000000	/* function should be expanded
+						   into gimple.  */
 #define RS6000_BTC_MISC_MASK	0x1f000000	/* Mask of the misc info.  */
 
 /* Convenience macros to document the instruction type.  */
@@ -2348,6 +2357,7 @@  extern int frame_pointer_needed;
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
@@ -2359,6 +2369,7 @@  extern int frame_pointer_needed;
 #define RS6000_BUILTIN_A(ENUM, NAME, MASK, ATTR, ICODE) ENUM,
 #define RS6000_BUILTIN_D(ENUM, NAME, MASK, ATTR, ICODE) ENUM,
 #define RS6000_BUILTIN_H(ENUM, NAME, MASK, ATTR, ICODE) ENUM,
+#define RS6000_BUILTIN_M(ENUM, NAME, MASK, ATTR, ICODE) ENUM,
 #define RS6000_BUILTIN_P(ENUM, NAME, MASK, ATTR, ICODE) ENUM,
 #define RS6000_BUILTIN_X(ENUM, NAME, MASK, ATTR, ICODE) ENUM,
 
@@ -2377,6 +2388,7 @@  enum rs6000_builtins
 #undef RS6000_BUILTIN_A
 #undef RS6000_BUILTIN_D
 #undef RS6000_BUILTIN_H
+#undef RS6000_BUILTIN_M
 #undef RS6000_BUILTIN_P
 #undef RS6000_BUILTIN_X
 
diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index b35a15a2be1..48182cec229 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -19,6 +19,241 @@ 
 ;; along with GCC; see the file COPYING3.  If not see
 ;; <http://www.gnu.org/licenses/>.
 
+
+(define_constants [(MAX_MMA_OPERANDS 7)])
+
+;; Constants for creating unspecs
+
+(define_c_enum "unspec"
+  [UNSPEC_MMA_ASSEMBLE_ACC
+   UNSPEC_MMA_PMXVBF16GER2
+   UNSPEC_MMA_PMXVBF16GER2NN
+   UNSPEC_MMA_PMXVBF16GER2NP
+   UNSPEC_MMA_PMXVBF16GER2PN
+   UNSPEC_MMA_PMXVBF16GER2PP
+   UNSPEC_MMA_PMXVF16GER2
+   UNSPEC_MMA_PMXVF16GER2NN
+   UNSPEC_MMA_PMXVF16GER2NP
+   UNSPEC_MMA_PMXVF16GER2PN
+   UNSPEC_MMA_PMXVF16GER2PP
+   UNSPEC_MMA_PMXVF32GER
+   UNSPEC_MMA_PMXVF32GERNN
+   UNSPEC_MMA_PMXVF32GERNP
+   UNSPEC_MMA_PMXVF32GERPN
+   UNSPEC_MMA_PMXVF32GERPP
+   UNSPEC_MMA_PMXVF64GER
+   UNSPEC_MMA_PMXVF64GERNN
+   UNSPEC_MMA_PMXVF64GERNP
+   UNSPEC_MMA_PMXVF64GERPN
+   UNSPEC_MMA_PMXVF64GERPP
+   UNSPEC_MMA_PMXVI16GER2
+   UNSPEC_MMA_PMXVI16GER2PP
+   UNSPEC_MMA_PMXVI16GER2S
+   UNSPEC_MMA_PMXVI16GER2SPP
+   UNSPEC_MMA_PMXVI4GER8
+   UNSPEC_MMA_PMXVI4GER8PP
+   UNSPEC_MMA_PMXVI8GER4
+   UNSPEC_MMA_PMXVI8GER4PP
+   UNSPEC_MMA_PMXVI8GER4SPP
+   UNSPEC_MMA_XVBF16GER2
+   UNSPEC_MMA_XVBF16GER2NN
+   UNSPEC_MMA_XVBF16GER2NP
+   UNSPEC_MMA_XVBF16GER2PN
+   UNSPEC_MMA_XVBF16GER2PP
+   UNSPEC_MMA_XVF16GER2
+   UNSPEC_MMA_XVF16GER2NN
+   UNSPEC_MMA_XVF16GER2NP
+   UNSPEC_MMA_XVF16GER2PN
+   UNSPEC_MMA_XVF16GER2PP
+   UNSPEC_MMA_XVF32GER
+   UNSPEC_MMA_XVF32GERNN
+   UNSPEC_MMA_XVF32GERNP
+   UNSPEC_MMA_XVF32GERPN
+   UNSPEC_MMA_XVF32GERPP
+   UNSPEC_MMA_XVF64GER
+   UNSPEC_MMA_XVF64GERNN
+   UNSPEC_MMA_XVF64GERNP
+   UNSPEC_MMA_XVF64GERPN
+   UNSPEC_MMA_XVF64GERPP
+   UNSPEC_MMA_XVI16GER2
+   UNSPEC_MMA_XVI16GER2PP
+   UNSPEC_MMA_XVI16GER2S
+   UNSPEC_MMA_XVI16GER2SPP
+   UNSPEC_MMA_XVI4GER8
+   UNSPEC_MMA_XVI4GER8PP
+   UNSPEC_MMA_XVI8GER4
+   UNSPEC_MMA_XVI8GER4PP
+   UNSPEC_MMA_XVI8GER4SPP
+   UNSPEC_MMA_XXMFACC
+   UNSPEC_MMA_XXMTACC
+  ])
+
+;; MMA instructions with 1 accumulator argument
+(define_int_iterator MMA_ACC		[UNSPEC_MMA_XXMFACC
+					 UNSPEC_MMA_XXMTACC])
+
+;; MMA instructions with 2 vector arguments
+(define_int_iterator MMA_VV		[UNSPEC_MMA_XVI4GER8
+					 UNSPEC_MMA_XVI8GER4
+					 UNSPEC_MMA_XVI16GER2
+					 UNSPEC_MMA_XVI16GER2S
+					 UNSPEC_MMA_XVF16GER2
+					 UNSPEC_MMA_XVBF16GER2
+					 UNSPEC_MMA_XVF32GER])
+
+;; MMA instructions with 1 accumulator and 2 vector arguments
+(define_int_iterator MMA_AVV		[UNSPEC_MMA_XVI4GER8PP
+					 UNSPEC_MMA_XVI8GER4PP
+					 UNSPEC_MMA_XVI8GER4SPP
+					 UNSPEC_MMA_XVI16GER2PP
+					 UNSPEC_MMA_XVI16GER2SPP
+					 UNSPEC_MMA_XVF16GER2PP
+					 UNSPEC_MMA_XVF16GER2PN
+					 UNSPEC_MMA_XVF16GER2NP
+					 UNSPEC_MMA_XVF16GER2NN
+					 UNSPEC_MMA_XVBF16GER2PP
+					 UNSPEC_MMA_XVBF16GER2PN
+					 UNSPEC_MMA_XVBF16GER2NP
+					 UNSPEC_MMA_XVBF16GER2NN
+					 UNSPEC_MMA_XVF32GERPP
+					 UNSPEC_MMA_XVF32GERPN
+					 UNSPEC_MMA_XVF32GERNP
+					 UNSPEC_MMA_XVF32GERNN])
+
+;; MMA instructions with 1 vector pair and 1 vector arguments
+(define_int_iterator MMA_PV		[UNSPEC_MMA_XVF64GER])
+
+;; MMA instructions with 1 accumulator, 1 vector pair and 1 vector arguments
+(define_int_iterator MMA_APV		[UNSPEC_MMA_XVF64GERPP
+					 UNSPEC_MMA_XVF64GERPN
+					 UNSPEC_MMA_XVF64GERNP
+					 UNSPEC_MMA_XVF64GERNN])
+
+;; MMA instructions with 2 vector, 2 4-bit and 1 8-bit arguments
+(define_int_iterator MMA_VVI4I4I8	[UNSPEC_MMA_PMXVI4GER8])
+
+;; MMA instructions with 1 accumulator, 2 vector, 2 4-bit and 1 8-bit arguments
+(define_int_iterator MMA_AVVI4I4I8	[UNSPEC_MMA_PMXVI4GER8PP])
+
+;; MMA instructions with 2 vector, 2 4-bit and 1 2-bit arguments
+(define_int_iterator MMA_VVI4I4I2	[UNSPEC_MMA_PMXVI16GER2
+					 UNSPEC_MMA_PMXVI16GER2S
+					 UNSPEC_MMA_PMXVF16GER2
+					 UNSPEC_MMA_PMXVBF16GER2])
+
+;; MMA instructions with 1 accumulator, 2 vector, 2 4-bit and 1 2-bit arguments
+(define_int_iterator MMA_AVVI4I4I2	[UNSPEC_MMA_PMXVI16GER2PP
+					 UNSPEC_MMA_PMXVI16GER2SPP
+					 UNSPEC_MMA_PMXVF16GER2PP
+					 UNSPEC_MMA_PMXVF16GER2PN
+					 UNSPEC_MMA_PMXVF16GER2NP
+					 UNSPEC_MMA_PMXVF16GER2NN
+					 UNSPEC_MMA_PMXVBF16GER2PP
+					 UNSPEC_MMA_PMXVBF16GER2PN
+					 UNSPEC_MMA_PMXVBF16GER2NP
+					 UNSPEC_MMA_PMXVBF16GER2NN])
+
+;; MMA instructions with 2 vector and 2 4-bit arguments
+(define_int_iterator MMA_VVI4I4		[UNSPEC_MMA_PMXVF32GER])
+
+;; MMA instructions with 1 accumulator, 2 vector and 2 4-bit arguments
+(define_int_iterator MMA_AVVI4I4	[UNSPEC_MMA_PMXVF32GERPP
+					 UNSPEC_MMA_PMXVF32GERPN
+					 UNSPEC_MMA_PMXVF32GERNP
+					 UNSPEC_MMA_PMXVF32GERNN])
+
+;; MMA instructions with 2 vector, 1 4-bit and 1 2-bit arguments
+(define_int_iterator MMA_PVI4I2		[UNSPEC_MMA_PMXVF64GER])
+
+;; MMA instructions with 1 accumulator, 2 vector, 1 4-bit and 1 2-bit arguments
+(define_int_iterator MMA_APVI4I2	[UNSPEC_MMA_PMXVF64GERPP
+					 UNSPEC_MMA_PMXVF64GERPN
+					 UNSPEC_MMA_PMXVF64GERNP
+					 UNSPEC_MMA_PMXVF64GERNN])
+
+;; MMA instructions with 2 vector and 3 4-bit arguments
+(define_int_iterator MMA_VVI4I4I4	[UNSPEC_MMA_PMXVI8GER4])
+
+;; MMA instructions with 1 accumulator, 2 vector and 3 4-bit arguments
+(define_int_iterator MMA_AVVI4I4I4	[UNSPEC_MMA_PMXVI8GER4PP
+					 UNSPEC_MMA_PMXVI8GER4SPP])
+
+(define_int_attr acc		[(UNSPEC_MMA_XXMFACC		"xxmfacc")
+				 (UNSPEC_MMA_XXMTACC		"xxmtacc")])
+
+(define_int_attr vv		[(UNSPEC_MMA_XVI4GER8		"xvi4ger8")
+				 (UNSPEC_MMA_XVI8GER4		"xvi8ger4")
+				 (UNSPEC_MMA_XVI16GER2		"xvi16ger2")
+				 (UNSPEC_MMA_XVI16GER2S		"xvi16ger2s")
+				 (UNSPEC_MMA_XVF16GER2		"xvf16ger2")
+				 (UNSPEC_MMA_XVBF16GER2		"xvbf16ger2")
+				 (UNSPEC_MMA_XVF32GER		"xvf32ger")])
+
+(define_int_attr avv		[(UNSPEC_MMA_XVI4GER8PP		"xvi4ger8pp")
+				 (UNSPEC_MMA_XVI8GER4PP		"xvi8ger4pp")
+				 (UNSPEC_MMA_XVI8GER4SPP	"xvi8ger4spp")
+				 (UNSPEC_MMA_XVI16GER2PP	"xvi16ger2pp")
+				 (UNSPEC_MMA_XVI16GER2SPP	"xvi16ger2spp")
+				 (UNSPEC_MMA_XVF16GER2PP	"xvf16ger2pp")
+				 (UNSPEC_MMA_XVF16GER2PN	"xvf16ger2pn")
+				 (UNSPEC_MMA_XVF16GER2NP	"xvf16ger2np")
+				 (UNSPEC_MMA_XVF16GER2NN	"xvf16ger2nn")
+				 (UNSPEC_MMA_XVBF16GER2PP	"xvbf16ger2pp")
+				 (UNSPEC_MMA_XVBF16GER2PN	"xvbf16ger2pn")
+				 (UNSPEC_MMA_XVBF16GER2NP	"xvbf16ger2np")
+				 (UNSPEC_MMA_XVBF16GER2NN	"xvbf16ger2nn")
+				 (UNSPEC_MMA_XVF32GERPP		"xvf32gerpp")
+				 (UNSPEC_MMA_XVF32GERPN		"xvf32gerpn")
+				 (UNSPEC_MMA_XVF32GERNP		"xvf32gernp")
+				 (UNSPEC_MMA_XVF32GERNN		"xvf32gernn")])
+
+(define_int_attr pv		[(UNSPEC_MMA_XVF64GER		"xvf64ger")])
+
+(define_int_attr apv		[(UNSPEC_MMA_XVF64GERPP		"xvf64gerpp")
+				 (UNSPEC_MMA_XVF64GERPN		"xvf64gerpn")
+				 (UNSPEC_MMA_XVF64GERNP		"xvf64gernp")
+				 (UNSPEC_MMA_XVF64GERNN		"xvf64gernn")])
+
+(define_int_attr vvi4i4i8	[(UNSPEC_MMA_PMXVI4GER8		"pmxvi4ger8")])
+
+(define_int_attr avvi4i4i8	[(UNSPEC_MMA_PMXVI4GER8PP	"pmxvi4ger8pp")])
+
+(define_int_attr vvi4i4i2	[(UNSPEC_MMA_PMXVI16GER2	"pmxvi16ger2")
+				 (UNSPEC_MMA_PMXVI16GER2S	"pmxvi16ger2s")
+				 (UNSPEC_MMA_PMXVF16GER2	"pmxvf16ger2")
+				 (UNSPEC_MMA_PMXVBF16GER2	"pmxvbf16ger2")])
+
+(define_int_attr avvi4i4i2	[(UNSPEC_MMA_PMXVI16GER2PP	"pmxvi16ger2pp")
+				 (UNSPEC_MMA_PMXVI16GER2SPP	"pmxvi16ger2spp")
+				 (UNSPEC_MMA_PMXVF16GER2PP	"pmxvf16ger2pp")
+				 (UNSPEC_MMA_PMXVF16GER2PN	"pmxvf16ger2pn")
+				 (UNSPEC_MMA_PMXVF16GER2NP	"pmxvf16ger2np")
+				 (UNSPEC_MMA_PMXVF16GER2NN	"pmxvf16ger2nn")
+				 (UNSPEC_MMA_PMXVBF16GER2PP	"pmxvbf16ger2pp")
+				 (UNSPEC_MMA_PMXVBF16GER2PN	"pmxvbf16ger2pn")
+				 (UNSPEC_MMA_PMXVBF16GER2NP	"pmxvbf16ger2np")
+				 (UNSPEC_MMA_PMXVBF16GER2NN	"pmxvbf16ger2nn")])
+
+(define_int_attr vvi4i4		[(UNSPEC_MMA_PMXVF32GER		"pmxvf32ger")])
+
+(define_int_attr avvi4i4	[(UNSPEC_MMA_PMXVF32GERPP	"pmxvf32gerpp")
+				 (UNSPEC_MMA_PMXVF32GERPN	"pmxvf32gerpn")
+				 (UNSPEC_MMA_PMXVF32GERNP	"pmxvf32gernp")
+				 (UNSPEC_MMA_PMXVF32GERNN	"pmxvf32gernn")])
+
+(define_int_attr pvi4i2		[(UNSPEC_MMA_PMXVF64GER		"pmxvf64ger")])
+
+(define_int_attr apvi4i2	[(UNSPEC_MMA_PMXVF64GERPP	"pmxvf64gerpp")
+				 (UNSPEC_MMA_PMXVF64GERPN	"pmxvf64gerpn")
+				 (UNSPEC_MMA_PMXVF64GERNP	"pmxvf64gernp")
+				 (UNSPEC_MMA_PMXVF64GERNN	"pmxvf64gernn")])
+
+(define_int_attr vvi4i4i4	[(UNSPEC_MMA_PMXVI8GER4		"pmxvi8ger4")])
+
+(define_int_attr avvi4i4i4	[(UNSPEC_MMA_PMXVI8GER4PP	"pmxvi8ger4pp")
+				 (UNSPEC_MMA_PMXVI8GER4SPP	"pmxvi8ger4spp")])
+
+
 ;; Vector load/store pair operations
 ;; We need to define an OImode move pattern, even though we don't enable it,
 ;; because the machine independent parts of the compiler at times uses the
@@ -111,10 +346,11 @@  (define_expand "movpxi"
 })
 
 (define_insn_and_split "*movpxi"
-  [(set (match_operand:PXI 0 "nonimmediate_operand" "=d,m,d")
-	(match_operand:PXI 1 "input_operand" "m,d,d"))]
+  [(set (match_operand:PXI 0 "nonimmediate_operand" "=d,m,d,d")
+	(match_operand:PXI 1 "input_operand"    "m,d,d,O"))]
   "TARGET_MMA
-   && (gpc_reg_operand (operands[0], PXImode)
+   && ((gpc_reg_operand (operands[0], PXImode)
+	&& !(CONST_INT_P (operands[1]) && INTVAL (operands[1]) == 0))
        || gpc_reg_operand (operands[1], PXImode))"
   "#"
   "&& reload_completed"
@@ -123,6 +359,249 @@  (define_insn_and_split "*movpxi"
   rs6000_split_multireg_move (operands[0], operands[1]);
   DONE;
 }
-  [(set_attr "type" "vecload,vecstore,veclogical")
-   (set_attr "length" "8,8,16")
-   (set_attr "max_prefixed_insns" "2,2,*")])
+  [(set_attr "type" "vecload,vecstore,veclogical,mma")
+   (set_attr "length" "8,8,16,*")
+   (set_attr "max_prefixed_insns" "2,2,*,*")])
+
+(define_expand "mma_assemble_pair"
+  [(match_operand:POI 0 "vsx_register_operand")
+   (match_operand:V16QI 1 "input_operand")
+   (match_operand:V16QI 2 "input_operand")]
+  "TARGET_MMA"
+{
+  rtx dst;
+
+  /* Let the compiler know the code below fully defines our output value.  */
+  emit_clobber (operands[0]);
+
+  dst = simplify_gen_subreg (V16QImode, operands[0], POImode, 0);
+  emit_move_insn (dst, operands[1]);
+  dst = simplify_gen_subreg (V16QImode, operands[0], POImode, 16);
+  emit_move_insn (dst, operands[2]);
+  DONE;
+})
+
+(define_expand "mma_assemble_acc"
+  [(match_operand:PXI 0 "fpr_reg_operand")
+   (match_operand:V16QI 1 "input_operand")
+   (match_operand:V16QI 2 "input_operand")
+   (match_operand:V16QI 3 "input_operand")
+   (match_operand:V16QI 4 "input_operand")]
+  "TARGET_MMA"
+{
+  rtx src = gen_rtx_UNSPEC (PXImode,
+			    gen_rtvec (4, operands[1], operands[2],
+				       operands[3], operands[4]),
+			    UNSPEC_MMA_ASSEMBLE_ACC);
+  emit_move_insn (operands[0], src);
+  DONE;
+})
+
+(define_insn_and_split "*mma_assemble_acc"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=d")
+	(unspec:PXI [(match_operand:PXI 1 "mma_input_operand" "mwa")
+		     (match_operand:PXI 2 "mma_input_operand" "mwa")
+		     (match_operand:PXI 3 "mma_input_operand" "mwa")
+		     (match_operand:PXI 4 "mma_input_operand" "mwa")]
+		     UNSPEC_MMA_ASSEMBLE_ACC))]
+  "TARGET_MMA
+   && fpr_reg_operand (operands[0], PXImode)"
+  "#"
+  "&& reload_completed"
+  [(const_int 0)]
+{
+  rtx src = gen_rtx_UNSPEC (PXImode,
+			    gen_rtvec (4, operands[1], operands[2],
+				       operands[3], operands[4]),
+			    UNSPEC_MMA_ASSEMBLE_ACC);
+  rs6000_split_multireg_move (operands[0], src);
+  DONE;
+})
+
+;; 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.
+
+(define_insn "mma_<acc>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")]
+		    MMA_ACC))]
+  "TARGET_MMA"
+  "<acc> %A0"
+  [(set_attr "type" "mma")])
+
+(define_insn "mma_xxsetaccz"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=d")
+	(const_int 0))]
+  "TARGET_MMA"
+  "xxsetaccz %A0"
+  [(set_attr "type" "mma")])
+
+(define_insn "mma_<vv>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")]
+		     MMA_VV))]
+  "TARGET_MMA"
+  "<vv> %A0,%x1,%x2"
+  [(set_attr "type" "mma")])
+
+(define_insn "mma_<avv>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 3 "vsx_register_operand" "wa")]
+		     MMA_AVV))]
+  "TARGET_MMA"
+  "<avv> %A0,%x2,%x3"
+  [(set_attr "type" "mma")])
+
+(define_insn "mma_<pv>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:POI 1 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")]
+		     MMA_PV))]
+  "TARGET_MMA"
+  "<pv> %A0,%x1,%x2"
+  [(set_attr "type" "mma")])
+
+(define_insn "mma_<apv>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
+		     (match_operand:POI 2 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 3 "vsx_register_operand" "wa")]
+		     MMA_APV))]
+  "TARGET_MMA"
+  "<apv> %A0,%x2,%x3"
+  [(set_attr "type" "mma")])
+
+(define_insn "mma_<vvi4i4i8>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:SI 3 "const_0_to_15_operand" "n")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")
+		     (match_operand:SI 5 "u8bit_cint_operand" "n")]
+		     MMA_VVI4I4I8))]
+  "TARGET_MMA"
+  "<vvi4i4i8> %A0,%x1,%x2,%3,%4,%5"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<avvi4i4i8>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 3 "vsx_register_operand" "wa")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")
+		     (match_operand:SI 5 "const_0_to_15_operand" "n")
+		     (match_operand:SI 6 "u8bit_cint_operand" "n")]
+		     MMA_AVVI4I4I8))]
+  "TARGET_MMA"
+  "<avvi4i4i8> %A0,%x2,%x3,%4,%5,%6"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<vvi4i4i2>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:SI 3 "const_0_to_15_operand" "n")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")
+		     (match_operand:SI 5 "const_0_to_3_operand" "n")]
+		     MMA_VVI4I4I2))]
+  "TARGET_MMA"
+  "<vvi4i4i2> %A0,%x1,%x2,%3,%4,%5"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<avvi4i4i2>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 3 "vsx_register_operand" "wa")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")
+		     (match_operand:SI 5 "const_0_to_15_operand" "n")
+		     (match_operand:SI 6 "const_0_to_3_operand" "n")]
+		     MMA_AVVI4I4I2))]
+  "TARGET_MMA"
+  "<avvi4i4i2> %A0,%x2,%x3,%4,%5,%6"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<vvi4i4>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:SI 3 "const_0_to_15_operand" "n")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")]
+		     MMA_VVI4I4))]
+  "TARGET_MMA"
+  "<vvi4i4> %A0,%x1,%x2,%3,%4"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<avvi4i4>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 3 "vsx_register_operand" "wa")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")
+		     (match_operand:SI 5 "const_0_to_15_operand" "n")]
+		     MMA_AVVI4I4))]
+  "TARGET_MMA"
+  "<avvi4i4> %A0,%x2,%x3,%4,%5"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<pvi4i2>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:POI 1 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:SI 3 "const_0_to_15_operand" "n")
+		     (match_operand:SI 4 "const_0_to_3_operand" "n")]
+		     MMA_PVI4I2))]
+  "TARGET_MMA"
+  "<pvi4i2> %A0,%x1,%x2,%3,%4"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<apvi4i2>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
+		     (match_operand:POI 2 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 3 "vsx_register_operand" "wa")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")
+		     (match_operand:SI 5 "const_0_to_3_operand" "n")]
+		     MMA_APVI4I2))]
+  "TARGET_MMA"
+  "<apvi4i2> %A0,%x2,%x3,%4,%5"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<vvi4i4i4>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:SI 3 "const_0_to_15_operand" "n")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")
+		     (match_operand:SI 5 "const_0_to_15_operand" "n")]
+		     MMA_VVI4I4I4))]
+  "TARGET_MMA"
+  "<vvi4i4i4> %A0,%x1,%x2,%3,%4,%5"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
+
+(define_insn "mma_<avvi4i4i4>"
+  [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
+	(unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
+		     (match_operand:V16QI 2 "vsx_register_operand" "wa")
+		     (match_operand:V16QI 3 "vsx_register_operand" "wa")
+		     (match_operand:SI 4 "const_0_to_15_operand" "n")
+		     (match_operand:SI 5 "const_0_to_15_operand" "n")
+		     (match_operand:SI 6 "const_0_to_15_operand" "n")]
+		     MMA_AVVI4I4I4))]
+  "TARGET_MMA"
+  "<avvi4i4i4> %A0,%x2,%x3,%4,%5,%6"
+  [(set_attr "type" "mma")
+   (set_attr "length" "8")])
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 6b462a3ecdb..bbe0b4610fb 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -203,7 +203,7 @@  (define_attr "type"
    vecsimple,veccomplex,vecdiv,veccmp,veccmpsimple,vecperm,
    vecfloat,vecfdiv,vecdouble,mffgpr,mftgpr,crypto,
    veclogical,veccmpfx,vecexts,vecmove,
-   htm,htmsimple,dfp"
+   htm,htmsimple,dfp,mma"
   (const_string "integer"))
 
 ;; What data size does this instruction work on?
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index 2a28215ac5b..342927abeda 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -296,6 +296,8 @@  (define_c_enum "unspec"
    UNSPEC_VSX_DIVUD
    UNSPEC_VSX_MULSD
    UNSPEC_VSX_SIGN_EXTEND
+   UNSPEC_VSX_XVCVBF16SP
+   UNSPEC_VSX_XVCVSPBF16
    UNSPEC_VSX_XVCVSPSXDS
    UNSPEC_VSX_VSLO
    UNSPEC_VSX_EXTRACT
@@ -346,6 +348,12 @@  (define_c_enum "unspec"
    UNSPEC_XXGENPCV
   ])
 
+(define_int_iterator XVCVBF16	[UNSPEC_VSX_XVCVSPBF16
+				 UNSPEC_VSX_XVCVBF16SP])
+
+(define_int_attr xvcvbf16       [(UNSPEC_VSX_XVCVSPBF16 "xvcvspbf16")
+				 (UNSPEC_VSX_XVCVBF16SP "xvcvbf16sp")])
+
 ;; VSX moves
 
 ;; The patterns for LE permuted loads and stores come before the general
@@ -5676,3 +5684,10 @@  (define_expand "vec_unpack_<su>fix_trunc_lo_v4sf"
   DONE;
 })
 
+(define_insn "vsx_<xvcvbf16>"
+  [(set (match_operand:V16QI 0 "vsx_register_operand" "=wa")
+	(unspec:V16QI [(match_operand:V16QI 1 "vsx_register_operand" "wa")]
+		      XVCVBF16))]
+  "TARGET_FUTURE"
+  "<xvcvbf16> %x0,%x1"
+  [(set_attr "type" "vecfloat")])
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index e656e66a80c..ca51c9bbadd 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -13858,6 +13858,7 @@  instructions, but allow the compiler to schedule those calls.
 * PowerPC AltiVec/VSX Built-in Functions::
 * PowerPC Hardware Transactional Memory Built-in Functions::
 * PowerPC Atomic Memory Operation Functions::
+* PowerPC Matrix-Multiply Assist Built-in Functions::
 * RX Built-in Functions::
 * S/390 System z Built-in Functions::
 * SH Built-in Functions::
@@ -21359,6 +21360,100 @@  void amo_stdat_smax (int64_t *, int64_t);
 void amo_stdat_smin (int64_t *, int64_t);
 @end smallexample
 
+@node PowerPC Matrix-Multiply Assist Built-in Functions
+@subsection PowerPC Matrix-Multiply Assist Built-in Functions
+ISA 3.1 of the PowerPC added new Matrix-Multiply Assist (MMA) instructions.
+GCC provides support for these instructions through the following built-in
+functions which are enabled with the @code{-mmma} option.  The vec_t type
+below is defined to be a normal vector unsigned char type.  The uint2, uint4
+and uint8 parameters are 2-bit, 4-bit and 8-bit unsigned integer constants
+respectively.  The compiler will verify that they are constants and that
+their values are within range. 
+
+The built-in functions supported are:
+
+@smallexample
+void __builtin_mma_xvi4ger8 (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvi8ger4 (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvi16ger2 (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvi16ger2s (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf16ger2 (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvbf16ger2 (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf32ger (__vector_quad *, vec_t, vec_t);
+
+void __builtin_mma_xvi4ger8pp (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvi8ger4pp (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvi8ger4spp(__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvi16ger2pp (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvi16ger2spp (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf16ger2pp (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf16ger2pn (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf16ger2np (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf16ger2nn (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvbf16ger2pp (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvbf16ger2pn (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvbf16ger2np (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvbf16ger2nn (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf32gerpp (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf32gerpn (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf32gernp (__vector_quad *, vec_t, vec_t);
+void __builtin_mma_xvf32gernn (__vector_quad *, vec_t, vec_t);
+
+void __builtin_mma_pmxvi4ger8 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint8);
+void __builtin_mma_pmxvi4ger8pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint8);
+
+void __builtin_mma_pmxvi8ger4 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint4);
+void __builtin_mma_pmxvi8ger4pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint4);
+void __builtin_mma_pmxvi8ger4spp(__vector_quad *, vec_t, vec_t, uint4, uint4, uint4);
+
+void __builtin_mma_pmxvi16ger2 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvi16ger2s (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvf16ger2 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvbf16ger2 (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+
+void __builtin_mma_pmxvi16ger2pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvi16ger2spp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvf16ger2pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvf16ger2pn (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvf16ger2np (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvf16ger2nn (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvbf16ger2pp (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvbf16ger2pn (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvbf16ger2np (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+void __builtin_mma_pmxvbf16ger2nn (__vector_quad *, vec_t, vec_t, uint4, uint4, uint2);
+
+void __builtin_mma_pmxvf32ger (__vector_quad *, vec_t, vec_t, uint4, uint4);
+void __builtin_mma_pmxvf32gerpp (__vector_quad *, vec_t, vec_t, uint4, uint4);
+void __builtin_mma_pmxvf32gerpn (__vector_quad *, vec_t, vec_t, uint4, uint4);
+void __builtin_mma_pmxvf32gernp (__vector_quad *, vec_t, vec_t, uint4, uint4);
+void __builtin_mma_pmxvf32gernn (__vector_quad *, vec_t, vec_t, uint4, uint4);
+
+void __builtin_mma_xvf64ger (__vector_quad *, __vector_pair, vec_t);
+void __builtin_mma_xvf64gerpp (__vector_quad *, __vector_pair, vec_t);
+void __builtin_mma_xvf64gerpn (__vector_quad *, __vector_pair, vec_t);
+void __builtin_mma_xvf64gernp (__vector_quad *, __vector_pair, vec_t);
+void __builtin_mma_xvf64gernn (__vector_quad *, __vector_pair, vec_t);
+
+void __builtin_mma_pmxvf64ger (__vector_quad *, __vector_pair, vec_t, uint4, uint2);
+void __builtin_mma_pmxvf64gerpp (__vector_quad *, __vector_pair, vec_t, uint4, uint2);
+void __builtin_mma_pmxvf64gerpn (__vector_quad *, __vector_pair, vec_t, uint4, uint2);
+void __builtin_mma_pmxvf64gernp (__vector_quad *, __vector_pair, vec_t, uint4, uint2);
+void __builtin_mma_pmxvf64gernn (__vector_quad *, __vector_pair, vec_t, uint4, uint2);
+
+void __builtin_mma_xxmtacc (__vector_quad *);
+void __builtin_mma_xxmfacc (__vector_quad *);
+void __builtin_mma_xxsetaccz (__vector_quad *);
+
+void __builtin_mma_assemble_acc (__vector_quad *, vec_t, vec_t, vec_t, vec_t);
+void __builtin_mma_disassemble_acc (void *, __vector_quad *);
+
+void __builtin_mma_assemble_pair (__vector_pair *, vec_t, vec_t);
+void __builtin_mma_disassemble_pair (void *, __vector_pair *);
+
+vec_t __builtin_xvcvspbf16 (vec_t);
+vec_t __builtin_xvcvbf16sp (vec_t);
+@end smallexample
+
 @node RX Built-in Functions
 @subsection RX Built-in Functions
 GCC supports some of the RX instructions which cannot be expressed in