[VE] Add new MVT types for NEC SX Aurora VE vector

[kaz7]

Summary

This patch adds entries for:

v64i64
v128i64
v256i64
v64f64
v128f64
v256f64

[kaz7]

Add people reviewed MVT recently. Thanks.

[kaz7]

Rebased to the latest.

[simoll]

LGTM

[kaz7]

Rebase to the latest to see whether the unknown error about an openmp test
is solved or not.

llvm/include/llvm/CodeGen/ValueTypes.td

 def v2048i32 : ValueType<65536,57>;  // 2048 x i32 vector value
 
 def v1i64  : ValueType<64 , 58>;   //  1 x i64 vector value
 def v2i64  : ValueType<128, 59>;   //  2 x i64 vector value
 def v4i64  : ValueType<256, 60>;   //  4 x i64 vector value
 def v8i64  : ValueType<512, 61>;   //  8 x i64 vector value
 def v16i64 : ValueType<1024,62>;   // 16 x i64 vector value
 def v32i64 : ValueType<2048,63>;   // 32 x i64 vector value
-
-def v1i128 : ValueType<128, 64>;   //  1 x i128 vector value
-
-def v2f16    : ValueType<32 , 65>;    //    2 x f16 vector value
-def v3f16    : ValueType<48 , 66>;    //    3 x f16 vector value
-def v4f16    : ValueType<64 , 67>;    //    4 x f16 vector value
-def v8f16    : ValueType<128, 68>;    //    8 x f16 vector value
-def v16f16   : ValueType<256, 69>;    //   16 x f16 vector value
-def v32f16   : ValueType<512, 70>;    //   32 x f16 vector value
-def v64f16   : ValueType<1024, 71>;   //   64 x f16 vector value
-def v128f16  : ValueType<2048, 72>;   //  128 x f16 vector value
-def v2bf16   : ValueType<32 , 73>;    //    2 x bf16 vector value
-def v3bf16   : ValueType<48 , 74>;    //    3 x bf16 vector value
-def v4bf16   : ValueType<64 , 75>;    //    4 x bf16 vector value
-def v8bf16   : ValueType<128, 76>;    //    8 x bf16 vector value
-def v16bf16  : ValueType<256, 77>;    //   16 x bf16 vector value
-def v32bf16  : ValueType<512, 78>;    //   32 x bf16 vector value
-def v64bf16  : ValueType<1024, 79>;   //   64 x bf16 vector value
-def v128bf16 : ValueType<2048, 80>;   //  128 x bf16 vector value
-def v1f32    : ValueType<32 , 81>;    //    1 x f32 vector value
-def v2f32    : ValueType<64 , 82>;    //    2 x f32 vector value
-def v3f32    : ValueType<96 , 83>;    //    3 x f32 vector value
-def v4f32    : ValueType<128, 84>;    //    4 x f32 vector value
-def v5f32    : ValueType<160, 85>;    //    5 x f32 vector value
-def v8f32    : ValueType<256, 86>;    //    8 x f32 vector value
-def v16f32   : ValueType<512,  87>;   //   16 x f32 vector value
-def v32f32   : ValueType<1024, 88>;   //   32 x f32 vector value
-def v64f32   : ValueType<2048, 89>;   //   64 x f32 vector value
-def v128f32  : ValueType<4096, 90>;   //  128 x f32 vector value
-def v256f32  : ValueType<8182, 91>;   //  256 x f32 vector value
-def v512f32  : ValueType<16384, 92>;  //  512 x f32 vector value
-def v1024f32 : ValueType<32768, 93>;  // 1024 x f32 vector value
-def v2048f32 : ValueType<65536, 94>;  // 2048 x f32 vector value
-def v1f64    : ValueType<64, 95>;     //    1 x f64 vector value
-def v2f64    : ValueType<128, 96>;    //    2 x f64 vector value
-def v4f64    : ValueType<256, 97>;    //    4 x f64 vector value
-def v8f64    : ValueType<512, 98>;    //    8 x f64 vector value
-def v16f64   : ValueType<1024, 99>;   //   16 x f64 vector value
-def v32f64   : ValueType<2048, 100>;  //   32 x f64 vector value
-
-def nxv1i1  : ValueType<1,  101>;  // n x  1 x i1  vector value
-def nxv2i1  : ValueType<2,  102>;  // n x  2 x i1  vector value
-def nxv4i1  : ValueType<4,  103>;  // n x  4 x i1  vector value
-def nxv8i1  : ValueType<8,  104>;  // n x  8 x i1  vector value
-def nxv16i1 : ValueType<16, 105>;  // n x 16 x i1  vector value
-def nxv32i1 : ValueType<32, 106>;  // n x 32 x i1  vector value
-def nxv64i1  : ValueType<64,107>;  // n x  64 x i1  vector value
-
-def nxv1i8  : ValueType<8,   108>;  // n x  1 x i8  vector value
-def nxv2i8  : ValueType<16,  109>;  // n x  2 x i8  vector value
-def nxv4i8  : ValueType<32,  110>;  // n x  4 x i8  vector value
-def nxv8i8  : ValueType<64,  111>;  // n x  8 x i8  vector value
-def nxv16i8 : ValueType<128, 112>;  // n x 16 x i8  vector value
-def nxv32i8 : ValueType<256, 113>;  // n x 32 x i8  vector value
-def nxv64i8  : ValueType<512,  114>;  // n x  64 x i8  vector value
-
-def nxv1i16 : ValueType<16,  115>; // n x  1 x i16 vector value
-def nxv2i16 : ValueType<32,  116>; // n x  2 x i16 vector value
-def nxv4i16 : ValueType<64,  117>; // n x  4 x i16 vector value
-def nxv8i16 : ValueType<128, 118>; // n x  8 x i16 vector value
-def nxv16i16: ValueType<256, 119>; // n x 16 x i16 vector value
-def nxv32i16: ValueType<512, 120>; // n x 32 x i16 vector value
-
-def nxv1i32 : ValueType<32,  121>; // n x  1 x i32 vector value
-def nxv2i32 : ValueType<64,  122>; // n x  2 x i32 vector value
-def nxv4i32 : ValueType<128, 123>; // n x  4 x i32 vector value
-def nxv8i32 : ValueType<256, 124>; // n x  8 x i32 vector value
-def nxv16i32: ValueType<512, 125>; // n x 16 x i32 vector value
-def nxv32i32: ValueType<1024,126>; // n x 32 x i32 vector value
-
-def nxv1i64 : ValueType<64,  127>; // n x  1 x i64 vector value
-def nxv2i64 : ValueType<128, 128>; // n x  2 x i64 vector value
-def nxv4i64 : ValueType<256, 129>; // n x  4 x i64 vector value
-def nxv8i64 : ValueType<512, 130>; // n x  8 x i64 vector value
-def nxv16i64: ValueType<1024,131>; // n x 16 x i64 vector value
-def nxv32i64: ValueType<2048,132>; // n x 32 x i64 vector value
-
-def nxv1f16   : ValueType<32, 133>; // n x   1 x f16 vector value
-def nxv2f16  : ValueType<32 , 134>; // n x  2 x f16 vector value
-def nxv4f16  : ValueType<64 , 135>; // n x  4 x f16 vector value
-def nxv8f16  : ValueType<128, 136>; // n x  8 x f16 vector value
-def nxv16f16  : ValueType<256,137>; // n x  16 x f16 vector value
-def nxv32f16  : ValueType<512,138>; // n x  32 x f16 vector value
-def nxv2bf16 : ValueType<32 , 139>; // n x  2 x bf16 vector value
-def nxv4bf16 : ValueType<64 , 140>; // n x  4 x bf16 vector value
-def nxv8bf16 : ValueType<128, 141>; // n x  8 x bf16 vector value
-def nxv1f32  : ValueType<32 , 142>; // n x  1 x f32 vector value
-def nxv2f32  : ValueType<64 , 143>; // n x  2 x f32 vector value
-def nxv4f32  : ValueType<128, 144>; // n x  4 x f32 vector value
-def nxv8f32  : ValueType<256, 145>; // n x  8 x f32 vector value
-def nxv16f32 : ValueType<512, 146>; // n x 16 x f32 vector value
-def nxv1f64  : ValueType<64,  147>; // n x  1 x f64 vector value
-def nxv2f64  : ValueType<128, 148>; // n x  2 x f64 vector value
-def nxv4f64  : ValueType<256, 149>; // n x  4 x f64 vector value
-def nxv8f64  : ValueType<512, 150>; // n x  8 x f64 vector value
-
-def x86mmx : ValueType<64 , 151>;   // X86 MMX value
-def FlagVT : ValueType<0  , 152>;   // Pre-RA sched glue
-def isVoid : ValueType<0  , 153>;   // Produces no value
-def untyped: ValueType<8  , 154>;   // Produces an untyped value
-def exnref : ValueType<0  , 155>;   // WebAssembly's exnref type
+def v64i64 : ValueType<4096,64>;   // 64 x i64 vector value
+def v128i64: ValueType<8192,65>;   // 128 x i64 vector value
+def v256i64: ValueType<16384,66>;  // 256 x i64 vector value
+
+def v1i128 : ValueType<128, 67>;   //  1 x i128 vector value
+
+def v2f16    : ValueType<32 , 68>;    //    2 x f16 vector value
+def v3f16    : ValueType<48 , 69>;    //    3 x f16 vector value
+def v4f16    : ValueType<64 , 70>;    //    4 x f16 vector value
+def v8f16    : ValueType<128, 71>;    //    8 x f16 vector value
+def v16f16   : ValueType<256, 72>;    //   16 x f16 vector value
+def v32f16   : ValueType<512, 73>;    //   32 x f16 vector value
+def v64f16   : ValueType<1024, 74>;   //   64 x f16 vector value
+def v128f16  : ValueType<2048, 75>;   //  128 x f16 vector value
+def v2bf16   : ValueType<32 , 76>;    //    2 x bf16 vector value
+def v3bf16   : ValueType<48 , 77>;    //    3 x bf16 vector value
+def v4bf16   : ValueType<64 , 78>;    //    4 x bf16 vector value
+def v8bf16   : ValueType<128, 79>;    //    8 x bf16 vector value
+def v16bf16  : ValueType<256, 80>;    //   16 x bf16 vector value
+def v32bf16  : ValueType<512, 81>;    //   32 x bf16 vector value
+def v64bf16  : ValueType<1024, 82>;   //   64 x bf16 vector value
+def v128bf16 : ValueType<2048, 83>;   //  128 x bf16 vector value
+def v1f32    : ValueType<32 , 84>;    //    1 x f32 vector value
+def v2f32    : ValueType<64 , 85>;    //    2 x f32 vector value
+def v3f32    : ValueType<96 , 86>;    //    3 x f32 vector value
+def v4f32    : ValueType<128, 87>;    //    4 x f32 vector value
+def v5f32    : ValueType<160, 88>;    //    5 x f32 vector value
+def v8f32    : ValueType<256, 89>;    //    8 x f32 vector value
+def v16f32   : ValueType<512,  90>;   //   16 x f32 vector value
+def v32f32   : ValueType<1024, 91>;   //   32 x f32 vector value
+def v64f32   : ValueType<2048, 92>;   //   64 x f32 vector value
+def v128f32  : ValueType<4096, 93>;   //  128 x f32 vector value
+def v256f32  : ValueType<8182, 94>;   //  256 x f32 vector value
+def v512f32  : ValueType<16384, 95>;  //  512 x f32 vector value
+def v1024f32 : ValueType<32768, 96>;  // 1024 x f32 vector value
+def v2048f32 : ValueType<65536, 97>;  // 2048 x f32 vector value
+def v1f64    : ValueType<64, 98>;     //    1 x f64 vector value
+def v2f64    : ValueType<128, 99>;    //    2 x f64 vector value
+def v4f64    : ValueType<256, 100>;    //    4 x f64 vector value
+def v8f64    : ValueType<512, 101>;    //    8 x f64 vector value
+def v16f64   : ValueType<1024, 102>;   //   16 x f64 vector value
+def v32f64   : ValueType<2048, 103>;  //   32 x f64 vector value
+def v64f64   : ValueType<4096, 104>;  //   64 x f64 vector value
+def v128f64  : ValueType<8192, 105>;  //  128 x f64 vector value
+def v256f64  : ValueType<16384, 106>; //  256 x f64 vector value
+
+def nxv1i1  : ValueType<1,  107>;  // n x  1 x i1  vector value
+def nxv2i1  : ValueType<2,  108>;  // n x  2 x i1  vector value
+def nxv4i1  : ValueType<4,  109>;  // n x  4 x i1  vector value
+def nxv8i1  : ValueType<8,  110>;  // n x  8 x i1  vector value
+def nxv16i1 : ValueType<16, 111>;  // n x 16 x i1  vector value
+def nxv32i1 : ValueType<32, 112>;  // n x 32 x i1  vector value
+def nxv64i1  : ValueType<64,113>;  // n x  64 x i1  vector value
+
+def nxv1i8  : ValueType<8,   114>;  // n x  1 x i8  vector value
+def nxv2i8  : ValueType<16,  115>;  // n x  2 x i8  vector value
+def nxv4i8  : ValueType<32,  116>;  // n x  4 x i8  vector value
+def nxv8i8  : ValueType<64,  117>;  // n x  8 x i8  vector value
+def nxv16i8 : ValueType<128, 118>;  // n x 16 x i8  vector value
+def nxv32i8 : ValueType<256, 119>;  // n x 32 x i8  vector value
+def nxv64i8  : ValueType<512,  120>;  // n x  64 x i8  vector value
+
+def nxv1i16 : ValueType<16,  121>; // n x  1 x i16 vector value
+def nxv2i16 : ValueType<32,  122>; // n x  2 x i16 vector value
+def nxv4i16 : ValueType<64,  123>; // n x  4 x i16 vector value
+def nxv8i16 : ValueType<128, 124>; // n x  8 x i16 vector value
+def nxv16i16: ValueType<256, 125>; // n x 16 x i16 vector value
+def nxv32i16: ValueType<512, 126>; // n x 32 x i16 vector value
+
+def nxv1i32 : ValueType<32,  127>; // n x  1 x i32 vector value
+def nxv2i32 : ValueType<64,  128>; // n x  2 x i32 vector value
+def nxv4i32 : ValueType<128, 129>; // n x  4 x i32 vector value
+def nxv8i32 : ValueType<256, 130>; // n x  8 x i32 vector value
+def nxv16i32: ValueType<512, 131>; // n x 16 x i32 vector value
+def nxv32i32: ValueType<1024,132>; // n x 32 x i32 vector value
+
+def nxv1i64 : ValueType<64,  133>; // n x  1 x i64 vector value
+def nxv2i64 : ValueType<128, 134>; // n x  2 x i64 vector value
+def nxv4i64 : ValueType<256, 135>; // n x  4 x i64 vector value
+def nxv8i64 : ValueType<512, 136>; // n x  8 x i64 vector value
+def nxv16i64: ValueType<1024,137>; // n x 16 x i64 vector value
+def nxv32i64: ValueType<2048,138>; // n x 32 x i64 vector value
+
+def nxv1f16   : ValueType<32, 139>; // n x   1 x f16 vector value
+def nxv2f16  : ValueType<32 , 140>; // n x  2 x f16 vector value
+def nxv4f16  : ValueType<64 , 141>; // n x  4 x f16 vector value
+def nxv8f16  : ValueType<128, 142>; // n x  8 x f16 vector value
+def nxv16f16  : ValueType<256,143>; // n x  16 x f16 vector value
+def nxv32f16  : ValueType<512,144>; // n x  32 x f16 vector value
+def nxv2bf16 : ValueType<32 , 145>; // n x  2 x bf16 vector value
+def nxv4bf16 : ValueType<64 , 146>; // n x  4 x bf16 vector value
+def nxv8bf16 : ValueType<128, 147>; // n x  8 x bf16 vector value
+def nxv1f32  : ValueType<32 , 148>; // n x  1 x f32 vector value
+def nxv2f32  : ValueType<64 , 149>; // n x  2 x f32 vector value
+def nxv4f32  : ValueType<128, 150>; // n x  4 x f32 vector value
+def nxv8f32  : ValueType<256, 151>; // n x  8 x f32 vector value
+def nxv16f32 : ValueType<512, 152>; // n x 16 x f32 vector value
+def nxv1f64  : ValueType<64,  153>; // n x  1 x f64 vector value
+def nxv2f64  : ValueType<128, 154>; // n x  2 x f64 vector value
+def nxv4f64  : ValueType<256, 155>; // n x  4 x f64 vector value
+def nxv8f64  : ValueType<512, 156>; // n x  8 x f64 vector value
+
+def x86mmx : ValueType<64 , 157>;   // X86 MMX value
+def FlagVT : ValueType<0  , 158>;   // Pre-RA sched glue
+def isVoid : ValueType<0  , 159>;   // Produces no value
+def untyped: ValueType<8  , 160>;   // Produces an untyped value
+def exnref : ValueType<0  , 161>;   // WebAssembly's exnref type
 
 def token  : ValueType<0  , 248>;   // TokenTy
 def MetadataVT: ValueType<0, 249>;  // Metadata
 
 // Pseudo valuetype mapped to the current pointer size to any address space.
 // Should only be used in TableGen.
 def iPTRAny   : ValueType<0, 250>;
 

llvm/include/llvm/Support/MachineValueType.h

namespace llvm {
   public:
     enum SimpleValueType : uint8_t {
       // Simple value types that aren't explicitly part of this enumeration
       // are considered extended value types.
       INVALID_SIMPLE_VALUE_TYPE = 0,
 
       // If you change this numbering, you must change the values in
       // ValueTypes.td as well!
       Other          =   1,   // This is a non-standard value
       i1             =   2,   // This is a 1 bit integer value
       i8             =   3,   // This is an 8 bit integer value
       i16            =   4,   // This is a 16 bit integer value
       i32            =   5,   // This is a 32 bit integer value
       i64            =   6,   // This is a 64 bit integer value
       i128           =   7,   // This is a 128 bit integer value
 
       FIRST_INTEGER_VALUETYPE = i1,
       LAST_INTEGER_VALUETYPE  = i128,
 
       bf16           =   8,   // This is a 16 bit brain floating point value
       f16            =   9,   // This is a 16 bit floating point value
       f32            =  10,   // This is a 32 bit floating point value
       f64            =  11,   // This is a 64 bit floating point value
       f80            =  12,   // This is a 80 bit floating point value
       f128           =  13,   // This is a 128 bit floating point value
       ppcf128        =  14,   // This is a PPC 128-bit floating point value
 
       FIRST_FP_VALUETYPE = bf16,
       LAST_FP_VALUETYPE  = ppcf128,
 
       v1i1           =  15,   //    1 x i1
       v2i1           =  16,   //    2 x i1
       v4i1           =  17,   //    4 x i1
       v8i1           =  18,   //    8 x i1
       v16i1          =  19,   //   16 x i1
       v32i1          =  20,   //   32 x i1
       v64i1          =  21,   //   64 x i1
enum SimpleValueType : uint8_t {
       v2048i32       =  57,   // 2048 x i32
 
       v1i64          =  58,   //  1 x i64
       v2i64          =  59,   //  2 x i64
       v4i64          =  60,   //  4 x i64
       v8i64          =  61,   //  8 x i64
       v16i64         =  62,   // 16 x i64
       v32i64         =  63,   // 32 x i64
+      v64i64         =  64,   // 64 x i64
+      v128i64        =  65,   // 128 x i64
+      v256i64        =  66,   // 256 x i64
 
-      v1i128         =  64,   //  1 x i128
+      v1i128         =  67,   //  1 x i128
 
       FIRST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE = v1i1,
       LAST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE = v1i128,
 
-      v2f16          =  65,   //    2 x f16
-      v3f16          =  66,   //    3 x f16
-      v4f16          =  67,   //    4 x f16
-      v8f16          =  68,   //    8 x f16
-      v16f16         =  69,   //   16 x f16
-      v32f16         =  70,   //   32 x f16
-      v64f16         =  71,   //   64 x f16
-      v128f16        =  72,   //  128 x f16
-      v2bf16         =  73,   //    2 x bf16
-      v3bf16         =  74,   //    3 x bf16
-      v4bf16         =  75,   //    4 x bf16
-      v8bf16         =  76,   //    8 x bf16
-      v16bf16        =  77,   //   16 x bf16
-      v32bf16        =  78,   //   32 x bf16
-      v64bf16        =  79,   //   64 x bf16
-      v128bf16       =  80,   //  128 x bf16
-      v1f32          =  81,   //    1 x f32
-      v2f32          =  82,   //    2 x f32
-      v3f32          =  83,   //    3 x f32
-      v4f32          =  84,   //    4 x f32
-      v5f32          =  85,   //    5 x f32
-      v8f32          =  86,   //    8 x f32
-      v16f32         =  87,   //   16 x f32
-      v32f32         =  88,   //   32 x f32
-      v64f32         =  89,   //   64 x f32
-      v128f32        =  90,   //  128 x f32
-      v256f32        =  91,   //  256 x f32
-      v512f32        =  92,   //  512 x f32
-      v1024f32       =  93,   // 1024 x f32
-      v2048f32       =  94,   // 2048 x f32
-      v1f64          =  95,   //    1 x f64
-      v2f64          =  96,   //    2 x f64
-      v4f64          =  97,   //    4 x f64
-      v8f64          =  98,   //    8 x f64
-      v16f64         =  99,   //   16 x f64
-      v32f64         = 100,   //   32 x f64
+      v2f16          =  68,   //    2 x f16
+      v3f16          =  69,   //    3 x f16
+      v4f16          =  70,   //    4 x f16
+      v8f16          =  71,   //    8 x f16
+      v16f16         =  72,   //   16 x f16
+      v32f16         =  73,   //   32 x f16
+      v64f16         =  74,   //   64 x f16
+      v128f16        =  75,   //  128 x f16
+      v2bf16         =  76,   //    2 x bf16
+      v3bf16         =  77,   //    3 x bf16
+      v4bf16         =  78,   //    4 x bf16
+      v8bf16         =  79,   //    8 x bf16
+      v16bf16        =  80,   //   16 x bf16
+      v32bf16        =  81,   //   32 x bf16
+      v64bf16        =  82,   //   64 x bf16
+      v128bf16       =  83,   //  128 x bf16
+      v1f32          =  84,   //    1 x f32
+      v2f32          =  85,   //    2 x f32
+      v3f32          =  86,   //    3 x f32
+      v4f32          =  87,   //    4 x f32
+      v5f32          =  88,   //    5 x f32
+      v8f32          =  89,   //    8 x f32
+      v16f32         =  90,   //   16 x f32
+      v32f32         =  91,   //   32 x f32
+      v64f32         =  92,   //   64 x f32
+      v128f32        =  93,   //  128 x f32
+      v256f32        =  94,   //  256 x f32
+      v512f32        =  95,   //  512 x f32
+      v1024f32       =  96,   // 1024 x f32
+      v2048f32       =  97,   // 2048 x f32
+      v1f64          =  98,   //    1 x f64
+      v2f64          =  99,   //    2 x f64
+      v4f64          = 100,   //    4 x f64
+      v8f64          = 101,   //    8 x f64
+      v16f64         = 102,   //   16 x f64
+      v32f64         = 103,   //   32 x f64
+      v64f64         = 104,   //   64 x f64
+      v128f64        = 105,   //  128 x f64
+      v256f64        = 106,   //  256 x f64
 
       FIRST_FP_FIXEDLEN_VECTOR_VALUETYPE = v2f16,
-      LAST_FP_FIXEDLEN_VECTOR_VALUETYPE = v32f64,
+      LAST_FP_FIXEDLEN_VECTOR_VALUETYPE = v256f64,
 
       FIRST_FIXEDLEN_VECTOR_VALUETYPE = v1i1,
-      LAST_FIXEDLEN_VECTOR_VALUETYPE = v32f64,
+      LAST_FIXEDLEN_VECTOR_VALUETYPE = v256f64,
 
-      nxv1i1         = 101,   // n x  1 x i1
-      nxv2i1         = 102,   // n x  2 x i1
-      nxv4i1         = 103,   // n x  4 x i1
-      nxv8i1         = 104,   // n x  8 x i1
-      nxv16i1        = 105,   // n x 16 x i1
-      nxv32i1        = 106,   // n x 32 x i1
-      nxv64i1        = 107,   // n x  64 x i1
-
-      nxv1i8         = 108,   // n x  1 x i8
-      nxv2i8         = 109,   // n x  2 x i8
-      nxv4i8         = 110,   // n x  4 x i8
-      nxv8i8         = 111,   // n x  8 x i8
-      nxv16i8        = 112,   // n x 16 x i8
-      nxv32i8        = 113,   // n x 32 x i8
-      nxv64i8        = 114,   // n x  64 x i8
-
-      nxv1i16        = 115,  // n x  1 x i16
-      nxv2i16        = 116,  // n x  2 x i16
-      nxv4i16        = 117,  // n x  4 x i16
-      nxv8i16        = 118,  // n x  8 x i16
-      nxv16i16       = 119,  // n x 16 x i16
-      nxv32i16       = 120,  // n x 32 x i16
-
-      nxv1i32        = 121,  // n x  1 x i32
-      nxv2i32        = 122,  // n x  2 x i32
-      nxv4i32        = 123,  // n x  4 x i32
-      nxv8i32        = 124,  // n x  8 x i32
-      nxv16i32       = 125,  // n x 16 x i32
-      nxv32i32       = 126,  // n x 32 x i32
-
-      nxv1i64        = 127,  // n x  1 x i64
-      nxv2i64        = 128,  // n x  2 x i64
-      nxv4i64        = 129,  // n x  4 x i64
-      nxv8i64        = 130,  // n x  8 x i64
-      nxv16i64       = 131,  // n x 16 x i64
-      nxv32i64       = 132,  // n x 32 x i64
+      nxv1i1         = 107,   // n x  1 x i1
+      nxv2i1         = 108,   // n x  2 x i1
+      nxv4i1         = 109,   // n x  4 x i1
+      nxv8i1         = 110,   // n x  8 x i1
+      nxv16i1        = 111,   // n x 16 x i1
+      nxv32i1        = 112,   // n x 32 x i1
+      nxv64i1        = 113,   // n x  64 x i1
+
+      nxv1i8         = 114,   // n x  1 x i8
+      nxv2i8         = 115,   // n x  2 x i8
+      nxv4i8         = 116,   // n x  4 x i8
+      nxv8i8         = 117,   // n x  8 x i8
+      nxv16i8        = 118,   // n x 16 x i8
+      nxv32i8        = 119,   // n x 32 x i8
+      nxv64i8        = 120,   // n x  64 x i8
+
+      nxv1i16        = 121,  // n x  1 x i16
+      nxv2i16        = 122,  // n x  2 x i16
+      nxv4i16        = 123,  // n x  4 x i16
+      nxv8i16        = 124,  // n x  8 x i16
+      nxv16i16       = 125,  // n x 16 x i16
+      nxv32i16       = 126,  // n x 32 x i16
+
+      nxv1i32        = 127,  // n x  1 x i32
+      nxv2i32        = 128,  // n x  2 x i32
+      nxv4i32        = 129,  // n x  4 x i32
+      nxv8i32        = 130,  // n x  8 x i32
+      nxv16i32       = 131,  // n x 16 x i32
+      nxv32i32       = 132,  // n x 32 x i32
+
+      nxv1i64        = 133,  // n x  1 x i64
+      nxv2i64        = 134,  // n x  2 x i64
+      nxv4i64        = 135,  // n x  4 x i64
+      nxv8i64        = 136,  // n x  8 x i64
+      nxv16i64       = 137,  // n x 16 x i64
+      nxv32i64       = 138,  // n x 32 x i64
 
       FIRST_INTEGER_SCALABLE_VECTOR_VALUETYPE = nxv1i1,
       LAST_INTEGER_SCALABLE_VECTOR_VALUETYPE = nxv32i64,
 
-      nxv1f16        = 133,   // n x   1 x f16
-      nxv2f16        = 134,  // n x  2 x f16
-      nxv4f16        = 135,  // n x  4 x f16
-      nxv8f16        = 136,  // n x  8 x f16
-      nxv16f16       = 137,   // n x  16 x f16
-      nxv32f16       = 138,   // n x  32 x f16
-      nxv2bf16       = 139,  // n x  2 x bf16
-      nxv4bf16       = 140,  // n x  4 x bf16
-      nxv8bf16       = 141,  // n x  8 x bf16
-      nxv1f32        = 142,  // n x  1 x f32
-      nxv2f32        = 143,  // n x  2 x f32
-      nxv4f32        = 144,  // n x  4 x f32
-      nxv8f32        = 145,  // n x  8 x f32
-      nxv16f32       = 146,  // n x 16 x f32
-      nxv1f64        = 147,  // n x  1 x f64
-      nxv2f64        = 148,  // n x  2 x f64
-      nxv4f64        = 149,  // n x  4 x f64
-      nxv8f64        = 150,  // n x  8 x f64
+      nxv1f16        = 139,   // n x   1 x f16
+      nxv2f16        = 140,  // n x  2 x f16
+      nxv4f16        = 141,  // n x  4 x f16
+      nxv8f16        = 142,  // n x  8 x f16
+      nxv16f16       = 143,   // n x  16 x f16
+      nxv32f16       = 144,   // n x  32 x f16
+      nxv2bf16       = 145,  // n x  2 x bf16
+      nxv4bf16       = 146,  // n x  4 x bf16
+      nxv8bf16       = 147,  // n x  8 x bf16
+      nxv1f32        = 148,  // n x  1 x f32
+      nxv2f32        = 149,  // n x  2 x f32
+      nxv4f32        = 150,  // n x  4 x f32
+      nxv8f32        = 151,  // n x  8 x f32
+      nxv16f32       = 152,  // n x 16 x f32
+      nxv1f64        = 153,  // n x  1 x f64
+      nxv2f64        = 154,  // n x  2 x f64
+      nxv4f64        = 155,  // n x  4 x f64
+      nxv8f64        = 156,  // n x  8 x f64
 
       FIRST_FP_SCALABLE_VECTOR_VALUETYPE = nxv1f16,
       LAST_FP_SCALABLE_VECTOR_VALUETYPE = nxv8f64,
 
       FIRST_SCALABLE_VECTOR_VALUETYPE = nxv1i1,
       LAST_SCALABLE_VECTOR_VALUETYPE = nxv8f64,
 
       FIRST_VECTOR_VALUETYPE = v1i1,
       LAST_VECTOR_VALUETYPE  = nxv8f64,
 
-      x86mmx         = 151,   // This is an X86 MMX value
+      x86mmx         = 157,   // This is an X86 MMX value
 
-      Glue           = 152,   // This glues nodes together during pre-RA sched
+      Glue           = 158,   // This glues nodes together during pre-RA sched
 
-      isVoid         = 153,   // This has no value
+      isVoid         = 159,   // This has no value
 
-      Untyped        = 154,   // This value takes a register, but has
+      Untyped        = 160,   // This value takes a register, but has
                               // unspecified type.  The register class
                               // will be determined by the opcode.
 
-      exnref         = 155,   // WebAssembly's exnref type
+      exnref         = 161,   // WebAssembly's exnref type
 
       FIRST_VALUETYPE =  1,   // This is always the beginning of the list.
-      LAST_VALUETYPE = 156,   // This always remains at the end of the list.
+      LAST_VALUETYPE = 162,   // This always remains at the end of the list.
 
       // This is the current maximum for LAST_VALUETYPE.
       // MVT::MAX_ALLOWED_VALUETYPE is used for asserts and to size bit vectors
       // This value must be a multiple of 32.
-      MAX_ALLOWED_VALUETYPE = 160,
+      MAX_ALLOWED_VALUETYPE = 192,
 
       // A value of type llvm::TokenTy
       token          = 248,
 
       // This is MDNode or MDString.
       Metadata       = 249,
 
       // An int value the size of the pointer of the current
       // target to any address space. This must only be used internal to
       // tblgen. Other than for overloading, we treat iPTRAny the same as iPTR.
       iPTRAny        = 250,
 
       // A vector with any length and element size. This is used
       // for intrinsics that have overloadings based on vector types.
       // This is only for tblgen's consumption!
       vAny           = 251,
 
       // Any floating-point or vector floating-point value. This is used
       // for intrinsics that have overloadings based on floating-point types.
       // This is only for tblgen's consumption!
       fAny           = 252,
 
       // An integer or vector integer value of any bit width. This is
       // used for intrinsics that have overloadings based on integer bit widths.
       // This is only for tblgen's consumption!
       iAny           = 253,
 
       // An int value the size of the pointer of the current
       // target.  This should only be used internal to tblgen!
       iPTR           = 254,
 
       // Any type. This is used for intrinsics that have overloadings.
       // This is only for tblgen's consumption!
       Any            = 255
     };
 
     SimpleValueType SimpleTy = INVALID_SIMPLE_VALUE_TYPE;
 
     constexpr MVT() = default;
     constexpr MVT(SimpleValueType SVT) : SimpleTy(SVT) {}
 
     bool operator>(const MVT& S)  const { return SimpleTy >  S.SimpleTy; }
MVT getVectorElementType() const {
       case nxv16i32:
       case nxv32i32: return i32;
       case v1i64:
       case v2i64:
       case v4i64:
       case v8i64:
       case v16i64:
       case v32i64:
+      case v64i64:
+      case v128i64:
+      case v256i64:
       case nxv1i64:
       case nxv2i64:
       case nxv4i64:
       case nxv8i64:
       case nxv16i64:
       case nxv32i64: return i64;
       case v1i128: return i128;
       case v2f16:
MVT getVectorElementType() const {
       case nxv8f32:
       case nxv16f32: return f32;
       case v1f64:
       case v2f64:
       case v4f64:
       case v8f64:
       case v16f64:
       case v32f64:
+      case v64f64:
+      case v128f64:
+      case v256f64:
       case nxv1f64:
       case nxv2f64:
       case nxv4f64:
       case nxv8f64: return f64;
       }
     }
 
     unsigned getVectorNumElements() const {
       switch (SimpleTy) {
       default:
         llvm_unreachable("Not a vector MVT!");
       case v2048i32:
       case v2048f32: return 2048;
       case v1024i1:
       case v1024i32:
       case v1024f32: return 1024;
       case v512i1:
       case v512i32:
       case v512f32: return 512;
       case v256i1:
       case v256i8:
       case v256i32:
-      case v256f32: return 256;
+      case v256i64:
+      case v256f32:
+      case v256f64: return 256;
       case v128i1:
       case v128i8:
       case v128i16:
       case v128i32:
+      case v128i64:
       case v128f16:
       case v128bf16:
-      case v128f32: return 128;
+      case v128f32:
+      case v128f64: return 128;
       case v64i1:
       case v64i8:
       case v64i16:
       case v64i32:
+      case v64i64:
       case v64f16:
       case v64bf16:
       case v64f32:
+      case v64f64:
       case nxv64i1:
       case nxv64i8: return 64;
       case v32i1:
       case v32i8:
       case v32i16:
       case v32i32:
       case v32i64:
       case v32f16:
TypeSize getSizeInBits() const {
       case v64i32:
       case v32i64:
       case v128f16:
       case v128bf16:
       case v64f32:
       case v32f64: return TypeSize::Fixed(2048);
       case nxv32i64: return TypeSize::Scalable(2048);
       case v128i32:
-      case v128f32:  return TypeSize::Fixed(4096);
+      case v64i64:
+      case v128f32:
+      case v64f64:  return TypeSize::Fixed(4096);
       case v256i32:
-      case v256f32:  return TypeSize::Fixed(8192);
+      case v128i64:
+      case v256f32:
+      case v128f64:  return TypeSize::Fixed(8192);
       case v512i32:
-      case v512f32:  return TypeSize::Fixed(16384);
+      case v256i64:
+      case v512f32:
+      case v256f64:  return TypeSize::Fixed(16384);
       case v1024i32:
       case v1024f32:  return TypeSize::Fixed(32768);
       case v2048i32:
       case v2048f32:  return TypeSize::Fixed(65536);
       case exnref: return TypeSize::Fixed(0); // opaque type
       }
     }
 
static MVT getVectorVT(MVT VT, unsigned NumElements) {
         break;
       case MVT::i64:
         if (NumElements == 1)  return MVT::v1i64;
         if (NumElements == 2)  return MVT::v2i64;
         if (NumElements == 4)  return MVT::v4i64;
         if (NumElements == 8)  return MVT::v8i64;
         if (NumElements == 16) return MVT::v16i64;
         if (NumElements == 32) return MVT::v32i64;
+        if (NumElements == 64) return MVT::v64i64;
+        if (NumElements == 128) return MVT::v128i64;
+        if (NumElements == 256) return MVT::v256i64;
         break;
       case MVT::i128:
         if (NumElements == 1)  return MVT::v1i128;
         break;
       case MVT::f16:
         if (NumElements == 2)   return MVT::v2f16;
         if (NumElements == 3)   return MVT::v3f16;
         if (NumElements == 4)   return MVT::v4f16;
static MVT getVectorVT(MVT VT, unsigned NumElements) {
         break;
       case MVT::f64:
         if (NumElements == 1)  return MVT::v1f64;
         if (NumElements == 2)  return MVT::v2f64;
         if (NumElements == 4)  return MVT::v4f64;
         if (NumElements == 8)  return MVT::v8f64;
         if (NumElements == 16) return MVT::v16f64;
         if (NumElements == 32) return MVT::v32f64;
+        if (NumElements == 64) return MVT::v64f64;
+        if (NumElements == 128) return MVT::v128f64;
+        if (NumElements == 256) return MVT::v256f64;
         break;
       }
       return (MVT::SimpleValueType)(MVT::INVALID_SIMPLE_VALUE_TYPE);
     }
 
     static MVT getScalableVectorVT(MVT VT, unsigned NumElements) {
       switch(VT.SimpleTy) {
         default:

llvm/lib/CodeGen/ValueTypes.cpp

Type *EVT::getTypeForEVT(LLVMContext &Context) const {
   case MVT::v4i64:
     return FixedVectorType::get(Type::getInt64Ty(Context), 4);
   case MVT::v8i64:
     return FixedVectorType::get(Type::getInt64Ty(Context), 8);
   case MVT::v16i64:
     return FixedVectorType::get(Type::getInt64Ty(Context), 16);
   case MVT::v32i64:
     return FixedVectorType::get(Type::getInt64Ty(Context), 32);
+  case MVT::v64i64:
+    return FixedVectorType::get(Type::getInt64Ty(Context), 64);
+  case MVT::v128i64:
+    return FixedVectorType::get(Type::getInt64Ty(Context), 128);
+  case MVT::v256i64:
+    return FixedVectorType::get(Type::getInt64Ty(Context), 256);
   case MVT::v1i128:
     return FixedVectorType::get(Type::getInt128Ty(Context), 1);
   case MVT::v2f16:
     return FixedVectorType::get(Type::getHalfTy(Context), 2);
   case MVT::v3f16:
     return FixedVectorType::get(Type::getHalfTy(Context), 3);
   case MVT::v4f16:
     return FixedVectorType::get(Type::getHalfTy(Context), 4);
Type *EVT::getTypeForEVT(LLVMContext &Context) const {
   case MVT::v4f64:
     return FixedVectorType::get(Type::getDoubleTy(Context), 4);
   case MVT::v8f64:
     return FixedVectorType::get(Type::getDoubleTy(Context), 8);
   case MVT::v16f64:
     return FixedVectorType::get(Type::getDoubleTy(Context), 16);
   case MVT::v32f64:
     return FixedVectorType::get(Type::getDoubleTy(Context), 32);
+  case MVT::v64f64:
+    return FixedVectorType::get(Type::getDoubleTy(Context), 64);
+  case MVT::v128f64:
+    return FixedVectorType::get(Type::getDoubleTy(Context), 128);
+  case MVT::v256f64:
+    return FixedVectorType::get(Type::getDoubleTy(Context), 256);
   case MVT::nxv1i1:
     return ScalableVectorType::get(Type::getInt1Ty(Context), 1);
   case MVT::nxv2i1:
     return ScalableVectorType::get(Type::getInt1Ty(Context), 2);
   case MVT::nxv4i1:
     return ScalableVectorType::get(Type::getInt1Ty(Context), 4);
   case MVT::nxv8i1:
     return ScalableVectorType::get(Type::getInt1Ty(Context), 8);

llvm/utils/TableGen/CodeGenTarget.cpp

StringRef llvm::getEnumName(MVT::SimpleValueType T) {
   case MVT::v1024i32: return "MVT::v1024i32";
   case MVT::v2048i32: return "MVT::v2048i32";
   case MVT::v1i64:    return "MVT::v1i64";
   case MVT::v2i64:    return "MVT::v2i64";
   case MVT::v4i64:    return "MVT::v4i64";
   case MVT::v8i64:    return "MVT::v8i64";
   case MVT::v16i64:   return "MVT::v16i64";
   case MVT::v32i64:   return "MVT::v32i64";
+  case MVT::v64i64:   return "MVT::v64i64";
+  case MVT::v128i64:  return "MVT::v128i64";
+  case MVT::v256i64:  return "MVT::v256i64";
   case MVT::v1i128:   return "MVT::v1i128";
   case MVT::v2f16:    return "MVT::v2f16";
   case MVT::v3f16:    return "MVT::v3f16";
   case MVT::v4f16:    return "MVT::v4f16";
   case MVT::v8f16:    return "MVT::v8f16";
   case MVT::v16f16:   return "MVT::v16f16";
   case MVT::v32f16:   return "MVT::v32f16";
   case MVT::v64f16:   return "MVT::v64f16";
StringRef llvm::getEnumName(MVT::SimpleValueType T) {
   case MVT::v1024f32: return "MVT::v1024f32";
   case MVT::v2048f32: return "MVT::v2048f32";
   case MVT::v1f64:    return "MVT::v1f64";
   case MVT::v2f64:    return "MVT::v2f64";
   case MVT::v4f64:    return "MVT::v4f64";
   case MVT::v8f64:    return "MVT::v8f64";
   case MVT::v16f64:   return "MVT::v16f64";
   case MVT::v32f64:   return "MVT::v32f64";
+  case MVT::v64f64:   return "MVT::v64f64";
+  case MVT::v128f64:  return "MVT::v128f64";
+  case MVT::v256f64:  return "MVT::v256f64";
   case MVT::nxv1i1:   return "MVT::nxv1i1";
   case MVT::nxv2i1:   return "MVT::nxv2i1";
   case MVT::nxv4i1:   return "MVT::nxv4i1";
   case MVT::nxv8i1:   return "MVT::nxv8i1";
   case MVT::nxv16i1:  return "MVT::nxv16i1";
   case MVT::nxv32i1:  return "MVT::nxv32i1";
   case MVT::nxv64i1:  return "MVT::nxv64i1";
   case MVT::nxv1i8:   return "MVT::nxv1i8";