diff --git a/llvm/include/llvm/CodeGen/ValueTypes.td b/llvm/include/llvm/CodeGen/ValueTypes.td
--- a/llvm/include/llvm/CodeGen/ValueTypes.td
+++ b/llvm/include/llvm/CodeGen/ValueTypes.td
@@ -89,131 +89,133 @@
 
 def v1i64   : ValueType<64,    64>;  //   1 x i64 vector value
 def v2i64   : ValueType<128,   65>;  //   2 x i64 vector value
-def v4i64   : ValueType<256,   66>;  //   4 x i64 vector value
-def v8i64   : ValueType<512,   67>;  //   8 x i64 vector value
-def v16i64  : ValueType<1024,  68>;  //  16 x i64 vector value
-def v32i64  : ValueType<2048,  69>;  //  32 x i64 vector value
-def v64i64  : ValueType<4096,  70>;  //  64 x i64 vector value
-def v128i64 : ValueType<8192,  71>;  // 128 x i64 vector value
-def v256i64 : ValueType<16384, 72>;  // 256 x i64 vector value
-
-def v1i128 : ValueType<128, 73>;  //  1 x i128 vector value
-
-def v1f16    : ValueType<16,     74>;  //    1 x f16 vector value
-def v2f16    : ValueType<32,     75>;  //    2 x f16 vector value
-def v3f16    : ValueType<48,     76>;  //    3 x f16 vector value
-def v4f16    : ValueType<64,     77>;  //    4 x f16 vector value
-def v8f16    : ValueType<128,    78>;  //    8 x f16 vector value
-def v16f16   : ValueType<256,    79>;  //   16 x f16 vector value
-def v32f16   : ValueType<512,    80>;  //   32 x f16 vector value
-def v64f16   : ValueType<1024,   81>;  //   64 x f16 vector value
-def v128f16  : ValueType<2048,   82>;  //  128 x f16 vector value
-def v256f16  : ValueType<4096,   83>;  //  256 x f16 vector value
-def v512f16  : ValueType<8192,   84>;  //  512 x f16 vector value
-
-def v2bf16   : ValueType<32,     85>;  //    2 x bf16 vector value
-def v3bf16   : ValueType<48,     86>;  //    3 x bf16 vector value
-def v4bf16   : ValueType<64,     87>;  //    4 x bf16 vector value
-def v8bf16   : ValueType<128,    88>;  //    8 x bf16 vector value
-def v16bf16  : ValueType<256,    89>;  //   16 x bf16 vector value
-def v32bf16  : ValueType<512,    90>;  //   32 x bf16 vector value
-def v64bf16  : ValueType<1024,   91>;  //   64 x bf16 vector value
-def v128bf16 : ValueType<2048,   92>;  //  128 x bf16 vector value
-
-def v1f32    : ValueType<32,     93>;  //    1 x f32 vector value
-def v2f32    : ValueType<64,     94>;  //    2 x f32 vector value
-def v3f32    : ValueType<96,     95>;  //    3 x f32 vector value
-def v4f32    : ValueType<128,    96>;  //    4 x f32 vector value
-def v5f32    : ValueType<160,    97>;  //    5 x f32 vector value
-def v6f32    : ValueType<192,    98>;  //    6 x f32 vector value
-def v7f32    : ValueType<224,    99>;  //    7 x f32 vector value
-def v8f32    : ValueType<256,   100>;  //    8 x f32 vector value
-def v16f32   : ValueType<512,   101>;  //   16 x f32 vector value
-def v32f32   : ValueType<1024,  102>;  //   32 x f32 vector value
-def v64f32   : ValueType<2048,  103>;  //   64 x f32 vector value
-def v128f32  : ValueType<4096,  104>;  //  128 x f32 vector value
-def v256f32  : ValueType<8192,  105>;  //  256 x f32 vector value
-def v512f32  : ValueType<16384, 106>;  //  512 x f32 vector value
-def v1024f32 : ValueType<32768, 107>;  // 1024 x f32 vector value
-def v2048f32 : ValueType<65536, 108>;  // 2048 x f32 vector value
-
-def v1f64    : ValueType<64,    109>;  //    1 x f64 vector value
-def v2f64    : ValueType<128,   110>;  //    2 x f64 vector value
-def v4f64    : ValueType<256,   111>;  //    4 x f64 vector value
-def v8f64    : ValueType<512,   112>;  //    8 x f64 vector value
-def v16f64   : ValueType<1024,  113>;  //   16 x f64 vector value
-def v32f64   : ValueType<2048,  114>;  //   32 x f64 vector value
-def v64f64   : ValueType<4096,  115>;  //   64 x f64 vector value
-def v128f64  : ValueType<8192,  116>;  //  128 x f64 vector value
-def v256f64  : ValueType<16384, 117>;  //  256 x f64 vector value
-
-def nxv1i1  : ValueType<1,  118>;  // n x  1 x i1  vector value
-def nxv2i1  : ValueType<2,  119>;  // n x  2 x i1  vector value
-def nxv4i1  : ValueType<4,  120>;  // n x  4 x i1  vector value
-def nxv8i1  : ValueType<8,  121>;  // n x  8 x i1  vector value
-def nxv16i1 : ValueType<16, 122>;  // n x 16 x i1  vector value
-def nxv32i1 : ValueType<32, 123>;  // n x 32 x i1  vector value
-def nxv64i1 : ValueType<64, 124>;  // n x 64 x i1  vector value
-
-def nxv1i8  : ValueType<8,   125>;  // n x  1 x i8  vector value
-def nxv2i8  : ValueType<16,  126>;  // n x  2 x i8  vector value
-def nxv4i8  : ValueType<32,  127>;  // n x  4 x i8  vector value
-def nxv8i8  : ValueType<64,  128>;  // n x  8 x i8  vector value
-def nxv16i8 : ValueType<128, 129>;  // n x 16 x i8  vector value
-def nxv32i8 : ValueType<256, 130>;  // n x 32 x i8  vector value
-def nxv64i8 : ValueType<512, 131>;  // n x 64 x i8  vector value
-
-def nxv1i16  : ValueType<16,  132>;  // n x  1 x i16 vector value
-def nxv2i16  : ValueType<32,  133>;  // n x  2 x i16 vector value
-def nxv4i16  : ValueType<64,  134>;  // n x  4 x i16 vector value
-def nxv8i16  : ValueType<128, 135>;  // n x  8 x i16 vector value
-def nxv16i16 : ValueType<256, 136>;  // n x 16 x i16 vector value
-def nxv32i16 : ValueType<512, 137>;  // n x 32 x i16 vector value
-
-def nxv1i32  : ValueType<32,   138>;  // n x  1 x i32 vector value
-def nxv2i32  : ValueType<64,   139>;  // n x  2 x i32 vector value
-def nxv4i32  : ValueType<128,  140>;  // n x  4 x i32 vector value
-def nxv8i32  : ValueType<256,  141>;  // n x  8 x i32 vector value
-def nxv16i32 : ValueType<512,  142>;  // n x 16 x i32 vector value
-def nxv32i32 : ValueType<1024, 143>;  // n x 32 x i32 vector value
-
-def nxv1i64  : ValueType<64,   144>;  // n x  1 x i64 vector value
-def nxv2i64  : ValueType<128,  145>;  // n x  2 x i64 vector value
-def nxv4i64  : ValueType<256,  146>;  // n x  4 x i64 vector value
-def nxv8i64  : ValueType<512,  147>;  // n x  8 x i64 vector value
-def nxv16i64 : ValueType<1024, 148>;  // n x 16 x i64 vector value
-def nxv32i64 : ValueType<2048, 149>;  // n x 32 x i64 vector value
-
-def nxv1f16  : ValueType<16,  150>;  // n x  1 x  f16 vector value
-def nxv2f16  : ValueType<32,  151>;  // n x  2 x  f16 vector value
-def nxv4f16  : ValueType<64,  152>;  // n x  4 x  f16 vector value
-def nxv8f16  : ValueType<128, 153>;  // n x  8 x  f16 vector value
-def nxv16f16 : ValueType<256, 154>;  // n x 16 x  f16 vector value
-def nxv32f16 : ValueType<512, 155>;  // n x 32 x  f16 vector value
-
-def nxv1bf16 : ValueType<16,  156>;  // n x  1 x bf16 vector value
-def nxv2bf16 : ValueType<32,  157>;  // n x  2 x bf16 vector value
-def nxv4bf16 : ValueType<64,  158>;  // n x  4 x bf16 vector value
-def nxv8bf16 : ValueType<128, 159>;  // n x  8 x bf16 vector value
-
-def nxv1f32  : ValueType<32,  160>;  // n x  1 x  f32 vector value
-def nxv2f32  : ValueType<64,  161>;  // n x  2 x  f32 vector value
-def nxv4f32  : ValueType<128, 162>;  // n x  4 x  f32 vector value
-def nxv8f32  : ValueType<256, 163>;  // n x  8 x  f32 vector value
-def nxv16f32 : ValueType<512, 164>;  // n x 16 x  f32 vector value
-
-def nxv1f64  : ValueType<64,  165>;  // n x  1 x  f64 vector value
-def nxv2f64  : ValueType<128, 166>;  // n x  2 x  f64 vector value
-def nxv4f64  : ValueType<256, 167>;  // n x  4 x  f64 vector value
-def nxv8f64  : ValueType<512, 168>;  // n x  8 x  f64 vector value
-
-def x86mmx    : ValueType<64,   169>;  // X86 MMX value
-def FlagVT    : ValueType<0,    170>;  // Pre-RA sched glue
-def isVoid    : ValueType<0,    171>;  // Produces no value
-def untyped   : ValueType<8,    172>;  // Produces an untyped value
-def funcref   : ValueType<0,    173>;  // WebAssembly's funcref type
-def externref : ValueType<0,    174>;  // WebAssembly's externref type
-def x86amx    : ValueType<8192, 175>;  // X86 AMX value
+def v3i64   : ValueType<192,   66>;  //   3 x i64 vector value
+def v4i64   : ValueType<256,   67>;  //   4 x i64 vector value
+def v8i64   : ValueType<512,   68>;  //   8 x i64 vector value
+def v16i64  : ValueType<1024,  69>;  //  16 x i64 vector value
+def v32i64  : ValueType<2048,  70>;  //  32 x i64 vector value
+def v64i64  : ValueType<4096,  71>;  //  64 x i64 vector value
+def v128i64 : ValueType<8192,  72>;  // 128 x i64 vector value
+def v256i64 : ValueType<16384, 73>;  // 256 x i64 vector value
+
+def v1i128 : ValueType<128, 74>;  //  1 x i128 vector value
+
+def v1f16    : ValueType<16,     75>;  //    1 x f16 vector value
+def v2f16    : ValueType<32,     76>;  //    2 x f16 vector value
+def v3f16    : ValueType<48,     77>;  //    3 x f16 vector value
+def v4f16    : ValueType<64,     78>;  //    4 x f16 vector value
+def v8f16    : ValueType<128,    79>;  //    8 x f16 vector value
+def v16f16   : ValueType<256,    80>;  //   16 x f16 vector value
+def v32f16   : ValueType<512,    81>;  //   32 x f16 vector value
+def v64f16   : ValueType<1024,   82>;  //   64 x f16 vector value
+def v128f16  : ValueType<2048,   83>;  //  128 x f16 vector value
+def v256f16  : ValueType<4096,   84>;  //  256 x f16 vector value
+def v512f16  : ValueType<8192,   85>;  //  512 x f16 vector value
+
+def v2bf16   : ValueType<32,     86>;  //    2 x bf16 vector value
+def v3bf16   : ValueType<48,     87>;  //    3 x bf16 vector value
+def v4bf16   : ValueType<64,     88>;  //    4 x bf16 vector value
+def v8bf16   : ValueType<128,    89>;  //    8 x bf16 vector value
+def v16bf16  : ValueType<256,    90>;  //   16 x bf16 vector value
+def v32bf16  : ValueType<512,    91>;  //   32 x bf16 vector value
+def v64bf16  : ValueType<1024,   92>;  //   64 x bf16 vector value
+def v128bf16 : ValueType<2048,   93>;  //  128 x bf16 vector value
+
+def v1f32    : ValueType<32,     94>;  //    1 x f32 vector value
+def v2f32    : ValueType<64,     95>;  //    2 x f32 vector value
+def v3f32    : ValueType<96,     96>;  //    3 x f32 vector value
+def v4f32    : ValueType<128,    97>;  //    4 x f32 vector value
+def v5f32    : ValueType<160,    98>;  //    5 x f32 vector value
+def v6f32    : ValueType<192,    99>;  //    6 x f32 vector value
+def v7f32    : ValueType<224,   100>;  //    7 x f32 vector value
+def v8f32    : ValueType<256,   101>;  //    8 x f32 vector value
+def v16f32   : ValueType<512,   102>;  //   16 x f32 vector value
+def v32f32   : ValueType<1024,  103>;  //   32 x f32 vector value
+def v64f32   : ValueType<2048,  104>;  //   64 x f32 vector value
+def v128f32  : ValueType<4096,  105>;  //  128 x f32 vector value
+def v256f32  : ValueType<8192,  106>;  //  256 x f32 vector value
+def v512f32  : ValueType<16384, 107>;  //  512 x f32 vector value
+def v1024f32 : ValueType<32768, 108>;  // 1024 x f32 vector value
+def v2048f32 : ValueType<65536, 109>;  // 2048 x f32 vector value
+
+def v1f64    : ValueType<64,    110>;  //    1 x f64 vector value
+def v2f64    : ValueType<128,   111>;  //    2 x f64 vector value
+def v3f64    : ValueType<192,   112>;  //    3 x f64 vector value
+def v4f64    : ValueType<256,   113>;  //    4 x f64 vector value
+def v8f64    : ValueType<512,   114>;  //    8 x f64 vector value
+def v16f64   : ValueType<1024,  115>;  //   16 x f64 vector value
+def v32f64   : ValueType<2048,  116>;  //   32 x f64 vector value
+def v64f64   : ValueType<4096,  117>;  //   64 x f64 vector value
+def v128f64  : ValueType<8192,  118>;  //  128 x f64 vector value
+def v256f64  : ValueType<16384, 119>;  //  256 x f64 vector value
+
+def nxv1i1  : ValueType<1,  120>;  // n x  1 x i1  vector value
+def nxv2i1  : ValueType<2,  121>;  // n x  2 x i1  vector value
+def nxv4i1  : ValueType<4,  122>;  // n x  4 x i1  vector value
+def nxv8i1  : ValueType<8,  123>;  // n x  8 x i1  vector value
+def nxv16i1 : ValueType<16, 124>;  // n x 16 x i1  vector value
+def nxv32i1 : ValueType<32, 125>;  // n x 32 x i1  vector value
+def nxv64i1 : ValueType<64, 126>;  // n x 64 x i1  vector value
+
+def nxv1i8  : ValueType<8,   127>;  // n x  1 x i8  vector value
+def nxv2i8  : ValueType<16,  128>;  // n x  2 x i8  vector value
+def nxv4i8  : ValueType<32,  129>;  // n x  4 x i8  vector value
+def nxv8i8  : ValueType<64,  130>;  // n x  8 x i8  vector value
+def nxv16i8 : ValueType<128, 131>;  // n x 16 x i8  vector value
+def nxv32i8 : ValueType<256, 132>;  // n x 32 x i8  vector value
+def nxv64i8 : ValueType<512, 133>;  // n x 64 x i8  vector value
+
+def nxv1i16  : ValueType<16,  134>;  // n x  1 x i16 vector value
+def nxv2i16  : ValueType<32,  135>;  // n x  2 x i16 vector value
+def nxv4i16  : ValueType<64,  136>;  // n x  4 x i16 vector value
+def nxv8i16  : ValueType<128, 137>;  // n x  8 x i16 vector value
+def nxv16i16 : ValueType<256, 138>;  // n x 16 x i16 vector value
+def nxv32i16 : ValueType<512, 139>;  // n x 32 x i16 vector value
+
+def nxv1i32  : ValueType<32,   140>;  // n x  1 x i32 vector value
+def nxv2i32  : ValueType<64,   141>;  // n x  2 x i32 vector value
+def nxv4i32  : ValueType<128,  142>;  // n x  4 x i32 vector value
+def nxv8i32  : ValueType<256,  143>;  // n x  8 x i32 vector value
+def nxv16i32 : ValueType<512,  144>;  // n x 16 x i32 vector value
+def nxv32i32 : ValueType<1024, 145>;  // n x 32 x i32 vector value
+
+def nxv1i64  : ValueType<64,   146>;  // n x  1 x i64 vector value
+def nxv2i64  : ValueType<128,  147>;  // n x  2 x i64 vector value
+def nxv4i64  : ValueType<256,  148>;  // n x  4 x i64 vector value
+def nxv8i64  : ValueType<512,  149>;  // n x  8 x i64 vector value
+def nxv16i64 : ValueType<1024, 150>;  // n x 16 x i64 vector value
+def nxv32i64 : ValueType<2048, 151>;  // n x 32 x i64 vector value
+
+def nxv1f16  : ValueType<16,  152>;  // n x  1 x  f16 vector value
+def nxv2f16  : ValueType<32,  153>;  // n x  2 x  f16 vector value
+def nxv4f16  : ValueType<64,  154>;  // n x  4 x  f16 vector value
+def nxv8f16  : ValueType<128, 155>;  // n x  8 x  f16 vector value
+def nxv16f16 : ValueType<256, 156>;  // n x 16 x  f16 vector value
+def nxv32f16 : ValueType<512, 157>;  // n x 32 x  f16 vector value
+
+def nxv1bf16 : ValueType<16,  158>;  // n x  1 x bf16 vector value
+def nxv2bf16 : ValueType<32,  159>;  // n x  2 x bf16 vector value
+def nxv4bf16 : ValueType<64,  160>;  // n x  4 x bf16 vector value
+def nxv8bf16 : ValueType<128, 161>;  // n x  8 x bf16 vector value
+
+def nxv1f32  : ValueType<32,  162>;  // n x  1 x  f32 vector value
+def nxv2f32  : ValueType<64,  163>;  // n x  2 x  f32 vector value
+def nxv4f32  : ValueType<128, 164>;  // n x  4 x  f32 vector value
+def nxv8f32  : ValueType<256, 165>;  // n x  8 x  f32 vector value
+def nxv16f32 : ValueType<512, 166>;  // n x 16 x  f32 vector value
+
+def nxv1f64  : ValueType<64,  167>;  // n x  1 x  f64 vector value
+def nxv2f64  : ValueType<128, 168>;  // n x  2 x  f64 vector value
+def nxv4f64  : ValueType<256, 169>;  // n x  4 x  f64 vector value
+def nxv8f64  : ValueType<512, 170>;  // n x  8 x  f64 vector value
+
+def x86mmx    : ValueType<64,   171>;  // X86 MMX value
+def FlagVT    : ValueType<0,    172>;  // Pre-RA sched glue
+def isVoid    : ValueType<0,    173>;  // Produces no value
+def untyped   : ValueType<8,    174>;  // Produces an untyped value
+def funcref   : ValueType<0,    175>;  // WebAssembly's funcref type
+def externref : ValueType<0,    176>;  // WebAssembly's externref type
+def x86amx    : ValueType<8192, 177>;  // X86 AMX value
 
 
 def token      : ValueType<0, 248>;  // TokenTy
diff --git a/llvm/include/llvm/Support/MachineValueType.h b/llvm/include/llvm/Support/MachineValueType.h
--- a/llvm/include/llvm/Support/MachineValueType.h
+++ b/llvm/include/llvm/Support/MachineValueType.h
@@ -115,66 +115,68 @@
 
       v1i64          =  64,   //   1 x i64
       v2i64          =  65,   //   2 x i64
-      v4i64          =  66,   //   4 x i64
-      v8i64          =  67,   //   8 x i64
-      v16i64         =  68,   //  16 x i64
-      v32i64         =  69,   //  32 x i64
-      v64i64         =  70,   //  64 x i64
-      v128i64        =  71,   // 128 x i64
-      v256i64        =  72,   // 256 x i64
+      v3i64          =  66,   //   3 x i64
+      v4i64          =  67,   //   4 x i64
+      v8i64          =  68,   //   8 x i64
+      v16i64         =  69,   //  16 x i64
+      v32i64         =  70,   //  32 x i64
+      v64i64         =  71,   //  64 x i64
+      v128i64        =  72,   // 128 x i64
+      v256i64        =  73,   // 256 x i64
 
-      v1i128         =  73,   //  1 x i128
+      v1i128         =  74,   //  1 x i128
 
       FIRST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE = v1i1,
       LAST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE = v1i128,
 
-      v1f16          =  74,   //    1 x f16
-      v2f16          =  75,   //    2 x f16
-      v3f16          =  76,   //    3 x f16
-      v4f16          =  77,   //    4 x f16
-      v8f16          =  78,   //    8 x f16
-      v16f16         =  79,   //   16 x f16
-      v32f16         =  80,   //   32 x f16
-      v64f16         =  81,   //   64 x f16
-      v128f16        =  82,   //  128 x f16
-      v256f16        =  83,   //  256 x f16
-      v512f16        =  84,   //  256 x f16
-
-      v2bf16         =  85,   //    2 x bf16
-      v3bf16         =  86,   //    3 x bf16
-      v4bf16         =  87,   //    4 x bf16
-      v8bf16         =  88,   //    8 x bf16
-      v16bf16        =  89,   //   16 x bf16
-      v32bf16        =  90,   //   32 x bf16
-      v64bf16        =  91,   //   64 x bf16
-      v128bf16       =  92,   //  128 x bf16
-
-      v1f32          =  93,   //    1 x f32
-      v2f32          =  94,   //    2 x f32
-      v3f32          =  95,   //    3 x f32
-      v4f32          =  96,   //    4 x f32
-      v5f32          =  97,   //    5 x f32
-      v6f32          =  98,   //    6 x f32
-      v7f32          =  99,   //    7 x f32
-      v8f32          = 100,   //    8 x f32
-      v16f32         = 101,   //   16 x f32
-      v32f32         = 102,   //   32 x f32
-      v64f32         = 103,   //   64 x f32
-      v128f32        = 104,   //  128 x f32
-      v256f32        = 105,   //  256 x f32
-      v512f32        = 106,   //  512 x f32
-      v1024f32       = 107,   // 1024 x f32
-      v2048f32       = 108,   // 2048 x f32
-
-      v1f64          = 109,   //    1 x f64
-      v2f64          = 110,   //    2 x f64
-      v4f64          = 111,   //    4 x f64
-      v8f64          = 112,   //    8 x f64
-      v16f64         = 113,   //   16 x f64
-      v32f64         = 114,   //   32 x f64
-      v64f64         = 115,   //   64 x f64
-      v128f64        = 116,   //  128 x f64
-      v256f64        = 117,   //  256 x f64
+      v1f16          =  75,   //    1 x f16
+      v2f16          =  76,   //    2 x f16
+      v3f16          =  77,   //    3 x f16
+      v4f16          =  78,   //    4 x f16
+      v8f16          =  79,   //    8 x f16
+      v16f16         =  80,   //   16 x f16
+      v32f16         =  81,   //   32 x f16
+      v64f16         =  82,   //   64 x f16
+      v128f16        =  83,   //  128 x f16
+      v256f16        =  84,   //  256 x f16
+      v512f16        =  85,   //  256 x f16
+
+      v2bf16         =  86,   //    2 x bf16
+      v3bf16         =  87,   //    3 x bf16
+      v4bf16         =  88,   //    4 x bf16
+      v8bf16         =  89,   //    8 x bf16
+      v16bf16        =  90,   //   16 x bf16
+      v32bf16        =  91,   //   32 x bf16
+      v64bf16        =  92,   //   64 x bf16
+      v128bf16       =  93,   //  128 x bf16
+
+      v1f32          =  94,   //    1 x f32
+      v2f32          =  95,   //    2 x f32
+      v3f32          =  96,   //    3 x f32
+      v4f32          =  97,   //    4 x f32
+      v5f32          =  98,   //    5 x f32
+      v6f32          =  99,   //    6 x f32
+      v7f32          = 100,   //    7 x f32
+      v8f32          = 101,   //    8 x f32
+      v16f32         = 102,   //   16 x f32
+      v32f32         = 103,   //   32 x f32
+      v64f32         = 104,   //   64 x f32
+      v128f32        = 105,   //  128 x f32
+      v256f32        = 106,   //  256 x f32
+      v512f32        = 107,   //  512 x f32
+      v1024f32       = 108,   // 1024 x f32
+      v2048f32       = 109,   // 2048 x f32
+
+      v1f64          = 110,   //    1 x f64
+      v2f64          = 111,   //    2 x f64
+      v3f64          = 112,   //    3 x f64
+      v4f64          = 113,   //    4 x f64
+      v8f64          = 114,   //    8 x f64
+      v16f64         = 115,   //   16 x f64
+      v32f64         = 116,   //   32 x f64
+      v64f64         = 117,   //   64 x f64
+      v128f64        = 118,   //  128 x f64
+      v256f64        = 119,   //  256 x f64
 
       FIRST_FP_FIXEDLEN_VECTOR_VALUETYPE = v1f16,
       LAST_FP_FIXEDLEN_VECTOR_VALUETYPE = v256f64,
@@ -182,68 +184,68 @@
       FIRST_FIXEDLEN_VECTOR_VALUETYPE = v1i1,
       LAST_FIXEDLEN_VECTOR_VALUETYPE = v256f64,
 
-      nxv1i1         = 118,   // n x  1 x i1
-      nxv2i1         = 119,   // n x  2 x i1
-      nxv4i1         = 120,   // n x  4 x i1
-      nxv8i1         = 121,   // n x  8 x i1
-      nxv16i1        = 122,   // n x 16 x i1
-      nxv32i1        = 123,   // n x 32 x i1
-      nxv64i1        = 124,   // n x 64 x i1
-
-      nxv1i8         = 125,   // n x  1 x i8
-      nxv2i8         = 126,   // n x  2 x i8
-      nxv4i8         = 127,   // n x  4 x i8
-      nxv8i8         = 128,   // n x  8 x i8
-      nxv16i8        = 129,   // n x 16 x i8
-      nxv32i8        = 130,   // n x 32 x i8
-      nxv64i8        = 131,   // n x 64 x i8
-
-      nxv1i16        = 132,  // n x  1 x i16
-      nxv2i16        = 133,  // n x  2 x i16
-      nxv4i16        = 134,  // n x  4 x i16
-      nxv8i16        = 135,  // n x  8 x i16
-      nxv16i16       = 136,  // n x 16 x i16
-      nxv32i16       = 137,  // n x 32 x i16
-
-      nxv1i32        = 138,  // n x  1 x i32
-      nxv2i32        = 139,  // n x  2 x i32
-      nxv4i32        = 140,  // n x  4 x i32
-      nxv8i32        = 141,  // n x  8 x i32
-      nxv16i32       = 142,  // n x 16 x i32
-      nxv32i32       = 143,  // n x 32 x i32
-
-      nxv1i64        = 144,  // n x  1 x i64
-      nxv2i64        = 145,  // n x  2 x i64
-      nxv4i64        = 146,  // n x  4 x i64
-      nxv8i64        = 147,  // n x  8 x i64
-      nxv16i64       = 148,  // n x 16 x i64
-      nxv32i64       = 149,  // n x 32 x i64
+      nxv1i1         = 120,   // n x  1 x i1
+      nxv2i1         = 121,   // n x  2 x i1
+      nxv4i1         = 122,   // n x  4 x i1
+      nxv8i1         = 123,   // n x  8 x i1
+      nxv16i1        = 124,   // n x 16 x i1
+      nxv32i1        = 125,   // n x 32 x i1
+      nxv64i1        = 126,   // n x 64 x i1
+
+      nxv1i8         = 127,   // n x  1 x i8
+      nxv2i8         = 128,   // n x  2 x i8
+      nxv4i8         = 129,   // n x  4 x i8
+      nxv8i8         = 130,   // n x  8 x i8
+      nxv16i8        = 131,   // n x 16 x i8
+      nxv32i8        = 132,   // n x 32 x i8
+      nxv64i8        = 133,   // n x 64 x i8
+
+      nxv1i16        = 134,  // n x  1 x i16
+      nxv2i16        = 135,  // n x  2 x i16
+      nxv4i16        = 136,  // n x  4 x i16
+      nxv8i16        = 137,  // n x  8 x i16
+      nxv16i16       = 138,  // n x 16 x i16
+      nxv32i16       = 139,  // n x 32 x i16
+
+      nxv1i32        = 140,  // n x  1 x i32
+      nxv2i32        = 141,  // n x  2 x i32
+      nxv4i32        = 142,  // n x  4 x i32
+      nxv8i32        = 143,  // n x  8 x i32
+      nxv16i32       = 144,  // n x 16 x i32
+      nxv32i32       = 145,  // n x 32 x i32
+
+      nxv1i64        = 146,  // n x  1 x i64
+      nxv2i64        = 147,  // n x  2 x i64
+      nxv4i64        = 148,  // n x  4 x i64
+      nxv8i64        = 149,  // n x  8 x i64
+      nxv16i64       = 150,  // n x 16 x i64
+      nxv32i64       = 151,  // n x 32 x i64
 
       FIRST_INTEGER_SCALABLE_VECTOR_VALUETYPE = nxv1i1,
       LAST_INTEGER_SCALABLE_VECTOR_VALUETYPE = nxv32i64,
 
-      nxv1f16        = 150,  // n x  1 x f16
-      nxv2f16        = 151,  // n x  2 x f16
-      nxv4f16        = 152,  // n x  4 x f16
-      nxv8f16        = 153,  // n x  8 x f16
-      nxv16f16       = 154,  // n x 16 x f16
-      nxv32f16       = 155,  // n x 32 x f16
-
-      nxv1bf16       = 156,  // n x  1 x bf16
-      nxv2bf16       = 157,  // n x  2 x bf16
-      nxv4bf16       = 158,  // n x  4 x bf16
-      nxv8bf16       = 159,  // n x  8 x bf16
-
-      nxv1f32        = 160,  // n x  1 x f32
-      nxv2f32        = 161,  // n x  2 x f32
-      nxv4f32        = 162,  // n x  4 x f32
-      nxv8f32        = 163,  // n x  8 x f32
-      nxv16f32       = 164,  // n x 16 x f32
-
-      nxv1f64        = 165,  // n x  1 x f64
-      nxv2f64        = 166,  // n x  2 x f64
-      nxv4f64        = 167,  // n x  4 x f64
-      nxv8f64        = 168,  // n x  8 x f64
+      nxv1f16        = 152,  // n x  1 x f16
+      nxv2f16        = 153,  // n x  2 x f16
+      nxv4f16        = 154,  // n x  4 x f16
+      nxv8f16        = 155,  // n x  8 x f16
+      nxv16f16       = 156,  // n x 16 x f16
+      nxv32f16       = 157,  // n x 32 x f16
+
+      nxv1bf16       = 158,  // n x  1 x bf16
+      nxv2bf16       = 159,  // n x  2 x bf16
+      nxv4bf16       = 160,  // n x  4 x bf16
+      nxv8bf16       = 161,  // n x  8 x bf16
+
+      nxv1f32        = 162,  // n x  1 x f32
+      nxv2f32        = 163,  // n x  2 x f32
+      nxv4f32        = 164,  // n x  4 x f32
+      nxv8f32        = 165,  // n x  8 x f32
+      nxv16f32       = 166,  // n x 16 x f32
+
+      nxv1f64        = 167,  // n x  1 x f64
+      nxv2f64        = 168,  // n x  2 x f64
+      nxv4f64        = 169,  // n x  4 x f64
+      nxv8f64        = 170,  // n x  8 x f64
 
       FIRST_FP_SCALABLE_VECTOR_VALUETYPE = nxv1f16,
       LAST_FP_SCALABLE_VECTOR_VALUETYPE = nxv8f64,
@@ -254,19 +256,19 @@
       FIRST_VECTOR_VALUETYPE = v1i1,
       LAST_VECTOR_VALUETYPE  = nxv8f64,
 
-      x86mmx         = 169,    // This is an X86 MMX value
+      x86mmx         = 171,    // This is an X86 MMX value
 
-      Glue           = 170,    // This glues nodes together during pre-RA sched
+      Glue           = 172,    // This glues nodes together during pre-RA sched
 
-      isVoid         = 171,    // This has no value
+      isVoid         = 173,    // This has no value
 
-      Untyped        = 172,    // This value takes a register, but has
+      Untyped        = 174,    // This value takes a register, but has
                                // unspecified type.  The register class
                                // will be determined by the opcode.
 
-      funcref        = 173,    // WebAssembly's funcref type
-      externref      = 174,    // WebAssembly's externref type
-      x86amx         = 175,    // This is an X86 AMX value
+      funcref        = 175,    // WebAssembly's funcref type
+      externref      = 176,    // WebAssembly's externref type
+      x86amx         = 177,    // This is an X86 AMX value
 
       FIRST_VALUETYPE =  1,    // This is always the beginning of the list.
       LAST_VALUETYPE = x86amx, // This always remains at the end of the list.
@@ -593,6 +595,7 @@
       case nxv32i32: return i32;
       case v1i64:
       case v2i64:
+      case v3i64:
       case v4i64:
       case v8i64:
       case v16i64:
@@ -659,6 +662,7 @@
       case nxv16f32: return f32;
       case v1f64:
       case v2f64:
+      case v3f64:
       case v4f64:
       case v8f64:
       case v16f64:
@@ -793,9 +797,11 @@
       case nxv4f64: return 4;
       case v3i16:
       case v3i32:
+      case v3i64:
       case v3f16:
       case v3bf16:
-      case v3f32: return 3;
+      case v3f32:
+      case v3f64: return 3;
       case v2i1:
       case v2i8:
       case v2i16:
@@ -958,6 +964,8 @@
       case nxv2f64: return TypeSize::Scalable(128);
       case v5i32:
       case v5f32: return TypeSize::Fixed(160);
+      case v3i64:
+      case v3f64:
       case v6i32:
       case v6f32: return TypeSize::Fixed(192);
       case v7i32:
@@ -1227,6 +1235,7 @@
       case MVT::i64:
         if (NumElements == 1)  return MVT::v1i64;
         if (NumElements == 2)  return MVT::v2i64;
+        if (NumElements == 3)  return MVT::v3i64;
         if (NumElements == 4)  return MVT::v4i64;
         if (NumElements == 8)  return MVT::v8i64;
         if (NumElements == 16) return MVT::v16i64;
@@ -1282,6 +1291,7 @@
       case MVT::f64:
         if (NumElements == 1)  return MVT::v1f64;
         if (NumElements == 2)  return MVT::v2f64;
+        if (NumElements == 3)  return MVT::v3f64;
         if (NumElements == 4)  return MVT::v4f64;
         if (NumElements == 8)  return MVT::v8f64;
         if (NumElements == 16) return MVT::v16f64;
diff --git a/llvm/lib/CodeGen/ValueTypes.cpp b/llvm/lib/CodeGen/ValueTypes.cpp
--- a/llvm/lib/CodeGen/ValueTypes.cpp
+++ b/llvm/lib/CodeGen/ValueTypes.cpp
@@ -300,6 +300,8 @@
     return FixedVectorType::get(Type::getInt64Ty(Context), 1);
   case MVT::v2i64:
     return FixedVectorType::get(Type::getInt64Ty(Context), 2);
+  case MVT::v3i64:
+    return FixedVectorType::get(Type::getInt64Ty(Context), 3);
   case MVT::v4i64:
     return FixedVectorType::get(Type::getInt64Ty(Context), 4);
   case MVT::v8i64:
@@ -390,6 +392,8 @@
     return FixedVectorType::get(Type::getDoubleTy(Context), 1);
   case MVT::v2f64:
     return FixedVectorType::get(Type::getDoubleTy(Context), 2);
+  case MVT::v3f64:
+    return FixedVectorType::get(Type::getDoubleTy(Context), 3);
   case MVT::v4f64:
     return FixedVectorType::get(Type::getDoubleTy(Context), 4);
   case MVT::v8f64:
diff --git a/llvm/utils/TableGen/CodeGenTarget.cpp b/llvm/utils/TableGen/CodeGenTarget.cpp
--- a/llvm/utils/TableGen/CodeGenTarget.cpp
+++ b/llvm/utils/TableGen/CodeGenTarget.cpp
@@ -130,6 +130,7 @@
   case MVT::v2048i32: return "MVT::v2048i32";
   case MVT::v1i64:    return "MVT::v1i64";
   case MVT::v2i64:    return "MVT::v2i64";
+  case MVT::v3i64:    return "MVT::v3i64";
   case MVT::v4i64:    return "MVT::v4i64";
   case MVT::v8i64:    return "MVT::v8i64";
   case MVT::v16i64:   return "MVT::v16i64";
@@ -175,6 +176,7 @@
   case MVT::v2048f32: return "MVT::v2048f32";
   case MVT::v1f64:    return "MVT::v1f64";
   case MVT::v2f64:    return "MVT::v2f64";
+  case MVT::v3f64:    return "MVT::v3f64";
   case MVT::v4f64:    return "MVT::v4f64";
   case MVT::v8f64:    return "MVT::v8f64";
   case MVT::v16f64:   return "MVT::v16f64";