[clang] 78ad22e - Recommit ARM-NEON: make type modifiers orthogonal and allow multiple modifiers.

Tim Northover via cfe-commits cfe-commits at lists.llvm.org
Tue Nov 26 01:22:26 PST 2019


Author: Tim Northover
Date: 2019-11-26T09:21:47Z
New Revision: 78ad22e0cc6390fcd44b2b7b5132f1b960ff975d

URL: https://github.com/llvm/llvm-project/commit/78ad22e0cc6390fcd44b2b7b5132f1b960ff975d
DIFF: https://github.com/llvm/llvm-project/commit/78ad22e0cc6390fcd44b2b7b5132f1b960ff975d.diff

LOG: Recommit ARM-NEON: make type modifiers orthogonal and allow multiple modifiers.

The modifier system used to mutate types on NEON intrinsic definitions had a
separate letter for all kinds of transformations that might be needed, and we
were quite quickly running out of letters to use. This patch converts to a much
smaller set of orthogonal modifiers that can be applied together to achieve the
desired effect.

When merging with downstream it is likely to cause a conflict with any local
modifications to the .td files. There is a new script in
utils/convert_arm_neon.py that was used to convert all .td definitions and I
would suggest running it on the last downstream version of those files before
this commit rather than resolving conflicts manually.

The original version broke vcreate_* because it became a macro and didn't
apply the normal integer promotion rules before bitcasting to a vector.
This adds a temporary.

Added: 
    clang/utils/convert_arm_neon.py

Modified: 
    clang/include/clang/Basic/arm_fp16.td
    clang/include/clang/Basic/arm_neon.td
    clang/include/clang/Basic/arm_neon_incl.td
    clang/test/CodeGen/aarch64-neon-intrinsics.c
    clang/test/CodeGen/arm_neon_intrinsics.c
    clang/utils/TableGen/NeonEmitter.cpp

Removed: 
    


################################################################################
diff  --git a/clang/include/clang/Basic/arm_fp16.td b/clang/include/clang/Basic/arm_fp16.td
index bb9873efac85..79cd16233c10 100644
--- a/clang/include/clang/Basic/arm_fp16.td
+++ b/clang/include/clang/Basic/arm_fp16.td
@@ -17,118 +17,118 @@ include "arm_neon_incl.td"
 let ArchGuard = "defined(__ARM_FEATURE_FP16_SCALAR_ARITHMETIC) && defined(__aarch64__)" in {
 
   // Negate
-  def VNEGSH          : SInst<"vneg", "ss", "Sh">;
+  def VNEGSH          : SInst<"vneg", "11", "Sh">;
 
   // Reciprocal/Sqrt
-  def SCALAR_FRECPSH  : IInst<"vrecps", "sss", "Sh">;
-  def FSQRTSH         : SInst<"vsqrt", "ss", "Sh">;
-  def SCALAR_FRSQRTSH : IInst<"vrsqrts", "sss", "Sh">;
+  def SCALAR_FRECPSH  : IInst<"vrecps", "111", "Sh">;
+  def FSQRTSH         : SInst<"vsqrt", "11", "Sh">;
+  def SCALAR_FRSQRTSH : IInst<"vrsqrts", "111", "Sh">;
 
   // Reciprocal Estimate
-  def SCALAR_FRECPEH  : IInst<"vrecpe", "ss", "Sh">;
+  def SCALAR_FRECPEH  : IInst<"vrecpe", "11", "Sh">;
 
   // Reciprocal Exponent
-  def SCALAR_FRECPXH  : IInst<"vrecpx", "ss", "Sh">;
+  def SCALAR_FRECPXH  : IInst<"vrecpx", "11", "Sh">;
 
   // Reciprocal Square Root Estimate
-  def SCALAR_FRSQRTEH : IInst<"vrsqrte", "ss", "Sh">;
+  def SCALAR_FRSQRTEH : IInst<"vrsqrte", "11", "Sh">;
 
   // Rounding
-  def FRINTZ_S64H     : SInst<"vrnd", "ss", "Sh">;
-  def FRINTA_S64H     : SInst<"vrnda", "ss", "Sh">;
-  def FRINTI_S64H     : SInst<"vrndi", "ss", "Sh">;
-  def FRINTM_S64H     : SInst<"vrndm", "ss", "Sh">;
-  def FRINTN_S64H     : SInst<"vrndn", "ss", "Sh">;
-  def FRINTP_S64H     : SInst<"vrndp", "ss", "Sh">;
-  def FRINTX_S64H     : SInst<"vrndx", "ss", "Sh">;
+  def FRINTZ_S64H     : SInst<"vrnd", "11", "Sh">;
+  def FRINTA_S64H     : SInst<"vrnda", "11", "Sh">;
+  def FRINTI_S64H     : SInst<"vrndi", "11", "Sh">;
+  def FRINTM_S64H     : SInst<"vrndm", "11", "Sh">;
+  def FRINTN_S64H     : SInst<"vrndn", "11", "Sh">;
+  def FRINTP_S64H     : SInst<"vrndp", "11", "Sh">;
+  def FRINTX_S64H     : SInst<"vrndx", "11", "Sh">;
 
   // Conversion
-  def SCALAR_SCVTFSH  : SInst<"vcvth_f16", "Ys", "sUs">;
-  def SCALAR_SCVTFSH1 : SInst<"vcvth_f16", "Ys", "iUi">;
-  def SCALAR_SCVTFSH2 : SInst<"vcvth_f16", "Ys", "lUl">;
-  def SCALAR_FCVTZSH  : SInst<"vcvt_s16", "$s", "Sh">;
-  def SCALAR_FCVTZSH1 : SInst<"vcvt_s32", "Is", "Sh">;
-  def SCALAR_FCVTZSH2 : SInst<"vcvt_s64", "Ls", "Sh">;
-  def SCALAR_FCVTZUH  : SInst<"vcvt_u16", "bs", "Sh">;
-  def SCALAR_FCVTZUH1 : SInst<"vcvt_u32", "Us", "Sh">;
-  def SCALAR_FCVTZUH2 : SInst<"vcvt_u64", "Os", "Sh">;
-  def SCALAR_FCVTASH  : SInst<"vcvta_s16", "$s", "Sh">;
-  def SCALAR_FCVTASH1 : SInst<"vcvta_s32", "Is", "Sh">;
-  def SCALAR_FCVTASH2 : SInst<"vcvta_s64", "Ls", "Sh">;
-  def SCALAR_FCVTAUH  : SInst<"vcvta_u16", "bs", "Sh">;
-  def SCALAR_FCVTAUH1 : SInst<"vcvta_u32", "Us", "Sh">;
-  def SCALAR_FCVTAUH2 : SInst<"vcvta_u64", "Os", "Sh">;
-  def SCALAR_FCVTMSH  : SInst<"vcvtm_s16", "$s", "Sh">;
-  def SCALAR_FCVTMSH1 : SInst<"vcvtm_s32", "Is", "Sh">;
-  def SCALAR_FCVTMSH2 : SInst<"vcvtm_s64", "Ls", "Sh">;
-  def SCALAR_FCVTMUH  : SInst<"vcvtm_u16", "bs", "Sh">;
-  def SCALAR_FCVTMUH1 : SInst<"vcvtm_u32", "Us", "Sh">;
-  def SCALAR_FCVTMUH2 : SInst<"vcvtm_u64", "Os", "Sh">;
-  def SCALAR_FCVTNSH  : SInst<"vcvtn_s16", "$s", "Sh">;
-  def SCALAR_FCVTNSH1 : SInst<"vcvtn_s32", "Is", "Sh">;
-  def SCALAR_FCVTNSH2 : SInst<"vcvtn_s64", "Ls", "Sh">;
-  def SCALAR_FCVTNUH  : SInst<"vcvtn_u16", "bs", "Sh">;
-  def SCALAR_FCVTNUH1 : SInst<"vcvtn_u32", "Us", "Sh">;
-  def SCALAR_FCVTNUH2 : SInst<"vcvtn_u64", "Os", "Sh">;
-  def SCALAR_FCVTPSH  : SInst<"vcvtp_s16", "$s", "Sh">;
-  def SCALAR_FCVTPSH1 : SInst<"vcvtp_s32", "Is", "Sh">;
-  def SCALAR_FCVTPSH2 : SInst<"vcvtp_s64", "Ls", "Sh">;
-  def SCALAR_FCVTPUH  : SInst<"vcvtp_u16", "bs", "Sh">;
-  def SCALAR_FCVTPUH1 : SInst<"vcvtp_u32", "Us", "Sh">;
-  def SCALAR_FCVTPUH2 : SInst<"vcvtp_u64", "Os", "Sh">;
+  def SCALAR_SCVTFSH  : SInst<"vcvth_f16", "(1F)(1!)", "sUs">;
+  def SCALAR_SCVTFSH1 : SInst<"vcvth_f16", "(1F<)(1!)", "iUi">;
+  def SCALAR_SCVTFSH2 : SInst<"vcvth_f16", "(1F<<)(1!)", "lUl">;
+  def SCALAR_FCVTZSH  : SInst<"vcvt_s16", "(1S)1", "Sh">;
+  def SCALAR_FCVTZSH1 : SInst<"vcvt_s32", "(1S>)1", "Sh">;
+  def SCALAR_FCVTZSH2 : SInst<"vcvt_s64", "(1S>>)1", "Sh">;
+  def SCALAR_FCVTZUH  : SInst<"vcvt_u16", "(1U)1", "Sh">;
+  def SCALAR_FCVTZUH1 : SInst<"vcvt_u32", "(1U>)1", "Sh">;
+  def SCALAR_FCVTZUH2 : SInst<"vcvt_u64", "(1U>>)1", "Sh">;
+  def SCALAR_FCVTASH  : SInst<"vcvta_s16", "(1S)1", "Sh">;
+  def SCALAR_FCVTASH1 : SInst<"vcvta_s32", "(1S>)1", "Sh">;
+  def SCALAR_FCVTASH2 : SInst<"vcvta_s64", "(1S>>)1", "Sh">;
+  def SCALAR_FCVTAUH  : SInst<"vcvta_u16", "(1U)1", "Sh">;
+  def SCALAR_FCVTAUH1 : SInst<"vcvta_u32", "(1U>)1", "Sh">;
+  def SCALAR_FCVTAUH2 : SInst<"vcvta_u64", "(1U>>)1", "Sh">;
+  def SCALAR_FCVTMSH  : SInst<"vcvtm_s16", "(1S)1", "Sh">;
+  def SCALAR_FCVTMSH1 : SInst<"vcvtm_s32", "(1S>)1", "Sh">;
+  def SCALAR_FCVTMSH2 : SInst<"vcvtm_s64", "(1S>>)1", "Sh">;
+  def SCALAR_FCVTMUH  : SInst<"vcvtm_u16", "(1U)1", "Sh">;
+  def SCALAR_FCVTMUH1 : SInst<"vcvtm_u32", "(1U>)1", "Sh">;
+  def SCALAR_FCVTMUH2 : SInst<"vcvtm_u64", "(1U>>)1", "Sh">;
+  def SCALAR_FCVTNSH  : SInst<"vcvtn_s16", "(1S)1", "Sh">;
+  def SCALAR_FCVTNSH1 : SInst<"vcvtn_s32", "(1S>)1", "Sh">;
+  def SCALAR_FCVTNSH2 : SInst<"vcvtn_s64", "(1S>>)1", "Sh">;
+  def SCALAR_FCVTNUH  : SInst<"vcvtn_u16", "(1U)1", "Sh">;
+  def SCALAR_FCVTNUH1 : SInst<"vcvtn_u32", "(1U>)1", "Sh">;
+  def SCALAR_FCVTNUH2 : SInst<"vcvtn_u64", "(1U>>)1", "Sh">;
+  def SCALAR_FCVTPSH  : SInst<"vcvtp_s16", "(1S)1", "Sh">;
+  def SCALAR_FCVTPSH1 : SInst<"vcvtp_s32", "(1S>)1", "Sh">;
+  def SCALAR_FCVTPSH2 : SInst<"vcvtp_s64", "(1S>>)1", "Sh">;
+  def SCALAR_FCVTPUH  : SInst<"vcvtp_u16", "(1U)1", "Sh">;
+  def SCALAR_FCVTPUH1 : SInst<"vcvtp_u32", "(1U>)1", "Sh">;
+  def SCALAR_FCVTPUH2 : SInst<"vcvtp_u64", "(1U>>)1", "Sh">;
   let isVCVT_N = 1 in {
-    def SCALAR_SCVTFSHO : SInst<"vcvth_n_f16", "Ysi", "sUs">;
-    def SCALAR_SCVTFSH1O: SInst<"vcvth_n_f16", "Ysi", "iUi">;
-    def SCALAR_SCVTFSH2O: SInst<"vcvth_n_f16", "Ysi", "lUl">;
-    def SCALAR_FCVTZSHO : SInst<"vcvt_n_s16", "$si", "Sh">;
-    def SCALAR_FCVTZSH1O: SInst<"vcvt_n_s32", "Isi", "Sh">;
-    def SCALAR_FCVTZSH2O: SInst<"vcvt_n_s64", "Lsi", "Sh">;
-    def SCALAR_FCVTZUHO : SInst<"vcvt_n_u16", "bsi", "Sh">;
-    def SCALAR_FCVTZUH1O: SInst<"vcvt_n_u32", "Usi", "Sh">;
-    def SCALAR_FCVTZUH2O: SInst<"vcvt_n_u64", "Osi", "Sh">;
+    def SCALAR_SCVTFSHO : SInst<"vcvth_n_f16", "(1F)(1!)I", "sUs">;
+    def SCALAR_SCVTFSH1O: SInst<"vcvth_n_f16", "(1F<)(1!)I", "iUi">;
+    def SCALAR_SCVTFSH2O: SInst<"vcvth_n_f16", "(1F<<)(1!)I", "lUl">;
+    def SCALAR_FCVTZSHO : SInst<"vcvt_n_s16", "(1S)1I", "Sh">;
+    def SCALAR_FCVTZSH1O: SInst<"vcvt_n_s32", "(1S>)1I", "Sh">;
+    def SCALAR_FCVTZSH2O: SInst<"vcvt_n_s64", "(1S>>)1I", "Sh">;
+    def SCALAR_FCVTZUHO : SInst<"vcvt_n_u16", "(1U)1I", "Sh">;
+    def SCALAR_FCVTZUH1O: SInst<"vcvt_n_u32", "(1U>)1I", "Sh">;
+    def SCALAR_FCVTZUH2O: SInst<"vcvt_n_u64", "(1U>>)1I", "Sh">;
   }
   // Comparison
-  def SCALAR_CMEQRH   : SInst<"vceq", "bss", "Sh">;
-  def SCALAR_CMEQZH   : SInst<"vceqz", "bs", "Sh">;
-  def SCALAR_CMGERH   : SInst<"vcge", "bss", "Sh">;
-  def SCALAR_CMGEZH   : SInst<"vcgez", "bs", "Sh">;
-  def SCALAR_CMGTRH   : SInst<"vcgt", "bss", "Sh">;
-  def SCALAR_CMGTZH   : SInst<"vcgtz", "bs", "Sh">;
-  def SCALAR_CMLERH   : SInst<"vcle", "bss", "Sh">;
-  def SCALAR_CMLEZH   : SInst<"vclez", "bs", "Sh">;
-  def SCALAR_CMLTH    : SInst<"vclt", "bss", "Sh">;
-  def SCALAR_CMLTZH   : SInst<"vcltz", "bs", "Sh">;
+  def SCALAR_CMEQRH   : SInst<"vceq", "(1U)11", "Sh">;
+  def SCALAR_CMEQZH   : SInst<"vceqz", "(1U)1", "Sh">;
+  def SCALAR_CMGERH   : SInst<"vcge", "(1U)11", "Sh">;
+  def SCALAR_CMGEZH   : SInst<"vcgez", "(1U)1", "Sh">;
+  def SCALAR_CMGTRH   : SInst<"vcgt", "(1U)11", "Sh">;
+  def SCALAR_CMGTZH   : SInst<"vcgtz", "(1U)1", "Sh">;
+  def SCALAR_CMLERH   : SInst<"vcle", "(1U)11", "Sh">;
+  def SCALAR_CMLEZH   : SInst<"vclez", "(1U)1", "Sh">;
+  def SCALAR_CMLTH    : SInst<"vclt", "(1U)11", "Sh">;
+  def SCALAR_CMLTZH   : SInst<"vcltz", "(1U)1", "Sh">;
 
   // Absolute Compare Mask Greater Than Or Equal
-  def SCALAR_FACGEH   : IInst<"vcage", "bss", "Sh">;
-  def SCALAR_FACLEH   : IInst<"vcale", "bss", "Sh">;
+  def SCALAR_FACGEH   : IInst<"vcage", "(1U)11", "Sh">;
+  def SCALAR_FACLEH   : IInst<"vcale", "(1U)11", "Sh">;
 
   // Absolute Compare Mask Greater Than
-  def SCALAR_FACGT    : IInst<"vcagt", "bss", "Sh">;
-  def SCALAR_FACLT    : IInst<"vcalt", "bss", "Sh">;
+  def SCALAR_FACGT    : IInst<"vcagt", "(1U)11", "Sh">;
+  def SCALAR_FACLT    : IInst<"vcalt", "(1U)11", "Sh">;
 
   // Scalar Absolute Value
-  def SCALAR_ABSH     : SInst<"vabs", "ss", "Sh">;
+  def SCALAR_ABSH     : SInst<"vabs", "11", "Sh">;
 
   // Scalar Absolute Difference
-  def SCALAR_ABDH: IInst<"vabd", "sss", "Sh">;
+  def SCALAR_ABDH: IInst<"vabd", "111", "Sh">;
 
   // Add/Sub
-  def VADDSH          : SInst<"vadd", "sss", "Sh">;
-  def VSUBHS          : SInst<"vsub", "sss", "Sh">;
+  def VADDSH          : SInst<"vadd", "111", "Sh">;
+  def VSUBHS          : SInst<"vsub", "111", "Sh">;
 
   // Max/Min
-  def VMAXHS          : SInst<"vmax", "sss", "Sh">;
-  def VMINHS          : SInst<"vmin", "sss", "Sh">;
-  def FMAXNMHS        : SInst<"vmaxnm", "sss", "Sh">;
-  def FMINNMHS        : SInst<"vminnm", "sss", "Sh">;
+  def VMAXHS          : SInst<"vmax", "111", "Sh">;
+  def VMINHS          : SInst<"vmin", "111", "Sh">;
+  def FMAXNMHS        : SInst<"vmaxnm", "111", "Sh">;
+  def FMINNMHS        : SInst<"vminnm", "111", "Sh">;
 
   // Multiplication/Division
-  def VMULHS          : SInst<"vmul", "sss", "Sh">;
-  def MULXHS          : SInst<"vmulx", "sss", "Sh">;
-  def FDIVHS          : SInst<"vdiv", "sss",  "Sh">;
+  def VMULHS          : SInst<"vmul", "111", "Sh">;
+  def MULXHS          : SInst<"vmulx", "111", "Sh">;
+  def FDIVHS          : SInst<"vdiv", "111",  "Sh">;
 
   // Vector fused multiply-add operations
-  def VFMAHS          : SInst<"vfma", "ssss", "Sh">;
-  def VFMSHS          : SInst<"vfms", "ssss", "Sh">;
+  def VFMAHS          : SInst<"vfma", "1111", "Sh">;
+  def VFMSHS          : SInst<"vfms", "1111", "Sh">;
 }

diff  --git a/clang/include/clang/Basic/arm_neon.td b/clang/include/clang/Basic/arm_neon.td
index 127c5af97ce6..b5e395c8103f 100644
--- a/clang/include/clang/Basic/arm_neon.td
+++ b/clang/include/clang/Basic/arm_neon.td
@@ -109,7 +109,8 @@ def OP_OR       : Op<(op "|", $p0, $p1)>;
 def OP_XOR      : Op<(op "^", $p0, $p1)>;
 def OP_ANDN     : Op<(op "&", $p0, (op "~", $p1))>;
 def OP_ORN      : Op<(op "|", $p0, (op "~", $p1))>;
-def OP_CAST     : Op<(cast "R", $p0)>;
+def OP_CAST     : LOp<[(save_temp $promote, $p0),
+                       (cast "R", $promote)]>;
 def OP_HI       : Op<(shuffle $p0, $p0, (highhalf mask0))>;
 def OP_LO       : Op<(shuffle $p0, $p0, (lowhalf mask0))>;
 def OP_CONC     : Op<(shuffle $p0, $p1, (add mask0, mask1))>;
@@ -226,240 +227,240 @@ def OP_FMLSL_LN_Hi  : Op<(call "vfmlsl_high", $p0, $p1,
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.1 Addition
-def VADD    : IOpInst<"vadd", "ddd",
+def VADD    : IOpInst<"vadd", "...",
                       "csilfUcUsUiUlQcQsQiQlQfQUcQUsQUiQUl", OP_ADD>;
-def VADDL   : SOpInst<"vaddl", "wdd", "csiUcUsUi", OP_ADDL>;
-def VADDW   : SOpInst<"vaddw", "wwd", "csiUcUsUi", OP_ADDW>;
-def VHADD   : SInst<"vhadd", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">;
-def VRHADD  : SInst<"vrhadd", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">;
-def VQADD   : SInst<"vqadd", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VADDHN  : IInst<"vaddhn", "hkk", "silUsUiUl">;
-def VRADDHN : IInst<"vraddhn", "hkk", "silUsUiUl">;
+def VADDL   : SOpInst<"vaddl", "(>Q)..", "csiUcUsUi", OP_ADDL>;
+def VADDW   : SOpInst<"vaddw", "(>Q)(>Q).", "csiUcUsUi", OP_ADDW>;
+def VHADD   : SInst<"vhadd", "...", "csiUcUsUiQcQsQiQUcQUsQUi">;
+def VRHADD  : SInst<"vrhadd", "...", "csiUcUsUiQcQsQiQUcQUsQUi">;
+def VQADD   : SInst<"vqadd", "...", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VADDHN  : IInst<"vaddhn", "<QQ", "silUsUiUl">;
+def VRADDHN : IInst<"vraddhn", "<QQ", "silUsUiUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.2 Multiplication
-def VMUL     : IOpInst<"vmul", "ddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MUL>;
-def VMULP    : SInst<"vmul", "ddd", "PcQPc">;
-def VMLA     : IOpInst<"vmla", "dddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MLA>;
-def VMLAL    : SOpInst<"vmlal", "wwdd", "csiUcUsUi", OP_MLAL>;
-def VMLS     : IOpInst<"vmls", "dddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MLS>;
-def VMLSL    : SOpInst<"vmlsl", "wwdd", "csiUcUsUi", OP_MLSL>;
-def VQDMULH  : SInst<"vqdmulh", "ddd", "siQsQi">;
-def VQRDMULH : SInst<"vqrdmulh", "ddd", "siQsQi">;
+def VMUL     : IOpInst<"vmul", "...", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MUL>;
+def VMULP    : SInst<"vmul", "...", "PcQPc">;
+def VMLA     : IOpInst<"vmla", "....", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MLA>;
+def VMLAL    : SOpInst<"vmlal", "(>Q)(>Q)..", "csiUcUsUi", OP_MLAL>;
+def VMLS     : IOpInst<"vmls", "....", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MLS>;
+def VMLSL    : SOpInst<"vmlsl", "(>Q)(>Q)..", "csiUcUsUi", OP_MLSL>;
+def VQDMULH  : SInst<"vqdmulh", "...", "siQsQi">;
+def VQRDMULH : SInst<"vqrdmulh", "...", "siQsQi">;
 
 let ArchGuard = "defined(__ARM_FEATURE_QRDMX)" in {
-def VQRDMLAH : SOpInst<"vqrdmlah", "dddd", "siQsQi", OP_QRDMLAH>;
-def VQRDMLSH : SOpInst<"vqrdmlsh", "dddd", "siQsQi", OP_QRDMLSH>;
+def VQRDMLAH : SOpInst<"vqrdmlah", "....", "siQsQi", OP_QRDMLAH>;
+def VQRDMLSH : SOpInst<"vqrdmlsh", "....", "siQsQi", OP_QRDMLSH>;
 }
 
-def VQDMLAL  : SInst<"vqdmlal", "wwdd", "si">;
-def VQDMLSL  : SInst<"vqdmlsl", "wwdd", "si">;
-def VMULL    : SInst<"vmull", "wdd", "csiUcUsUiPc">;
-def VQDMULL  : SInst<"vqdmull", "wdd", "si">;
+def VQDMLAL  : SInst<"vqdmlal", "(>Q)(>Q)..", "si">;
+def VQDMLSL  : SInst<"vqdmlsl", "(>Q)(>Q)..", "si">;
+def VMULL    : SInst<"vmull", "(>Q)..", "csiUcUsUiPc">;
+def VQDMULL  : SInst<"vqdmull", "(>Q)..", "si">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.3 Subtraction
-def VSUB    : IOpInst<"vsub", "ddd",
+def VSUB    : IOpInst<"vsub", "...",
                       "csilfUcUsUiUlQcQsQiQlQfQUcQUsQUiQUl", OP_SUB>;
-def VSUBL   : SOpInst<"vsubl", "wdd", "csiUcUsUi", OP_SUBL>;
-def VSUBW   : SOpInst<"vsubw", "wwd", "csiUcUsUi", OP_SUBW>;
-def VQSUB   : SInst<"vqsub", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VHSUB   : SInst<"vhsub", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">;
-def VSUBHN  : IInst<"vsubhn", "hkk", "silUsUiUl">;
-def VRSUBHN : IInst<"vrsubhn", "hkk", "silUsUiUl">;
+def VSUBL   : SOpInst<"vsubl", "(>Q)..", "csiUcUsUi", OP_SUBL>;
+def VSUBW   : SOpInst<"vsubw", "(>Q)(>Q).", "csiUcUsUi", OP_SUBW>;
+def VQSUB   : SInst<"vqsub", "...", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VHSUB   : SInst<"vhsub", "...", "csiUcUsUiQcQsQiQUcQUsQUi">;
+def VSUBHN  : IInst<"vsubhn", "<QQ", "silUsUiUl">;
+def VRSUBHN : IInst<"vrsubhn", "<QQ", "silUsUiUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.4 Comparison
-def VCEQ  : IOpInst<"vceq", "udd", "csifUcUsUiPcQcQsQiQfQUcQUsQUiQPc", OP_EQ>;
-def VCGE  : SOpInst<"vcge", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_GE>;
+def VCEQ  : IOpInst<"vceq", "U..", "csifUcUsUiPcQcQsQiQfQUcQUsQUiQPc", OP_EQ>;
+def VCGE  : SOpInst<"vcge", "U..", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_GE>;
 let InstName = "vcge" in
-def VCLE  : SOpInst<"vcle", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_LE>;
-def VCGT  : SOpInst<"vcgt", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_GT>;
+def VCLE  : SOpInst<"vcle", "U..", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_LE>;
+def VCGT  : SOpInst<"vcgt", "U..", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_GT>;
 let InstName = "vcgt" in
-def VCLT  : SOpInst<"vclt", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_LT>;
+def VCLT  : SOpInst<"vclt", "U..", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_LT>;
 let InstName = "vacge" in {
-def VCAGE : IInst<"vcage", "udd", "fQf">;
-def VCALE : IInst<"vcale", "udd", "fQf">;
+def VCAGE : IInst<"vcage", "U..", "fQf">;
+def VCALE : IInst<"vcale", "U..", "fQf">;
 }
 let InstName = "vacgt" in {
-def VCAGT : IInst<"vcagt", "udd", "fQf">;
-def VCALT : IInst<"vcalt", "udd", "fQf">;
+def VCAGT : IInst<"vcagt", "U..", "fQf">;
+def VCALT : IInst<"vcalt", "U..", "fQf">;
 }
-def VTST  : WInst<"vtst", "udd", "csiUcUsUiPcPsQcQsQiQUcQUsQUiQPcQPs">;
+def VTST  : WInst<"vtst", "U..", "csiUcUsUiPcPsQcQsQiQUcQUsQUiQPcQPs">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.5 Absolute Difference
-def VABD  : SInst<"vabd", "ddd",  "csiUcUsUifQcQsQiQUcQUsQUiQf">;
-def VABDL : SOpInst<"vabdl", "wdd",  "csiUcUsUi", OP_ABDL>;
-def VABA  : SOpInst<"vaba", "dddd", "csiUcUsUiQcQsQiQUcQUsQUi", OP_ABA>;
-def VABAL : SOpInst<"vabal", "wwdd", "csiUcUsUi", OP_ABAL>;
+def VABD  : SInst<"vabd", "...",  "csiUcUsUifQcQsQiQUcQUsQUiQf">;
+def VABDL : SOpInst<"vabdl", "(>Q)..",  "csiUcUsUi", OP_ABDL>;
+def VABA  : SOpInst<"vaba", "....", "csiUcUsUiQcQsQiQUcQUsQUi", OP_ABA>;
+def VABAL : SOpInst<"vabal", "(>Q)(>Q)..", "csiUcUsUi", OP_ABAL>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.6 Max/Min
-def VMAX : SInst<"vmax", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQf">;
-def VMIN : SInst<"vmin", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQf">;
+def VMAX : SInst<"vmax", "...", "csiUcUsUifQcQsQiQUcQUsQUiQf">;
+def VMIN : SInst<"vmin", "...", "csiUcUsUifQcQsQiQUcQUsQUiQf">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.7 Pairwise Addition
-def VPADD  : IInst<"vpadd", "ddd", "csiUcUsUif">;
-def VPADDL : SInst<"vpaddl", "nd",  "csiUcUsUiQcQsQiQUcQUsQUi">;
-def VPADAL : SInst<"vpadal", "nnd", "csiUcUsUiQcQsQiQUcQUsQUi">;
+def VPADD  : IInst<"vpadd", "...", "csiUcUsUif">;
+def VPADDL : SInst<"vpaddl", ">.",  "csiUcUsUiQcQsQiQUcQUsQUi">;
+def VPADAL : SInst<"vpadal", ">>.", "csiUcUsUiQcQsQiQUcQUsQUi">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.8-9 Folding Max/Min
-def VPMAX : SInst<"vpmax", "ddd", "csiUcUsUif">;
-def VPMIN : SInst<"vpmin", "ddd", "csiUcUsUif">;
+def VPMAX : SInst<"vpmax", "...", "csiUcUsUif">;
+def VPMIN : SInst<"vpmin", "...", "csiUcUsUif">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.10 Reciprocal/Sqrt
-def VRECPS  : IInst<"vrecps", "ddd", "fQf">;
-def VRSQRTS : IInst<"vrsqrts", "ddd", "fQf">;
+def VRECPS  : IInst<"vrecps", "...", "fQf">;
+def VRSQRTS : IInst<"vrsqrts", "...", "fQf">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.11 Shifts by signed variable
-def VSHL   : SInst<"vshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VQSHL  : SInst<"vqshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VRSHL  : SInst<"vrshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VQRSHL : SInst<"vqrshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VSHL   : SInst<"vshl", "..S", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VQSHL  : SInst<"vqshl", "..S", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VRSHL  : SInst<"vrshl", "..S", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VQRSHL : SInst<"vqrshl", "..S", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.12 Shifts by constant
 let isShift = 1 in {
-def VSHR_N     : SInst<"vshr_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VSHL_N     : IInst<"vshl_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VRSHR_N    : SInst<"vrshr_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VSRA_N     : SInst<"vsra_n", "dddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VRSRA_N    : SInst<"vrsra_n", "dddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VQSHL_N    : SInst<"vqshl_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
-def VQSHLU_N   : SInst<"vqshlu_n", "udi", "csilQcQsQiQl">;
-def VSHRN_N    : IInst<"vshrn_n", "hki", "silUsUiUl">;
-def VQSHRUN_N  : SInst<"vqshrun_n", "eki", "sil">;
-def VQRSHRUN_N : SInst<"vqrshrun_n", "eki", "sil">;
-def VQSHRN_N   : SInst<"vqshrn_n", "hki", "silUsUiUl">;
-def VRSHRN_N   : IInst<"vrshrn_n", "hki", "silUsUiUl">;
-def VQRSHRN_N  : SInst<"vqrshrn_n", "hki", "silUsUiUl">;
-def VSHLL_N    : SInst<"vshll_n", "wdi", "csiUcUsUi">;
+def VSHR_N     : SInst<"vshr_n", "..I", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VSHL_N     : IInst<"vshl_n", "..I", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VRSHR_N    : SInst<"vrshr_n", "..I", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VSRA_N     : SInst<"vsra_n", "...I", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VRSRA_N    : SInst<"vrsra_n", "...I", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VQSHL_N    : SInst<"vqshl_n", "..I", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">;
+def VQSHLU_N   : SInst<"vqshlu_n", "U.I", "csilQcQsQiQl">;
+def VSHRN_N    : IInst<"vshrn_n", "<QI", "silUsUiUl">;
+def VQSHRUN_N  : SInst<"vqshrun_n", "(<U)QI", "sil">;
+def VQRSHRUN_N : SInst<"vqrshrun_n", "(<U)QI", "sil">;
+def VQSHRN_N   : SInst<"vqshrn_n", "<QI", "silUsUiUl">;
+def VRSHRN_N   : IInst<"vrshrn_n", "<QI", "silUsUiUl">;
+def VQRSHRN_N  : SInst<"vqrshrn_n", "<QI", "silUsUiUl">;
+def VSHLL_N    : SInst<"vshll_n", "(>Q).I", "csiUcUsUi">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.13 Shifts with insert
-def VSRI_N : WInst<"vsri_n", "dddi",
+def VSRI_N : WInst<"vsri_n", "...I",
                    "csilUcUsUiUlPcPsQcQsQiQlQUcQUsQUiQUlQPcQPs">;
-def VSLI_N : WInst<"vsli_n", "dddi",
+def VSLI_N : WInst<"vsli_n", "...I",
                    "csilUcUsUiUlPcPsQcQsQiQlQUcQUsQUiQUlQPcQPs">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.14 Loads and stores of a single vector
-def VLD1      : WInst<"vld1", "dc",
+def VLD1      : WInst<"vld1", ".(c*!)",
                       "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VLD1_X2   : WInst<"vld1_x2", "2c",
+def VLD1_X2   : WInst<"vld1_x2", "2(c*!)",
                       "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">;
-def VLD1_X3   : WInst<"vld1_x3", "3c",
+def VLD1_X3   : WInst<"vld1_x3", "3(c*!)",
                       "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">;
-def VLD1_X4   : WInst<"vld1_x4", "4c",
+def VLD1_X4   : WInst<"vld1_x4", "4(c*!)",
                       "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">;
-def VLD1_LANE : WInst<"vld1_lane", "dcdi",
+def VLD1_LANE : WInst<"vld1_lane", ".(c*!).I",
                       "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VLD1_DUP  : WInst<"vld1_dup", "dc",
+def VLD1_DUP  : WInst<"vld1_dup", ".(c*!)",
                       "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VST1      : WInst<"vst1", "vpd",
+def VST1      : WInst<"vst1", "v*(.!)",
                       "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VST1_X2   : WInst<"vst1_x2", "vp2",
+def VST1_X2   : WInst<"vst1_x2", "v*(2!)",
                       "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">;
-def VST1_X3   : WInst<"vst1_x3", "vp3",
+def VST1_X3   : WInst<"vst1_x3", "v*(3!)",
                       "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">;
-def VST1_X4   : WInst<"vst1_x4", "vp4",
+def VST1_X4   : WInst<"vst1_x4", "v*(4!)",
                       "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">;
-def VST1_LANE : WInst<"vst1_lane", "vpdi",
+def VST1_LANE : WInst<"vst1_lane", "v*(.!)I",
                       "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">;
 let ArchGuard = "(__ARM_FP & 2)" in {
-def VLD1_F16      : WInst<"vld1", "dc", "hQh">;
-def VLD1_X2_F16   : WInst<"vld1_x2", "2c", "hQh">;
-def VLD1_X3_F16   : WInst<"vld1_x3", "3c", "hQh">;
-def VLD1_X4_F16   : WInst<"vld1_x4", "4c", "hQh">;
-def VLD1_LANE_F16 : WInst<"vld1_lane", "dcdi", "hQh">;
-def VLD1_DUP_F16  : WInst<"vld1_dup", "dc", "hQh">;
-def VST1_F16      : WInst<"vst1", "vpd", "hQh">;
-def VST1_X2_F16   : WInst<"vst1_x2", "vp2", "hQh">;
-def VST1_X3_F16   : WInst<"vst1_x3", "vp3", "hQh">;
-def VST1_X4_F16   : WInst<"vst1_x4", "vp4", "hQh">;
-def VST1_LANE_F16 : WInst<"vst1_lane", "vpdi", "hQh">;
+def VLD1_F16      : WInst<"vld1", ".(c*!)", "hQh">;
+def VLD1_X2_F16   : WInst<"vld1_x2", "2(c*!)", "hQh">;
+def VLD1_X3_F16   : WInst<"vld1_x3", "3(c*!)", "hQh">;
+def VLD1_X4_F16   : WInst<"vld1_x4", "4(c*!)", "hQh">;
+def VLD1_LANE_F16 : WInst<"vld1_lane", ".(c*!).I", "hQh">;
+def VLD1_DUP_F16  : WInst<"vld1_dup", ".(c*!)", "hQh">;
+def VST1_F16      : WInst<"vst1", "v*(.!)", "hQh">;
+def VST1_X2_F16   : WInst<"vst1_x2", "v*(2!)", "hQh">;
+def VST1_X3_F16   : WInst<"vst1_x3", "v*(3!)", "hQh">;
+def VST1_X4_F16   : WInst<"vst1_x4", "v*(4!)", "hQh">;
+def VST1_LANE_F16 : WInst<"vst1_lane", "v*(.!)I", "hQh">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.15 Loads and stores of an N-element structure
-def VLD2 : WInst<"vld2", "2c", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VLD3 : WInst<"vld3", "3c", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VLD4 : WInst<"vld4", "4c", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VLD2_DUP  : WInst<"vld2_dup", "2c",
+def VLD2 : WInst<"vld2", "2(c*!)", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
+def VLD3 : WInst<"vld3", "3(c*!)", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
+def VLD4 : WInst<"vld4", "4(c*!)", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
+def VLD2_DUP  : WInst<"vld2_dup", "2(c*!)",
                       "UcUsUiUlcsilfPcPsQcQfQiQlQsQPcQPsQUcQUiQUlQUs">;
-def VLD3_DUP  : WInst<"vld3_dup", "3c",
+def VLD3_DUP  : WInst<"vld3_dup", "3(c*!)",
                       "UcUsUiUlcsilfPcPsQcQfQiQlQsQPcQPsQUcQUiQUlQUs">;
-def VLD4_DUP  : WInst<"vld4_dup", "4c",
+def VLD4_DUP  : WInst<"vld4_dup", "4(c*!)",
                       "UcUsUiUlcsilfPcPsQcQfQiQlQsQPcQPsQUcQUiQUlQUs">;
-def VLD2_LANE : WInst<"vld2_lane", "2c2i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
-def VLD3_LANE : WInst<"vld3_lane", "3c3i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
-def VLD4_LANE : WInst<"vld4_lane", "4c4i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
-def VST2 : WInst<"vst2", "vp2", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VST3 : WInst<"vst3", "vp3", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VST4 : WInst<"vst4", "vp4", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
-def VST2_LANE : WInst<"vst2_lane", "vp2i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
-def VST3_LANE : WInst<"vst3_lane", "vp3i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
-def VST4_LANE : WInst<"vst4_lane", "vp4i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
+def VLD2_LANE : WInst<"vld2_lane", "2(c*!)2I", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
+def VLD3_LANE : WInst<"vld3_lane", "3(c*!)3I", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
+def VLD4_LANE : WInst<"vld4_lane", "4(c*!)4I", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
+def VST2 : WInst<"vst2", "v*(2!)", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
+def VST3 : WInst<"vst3", "v*(3!)", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
+def VST4 : WInst<"vst4", "v*(4!)", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">;
+def VST2_LANE : WInst<"vst2_lane", "v*(2!)I", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
+def VST3_LANE : WInst<"vst3_lane", "v*(3!)I", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
+def VST4_LANE : WInst<"vst4_lane", "v*(4!)I", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">;
 let ArchGuard = "(__ARM_FP & 2)" in {
-def VLD2_F16      : WInst<"vld2", "2c", "hQh">;
-def VLD3_F16      : WInst<"vld3", "3c", "hQh">;
-def VLD4_F16      : WInst<"vld4", "4c", "hQh">;
-def VLD2_DUP_F16  : WInst<"vld2_dup", "2c", "hQh">;
-def VLD3_DUP_F16  : WInst<"vld3_dup", "3c", "hQh">;
-def VLD4_DUP_F16  : WInst<"vld4_dup", "4c", "hQh">;
-def VLD2_LANE_F16 : WInst<"vld2_lane", "2c2i", "hQh">;
-def VLD3_LANE_F16 : WInst<"vld3_lane", "3c3i", "hQh">;
-def VLD4_LANE_F16 : WInst<"vld4_lane", "4c4i", "hQh">;
-def VST2_F16      : WInst<"vst2", "vp2", "hQh">;
-def VST3_F16      : WInst<"vst3", "vp3", "hQh">;
-def VST4_F16      : WInst<"vst4", "vp4", "hQh">;
-def VST2_LANE_F16 : WInst<"vst2_lane", "vp2i", "hQh">;
-def VST3_LANE_F16 : WInst<"vst3_lane", "vp3i", "hQh">;
-def VST4_LANE_F16 : WInst<"vst4_lane", "vp4i", "hQh">;
+def VLD2_F16      : WInst<"vld2", "2(c*!)", "hQh">;
+def VLD3_F16      : WInst<"vld3", "3(c*!)", "hQh">;
+def VLD4_F16      : WInst<"vld4", "4(c*!)", "hQh">;
+def VLD2_DUP_F16  : WInst<"vld2_dup", "2(c*!)", "hQh">;
+def VLD3_DUP_F16  : WInst<"vld3_dup", "3(c*!)", "hQh">;
+def VLD4_DUP_F16  : WInst<"vld4_dup", "4(c*!)", "hQh">;
+def VLD2_LANE_F16 : WInst<"vld2_lane", "2(c*!)2I", "hQh">;
+def VLD3_LANE_F16 : WInst<"vld3_lane", "3(c*!)3I", "hQh">;
+def VLD4_LANE_F16 : WInst<"vld4_lane", "4(c*!)4I", "hQh">;
+def VST2_F16      : WInst<"vst2", "v*(2!)", "hQh">;
+def VST3_F16      : WInst<"vst3", "v*(3!)", "hQh">;
+def VST4_F16      : WInst<"vst4", "v*(4!)", "hQh">;
+def VST2_LANE_F16 : WInst<"vst2_lane", "v*(2!)I", "hQh">;
+def VST3_LANE_F16 : WInst<"vst3_lane", "v*(3!)I", "hQh">;
+def VST4_LANE_F16 : WInst<"vst4_lane", "v*(4!)I", "hQh">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.16 Extract lanes from a vector
 let InstName = "vmov" in
-def VGET_LANE : IInst<"vget_lane", "sdi",
+def VGET_LANE : IInst<"vget_lane", "1.I",
                       "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.17 Set lanes within a vector
 let InstName = "vmov" in
-def VSET_LANE : IInst<"vset_lane", "dsdi",
+def VSET_LANE : IInst<"vset_lane", ".1.I",
                       "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.18 Initialize a vector from bit pattern
-def VCREATE : NoTestOpInst<"vcreate", "dl", "csihfUcUsUiUlPcPsl", OP_CAST> {
+def VCREATE : NoTestOpInst<"vcreate", ".(IU>)", "csihfUcUsUiUlPcPsl", OP_CAST> {
   let BigEndianSafe = 1;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.19 Set all lanes to same value
 let InstName = "vmov" in {
-def VDUP_N   : WOpInst<"vdup_n", "ds",
+def VDUP_N   : WOpInst<"vdup_n", ".1",
                        "UcUsUicsiPcPshfQUcQUsQUiQcQsQiQPcQPsQhQflUlQlQUl",
                        OP_DUP>;
-def VMOV_N   : WOpInst<"vmov_n", "ds",
+def VMOV_N   : WOpInst<"vmov_n", ".1",
                        "UcUsUicsiPcPshfQUcQUsQUiQcQsQiQPcQPsQhQflUlQlQUl",
                        OP_DUP>;
 }
 let InstName = "" in
-def VDUP_LANE: WOpInst<"vdup_lane", "dgi",
+def VDUP_LANE: WOpInst<"vdup_lane", ".qI",
                        "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl",
                        OP_DUP_LN>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.20 Combining vectors
-def VCOMBINE : NoTestOpInst<"vcombine", "kdd", "csilhfUcUsUiUlPcPs", OP_CONC>;
+def VCOMBINE : NoTestOpInst<"vcombine", "Q..", "csilhfUcUsUiUlPcPs", OP_CONC>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.21 Splitting vectors
@@ -468,127 +469,127 @@ def VCOMBINE : NoTestOpInst<"vcombine", "kdd", "csilhfUcUsUiUlPcPs", OP_CONC>;
 // versions of these intrinsics in both AArch32 and AArch64 architectures. See
 // D45668 for more details.
 let InstName = "vmov" in {
-def VGET_HIGH : NoTestOpInst<"vget_high", "dk", "csilhfUcUsUiUlPcPs", OP_HI>;
-def VGET_LOW  : NoTestOpInst<"vget_low", "dk", "csilhfUcUsUiUlPcPs", OP_LO>;
+def VGET_HIGH : NoTestOpInst<"vget_high", ".Q", "csilhfUcUsUiUlPcPs", OP_HI>;
+def VGET_LOW  : NoTestOpInst<"vget_low", ".Q", "csilhfUcUsUiUlPcPs", OP_LO>;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.22 Converting vectors
 
 let ArchGuard = "(__ARM_FP & 2)" in {
-  def VCVT_F16_F32 : SInst<"vcvt_f16_f32", "md", "Hf">;
-  def VCVT_F32_F16 : SInst<"vcvt_f32_f16", "wd", "h">;
+  def VCVT_F16_F32 : SInst<"vcvt_f16_f32", "(<q)(.!)", "Hf">;
+  def VCVT_F32_F16 : SInst<"vcvt_f32_f16", "(>Q)(.!)", "h">;
 }
 
-def VCVT_S32     : SInst<"vcvt_s32", "xd",  "fQf">;
-def VCVT_U32     : SInst<"vcvt_u32", "ud",  "fQf">;
-def VCVT_F32     : SInst<"vcvt_f32", "fd",  "iUiQiQUi">;
+def VCVT_S32     : SInst<"vcvt_s32", "S.",  "fQf">;
+def VCVT_U32     : SInst<"vcvt_u32", "U.",  "fQf">;
+def VCVT_F32     : SInst<"vcvt_f32", "F(.!)",  "iUiQiQUi">;
 let isVCVT_N = 1 in {
-def VCVT_N_S32   : SInst<"vcvt_n_s32", "xdi", "fQf">;
-def VCVT_N_U32   : SInst<"vcvt_n_u32", "udi", "fQf">;
-def VCVT_N_F32   : SInst<"vcvt_n_f32", "fdi", "iUiQiQUi">;
+def VCVT_N_S32   : SInst<"vcvt_n_s32", "S.I", "fQf">;
+def VCVT_N_U32   : SInst<"vcvt_n_u32", "U.I", "fQf">;
+def VCVT_N_F32   : SInst<"vcvt_n_f32", "F(.!)I", "iUiQiQUi">;
 }
 
-def VMOVN        : IInst<"vmovn", "hk",  "silUsUiUl">;
-def VMOVL        : SInst<"vmovl", "wd",  "csiUcUsUi">;
-def VQMOVN       : SInst<"vqmovn", "hk",  "silUsUiUl">;
-def VQMOVUN      : SInst<"vqmovun", "ek",  "sil">;
+def VMOVN        : IInst<"vmovn", "<Q",  "silUsUiUl">;
+def VMOVL        : SInst<"vmovl", "(>Q).",  "csiUcUsUi">;
+def VQMOVN       : SInst<"vqmovn", "<Q",  "silUsUiUl">;
+def VQMOVUN      : SInst<"vqmovun", "(<U)Q",  "sil">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.23-24 Table lookup, Extended table lookup
 let InstName = "vtbl" in {
-def VTBL1 : WInst<"vtbl1", "ddt",  "UccPc">;
-def VTBL2 : WInst<"vtbl2", "d2t",  "UccPc">;
-def VTBL3 : WInst<"vtbl3", "d3t",  "UccPc">;
-def VTBL4 : WInst<"vtbl4", "d4t",  "UccPc">;
+def VTBL1 : WInst<"vtbl1", "..p",  "UccPc">;
+def VTBL2 : WInst<"vtbl2", ".2p",  "UccPc">;
+def VTBL3 : WInst<"vtbl3", ".3p",  "UccPc">;
+def VTBL4 : WInst<"vtbl4", ".4p",  "UccPc">;
 }
 let InstName = "vtbx" in {
-def VTBX1 : WInst<"vtbx1", "dddt", "UccPc">;
-def VTBX2 : WInst<"vtbx2", "dd2t", "UccPc">;
-def VTBX3 : WInst<"vtbx3", "dd3t", "UccPc">;
-def VTBX4 : WInst<"vtbx4", "dd4t", "UccPc">;
+def VTBX1 : WInst<"vtbx1", "...p", "UccPc">;
+def VTBX2 : WInst<"vtbx2", "..2p", "UccPc">;
+def VTBX3 : WInst<"vtbx3", "..3p", "UccPc">;
+def VTBX4 : WInst<"vtbx4", "..4p", "UccPc">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.25 Operations with a scalar value
-def VMLA_LANE     : IOpInst<"vmla_lane", "dddgi",
+def VMLA_LANE     : IOpInst<"vmla_lane", "...qI",
                             "siUsUifQsQiQUsQUiQf", OP_MLA_LN>;
-def VMLAL_LANE    : SOpInst<"vmlal_lane", "wwddi", "siUsUi", OP_MLAL_LN>;
-def VQDMLAL_LANE  : SOpInst<"vqdmlal_lane", "wwddi", "si", OP_QDMLAL_LN>;
-def VMLS_LANE     : IOpInst<"vmls_lane", "dddgi",
+def VMLAL_LANE    : SOpInst<"vmlal_lane", "(>Q)(>Q)..I", "siUsUi", OP_MLAL_LN>;
+def VQDMLAL_LANE  : SOpInst<"vqdmlal_lane", "(>Q)(>Q)..I", "si", OP_QDMLAL_LN>;
+def VMLS_LANE     : IOpInst<"vmls_lane", "...qI",
                             "siUsUifQsQiQUsQUiQf", OP_MLS_LN>;
-def VMLSL_LANE    : SOpInst<"vmlsl_lane", "wwddi", "siUsUi", OP_MLSL_LN>;
-def VQDMLSL_LANE  : SOpInst<"vqdmlsl_lane", "wwddi", "si", OP_QDMLSL_LN>;
-def VMUL_N        : IOpInst<"vmul_n", "dds", "sifUsUiQsQiQfQUsQUi", OP_MUL_N>;
-def VMUL_LANE     : IOpInst<"vmul_lane", "ddgi",
+def VMLSL_LANE    : SOpInst<"vmlsl_lane", "(>Q)(>Q)..I", "siUsUi", OP_MLSL_LN>;
+def VQDMLSL_LANE  : SOpInst<"vqdmlsl_lane", "(>Q)(>Q)..I", "si", OP_QDMLSL_LN>;
+def VMUL_N        : IOpInst<"vmul_n", "..1", "sifUsUiQsQiQfQUsQUi", OP_MUL_N>;
+def VMUL_LANE     : IOpInst<"vmul_lane", "..qI",
                             "sifUsUiQsQiQfQUsQUi", OP_MUL_LN>;
-def VMULL_N       : SOpInst<"vmull_n", "wds", "siUsUi", OP_MULL_N>;
-def VMULL_LANE    : SOpInst<"vmull_lane", "wddi", "siUsUi", OP_MULL_LN>;
-def VQDMULL_N     : SOpInst<"vqdmull_n", "wds", "si", OP_QDMULL_N>;
-def VQDMULL_LANE  : SOpInst<"vqdmull_lane", "wddi", "si", OP_QDMULL_LN>;
-def VQDMULH_N     : SOpInst<"vqdmulh_n", "dds", "siQsQi", OP_QDMULH_N>;
-def VQDMULH_LANE  : SOpInst<"vqdmulh_lane", "ddgi", "siQsQi", OP_QDMULH_LN>;
-def VQRDMULH_N    : SOpInst<"vqrdmulh_n", "dds", "siQsQi", OP_QRDMULH_N>;
-def VQRDMULH_LANE : SOpInst<"vqrdmulh_lane", "ddgi", "siQsQi", OP_QRDMULH_LN>;
+def VMULL_N       : SOpInst<"vmull_n", "(>Q).1", "siUsUi", OP_MULL_N>;
+def VMULL_LANE    : SOpInst<"vmull_lane", "(>Q)..I", "siUsUi", OP_MULL_LN>;
+def VQDMULL_N     : SOpInst<"vqdmull_n", "(>Q).1", "si", OP_QDMULL_N>;
+def VQDMULL_LANE  : SOpInst<"vqdmull_lane", "(>Q)..I", "si", OP_QDMULL_LN>;
+def VQDMULH_N     : SOpInst<"vqdmulh_n", "..1", "siQsQi", OP_QDMULH_N>;
+def VQDMULH_LANE  : SOpInst<"vqdmulh_lane", "..qI", "siQsQi", OP_QDMULH_LN>;
+def VQRDMULH_N    : SOpInst<"vqrdmulh_n", "..1", "siQsQi", OP_QRDMULH_N>;
+def VQRDMULH_LANE : SOpInst<"vqrdmulh_lane", "..qI", "siQsQi", OP_QRDMULH_LN>;
 
 let ArchGuard = "defined(__ARM_FEATURE_QRDMX)" in {
-def VQRDMLAH_LANE : SOpInst<"vqrdmlah_lane", "dddgi", "siQsQi", OP_QRDMLAH_LN>;
-def VQRDMLSH_LANE : SOpInst<"vqrdmlsh_lane", "dddgi", "siQsQi", OP_QRDMLSH_LN>;
+def VQRDMLAH_LANE : SOpInst<"vqrdmlah_lane", "...qI", "siQsQi", OP_QRDMLAH_LN>;
+def VQRDMLSH_LANE : SOpInst<"vqrdmlsh_lane", "...qI", "siQsQi", OP_QRDMLSH_LN>;
 }
 
-def VMLA_N        : IOpInst<"vmla_n", "ddds", "siUsUifQsQiQUsQUiQf", OP_MLA_N>;
-def VMLAL_N       : SOpInst<"vmlal_n", "wwds", "siUsUi", OP_MLAL_N>;
-def VQDMLAL_N     : SOpInst<"vqdmlal_n", "wwds", "si", OP_QDMLAL_N>;
-def VMLS_N        : IOpInst<"vmls_n", "ddds", "siUsUifQsQiQUsQUiQf", OP_MLS_N>;
-def VMLSL_N       : SOpInst<"vmlsl_n", "wwds", "siUsUi", OP_MLSL_N>;
-def VQDMLSL_N     : SOpInst<"vqdmlsl_n", "wwds", "si", OP_QDMLSL_N>;
+def VMLA_N        : IOpInst<"vmla_n", "...1", "siUsUifQsQiQUsQUiQf", OP_MLA_N>;
+def VMLAL_N       : SOpInst<"vmlal_n", "(>Q)(>Q).1", "siUsUi", OP_MLAL_N>;
+def VQDMLAL_N     : SOpInst<"vqdmlal_n", "(>Q)(>Q).1", "si", OP_QDMLAL_N>;
+def VMLS_N        : IOpInst<"vmls_n", "...1", "siUsUifQsQiQUsQUiQf", OP_MLS_N>;
+def VMLSL_N       : SOpInst<"vmlsl_n", "(>Q)(>Q).1", "siUsUi", OP_MLSL_N>;
+def VQDMLSL_N     : SOpInst<"vqdmlsl_n", "(>Q)(>Q).1", "si", OP_QDMLSL_N>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.26 Vector Extract
-def VEXT : WInst<"vext", "dddi",
+def VEXT : WInst<"vext", "...I",
                  "cUcPcsUsPsiUilUlfQcQUcQPcQsQUsQPsQiQUiQlQUlQf">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.27 Reverse vector elements
-def VREV64 : WOpInst<"vrev64", "dd", "csiUcUsUiPcPsfQcQsQiQUcQUsQUiQPcQPsQf",
+def VREV64 : WOpInst<"vrev64", "..", "csiUcUsUiPcPsfQcQsQiQUcQUsQUiQPcQPsQf",
                   OP_REV64>;
-def VREV32 : WOpInst<"vrev32", "dd", "csUcUsPcPsQcQsQUcQUsQPcQPs", OP_REV32>;
-def VREV16 : WOpInst<"vrev16", "dd", "cUcPcQcQUcQPc", OP_REV16>;
+def VREV32 : WOpInst<"vrev32", "..", "csUcUsPcPsQcQsQUcQUsQPcQPs", OP_REV32>;
+def VREV16 : WOpInst<"vrev16", "..", "cUcPcQcQUcQPc", OP_REV16>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.28 Other single operand arithmetic
-def VABS    : SInst<"vabs", "dd", "csifQcQsQiQf">;
-def VQABS   : SInst<"vqabs", "dd", "csiQcQsQi">;
-def VNEG    : SOpInst<"vneg", "dd", "csifQcQsQiQf", OP_NEG>;
-def VQNEG   : SInst<"vqneg", "dd", "csiQcQsQi">;
-def VCLS    : SInst<"vcls", "dd", "csiQcQsQi">;
-def VCLZ    : IInst<"vclz", "dd", "csiUcUsUiQcQsQiQUcQUsQUi">;
-def VCNT    : WInst<"vcnt", "dd", "UccPcQUcQcQPc">;
-def VRECPE  : SInst<"vrecpe", "dd", "fUiQfQUi">;
-def VRSQRTE : SInst<"vrsqrte", "dd", "fUiQfQUi">;
+def VABS    : SInst<"vabs", "..", "csifQcQsQiQf">;
+def VQABS   : SInst<"vqabs", "..", "csiQcQsQi">;
+def VNEG    : SOpInst<"vneg", "..", "csifQcQsQiQf", OP_NEG>;
+def VQNEG   : SInst<"vqneg", "..", "csiQcQsQi">;
+def VCLS    : SInst<"vcls", "..", "csiQcQsQi">;
+def VCLZ    : IInst<"vclz", "..", "csiUcUsUiQcQsQiQUcQUsQUi">;
+def VCNT    : WInst<"vcnt", "..", "UccPcQUcQcQPc">;
+def VRECPE  : SInst<"vrecpe", "..", "fUiQfQUi">;
+def VRSQRTE : SInst<"vrsqrte", "..", "fUiQfQUi">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.29 Logical operations
-def VMVN : LOpInst<"vmvn", "dd", "csiUcUsUiPcQcQsQiQUcQUsQUiQPc", OP_NOT>;
-def VAND : LOpInst<"vand", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_AND>;
-def VORR : LOpInst<"vorr", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_OR>;
-def VEOR : LOpInst<"veor", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_XOR>;
-def VBIC : LOpInst<"vbic", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_ANDN>;
-def VORN : LOpInst<"vorn", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_ORN>;
+def VMVN : LOpInst<"vmvn", "..", "csiUcUsUiPcQcQsQiQUcQUsQUiQPc", OP_NOT>;
+def VAND : LOpInst<"vand", "...", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_AND>;
+def VORR : LOpInst<"vorr", "...", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_OR>;
+def VEOR : LOpInst<"veor", "...", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_XOR>;
+def VBIC : LOpInst<"vbic", "...", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_ANDN>;
+def VORN : LOpInst<"vorn", "...", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_ORN>;
 let isHiddenLInst = 1 in
-def VBSL : SInst<"vbsl", "dudd",
+def VBSL : SInst<"vbsl", ".U..",
                 "csilUcUsUiUlfPcPsQcQsQiQlQUcQUsQUiQUlQfQPcQPs">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.30 Transposition operations
-def VTRN : WInst<"vtrn", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;
-def VZIP : WInst<"vzip", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;
-def VUZP : WInst<"vuzp", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;
+def VTRN : WInst<"vtrn", "2..", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;
+def VZIP : WInst<"vzip", "2..", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;
+def VUZP : WInst<"vuzp", "2..", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // E.3.31 Vector reinterpret cast operations
 def VREINTERPRET
-  : NoTestOpInst<"vreinterpret", "dd",
+  : NoTestOpInst<"vreinterpret", "..",
          "csilUcUsUiUlhfPcPsQcQsQiQlQUcQUsQUiQUlQhQfQPcQPs", OP_REINT> {
   let CartesianProductOfTypes = 1;
   let ArchGuard = "!defined(__aarch64__)";
@@ -599,17 +600,17 @@ def VREINTERPRET
 // Vector fused multiply-add operations
 
 let ArchGuard = "defined(__ARM_FEATURE_FMA)" in {
-  def VFMA : SInst<"vfma", "dddd", "fQf">;
-  def VFMS : SOpInst<"vfms", "dddd", "fQf", OP_FMLS>;
-  def FMLA_N_F32 : SOpInst<"vfma_n", "ddds", "fQf", OP_FMLA_N>;
+  def VFMA : SInst<"vfma", "....", "fQf">;
+  def VFMS : SOpInst<"vfms", "....", "fQf", OP_FMLS>;
+  def FMLA_N_F32 : SOpInst<"vfma_n", "...1", "fQf", OP_FMLA_N>;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // fp16 vector operations
-def SCALAR_HALF_GET_LANE : IOpInst<"vget_lane", "sdi", "h", OP_SCALAR_HALF_GET_LN>;
-def SCALAR_HALF_SET_LANE : IOpInst<"vset_lane", "dsdi", "h", OP_SCALAR_HALF_SET_LN>;
-def SCALAR_HALF_GET_LANEQ : IOpInst<"vget_lane", "sdi", "Qh", OP_SCALAR_HALF_GET_LNQ>;
-def SCALAR_HALF_SET_LANEQ : IOpInst<"vset_lane", "dsdi", "Qh", OP_SCALAR_HALF_SET_LNQ>;
+def SCALAR_HALF_GET_LANE : IOpInst<"vget_lane", "1.I", "h", OP_SCALAR_HALF_GET_LN>;
+def SCALAR_HALF_SET_LANE : IOpInst<"vset_lane", ".1.I", "h", OP_SCALAR_HALF_SET_LN>;
+def SCALAR_HALF_GET_LANEQ : IOpInst<"vget_lane", "1.I", "Qh", OP_SCALAR_HALF_GET_LNQ>;
+def SCALAR_HALF_SET_LANEQ : IOpInst<"vset_lane", ".1.I", "Qh", OP_SCALAR_HALF_SET_LNQ>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // AArch64 Intrinsics
@@ -618,474 +619,474 @@ let ArchGuard = "defined(__aarch64__)" in {
 
 ////////////////////////////////////////////////////////////////////////////////
 // Load/Store
-def LD1 : WInst<"vld1", "dc", "dQdPlQPl">;
-def LD2 : WInst<"vld2", "2c", "QUlQldQdPlQPl">;
-def LD3 : WInst<"vld3", "3c", "QUlQldQdPlQPl">;
-def LD4 : WInst<"vld4", "4c", "QUlQldQdPlQPl">;
-def ST1 : WInst<"vst1", "vpd", "dQdPlQPl">;
-def ST2 : WInst<"vst2", "vp2", "QUlQldQdPlQPl">;
-def ST3 : WInst<"vst3", "vp3", "QUlQldQdPlQPl">;
-def ST4 : WInst<"vst4", "vp4", "QUlQldQdPlQPl">;
-
-def LD1_X2 : WInst<"vld1_x2", "2c",
+def LD1 : WInst<"vld1", ".(c*!)", "dQdPlQPl">;
+def LD2 : WInst<"vld2", "2(c*!)", "QUlQldQdPlQPl">;
+def LD3 : WInst<"vld3", "3(c*!)", "QUlQldQdPlQPl">;
+def LD4 : WInst<"vld4", "4(c*!)", "QUlQldQdPlQPl">;
+def ST1 : WInst<"vst1", "v*(.!)", "dQdPlQPl">;
+def ST2 : WInst<"vst2", "v*(2!)", "QUlQldQdPlQPl">;
+def ST3 : WInst<"vst3", "v*(3!)", "QUlQldQdPlQPl">;
+def ST4 : WInst<"vst4", "v*(4!)", "QUlQldQdPlQPl">;
+
+def LD1_X2 : WInst<"vld1_x2", "2(c*!)",
                    "dQdPlQPl">;
-def LD1_X3 : WInst<"vld1_x3", "3c",
+def LD1_X3 : WInst<"vld1_x3", "3(c*!)",
                    "dQdPlQPl">;
-def LD1_X4 : WInst<"vld1_x4", "4c",
+def LD1_X4 : WInst<"vld1_x4", "4(c*!)",
                    "dQdPlQPl">;
 
-def ST1_X2 : WInst<"vst1_x2", "vp2", "dQdPlQPl">;
-def ST1_X3 : WInst<"vst1_x3", "vp3", "dQdPlQPl">;
-def ST1_X4 : WInst<"vst1_x4", "vp4", "dQdPlQPl">;
+def ST1_X2 : WInst<"vst1_x2", "v*(2!)", "dQdPlQPl">;
+def ST1_X3 : WInst<"vst1_x3", "v*(3!)", "dQdPlQPl">;
+def ST1_X4 : WInst<"vst1_x4", "v*(4!)", "dQdPlQPl">;
 
-def LD1_LANE : WInst<"vld1_lane", "dcdi", "dQdPlQPl">;
-def LD2_LANE : WInst<"vld2_lane", "2c2i", "lUlQcQUcQPcQlQUldQdPlQPl">;
-def LD3_LANE : WInst<"vld3_lane", "3c3i", "lUlQcQUcQPcQlQUldQdPlQPl">;
-def LD4_LANE : WInst<"vld4_lane", "4c4i", "lUlQcQUcQPcQlQUldQdPlQPl">;
-def ST1_LANE : WInst<"vst1_lane", "vpdi", "dQdPlQPl">;
-def ST2_LANE : WInst<"vst2_lane", "vp2i", "lUlQcQUcQPcQlQUldQdPlQPl">;
-def ST3_LANE : WInst<"vst3_lane", "vp3i", "lUlQcQUcQPcQlQUldQdPlQPl">;
-def ST4_LANE : WInst<"vst4_lane", "vp4i", "lUlQcQUcQPcQlQUldQdPlQPl">;
+def LD1_LANE : WInst<"vld1_lane", ".(c*!).I", "dQdPlQPl">;
+def LD2_LANE : WInst<"vld2_lane", "2(c*!)2I", "lUlQcQUcQPcQlQUldQdPlQPl">;
+def LD3_LANE : WInst<"vld3_lane", "3(c*!)3I", "lUlQcQUcQPcQlQUldQdPlQPl">;
+def LD4_LANE : WInst<"vld4_lane", "4(c*!)4I", "lUlQcQUcQPcQlQUldQdPlQPl">;
+def ST1_LANE : WInst<"vst1_lane", "v*(.!)I", "dQdPlQPl">;
+def ST2_LANE : WInst<"vst2_lane", "v*(2!)I", "lUlQcQUcQPcQlQUldQdPlQPl">;
+def ST3_LANE : WInst<"vst3_lane", "v*(3!)I", "lUlQcQUcQPcQlQUldQdPlQPl">;
+def ST4_LANE : WInst<"vst4_lane", "v*(4!)I", "lUlQcQUcQPcQlQUldQdPlQPl">;
 
-def LD1_DUP  : WInst<"vld1_dup", "dc", "dQdPlQPl">;
-def LD2_DUP  : WInst<"vld2_dup", "2c", "dQdPlQPl">;
-def LD3_DUP  : WInst<"vld3_dup", "3c", "dQdPlQPl">;
-def LD4_DUP  : WInst<"vld4_dup", "4c", "dQdPlQPl">;
+def LD1_DUP  : WInst<"vld1_dup", ".(c*!)", "dQdPlQPl">;
+def LD2_DUP  : WInst<"vld2_dup", "2(c*!)", "dQdPlQPl">;
+def LD3_DUP  : WInst<"vld3_dup", "3(c*!)", "dQdPlQPl">;
+def LD4_DUP  : WInst<"vld4_dup", "4(c*!)", "dQdPlQPl">;
 
-def VLDRQ : WInst<"vldrq", "sc", "Pk">;
-def VSTRQ : WInst<"vstrq", "vps", "Pk">;
+def VLDRQ : WInst<"vldrq", "1(c*!)", "Pk">;
+def VSTRQ : WInst<"vstrq", "v*(1!)", "Pk">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Addition
-def ADD : IOpInst<"vadd", "ddd", "dQd", OP_ADD>;
+def ADD : IOpInst<"vadd", "...", "dQd", OP_ADD>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Subtraction
-def SUB : IOpInst<"vsub", "ddd", "dQd", OP_SUB>;
+def SUB : IOpInst<"vsub", "...", "dQd", OP_SUB>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Multiplication
-def MUL     : IOpInst<"vmul", "ddd", "dQd", OP_MUL>;
-def MLA     : IOpInst<"vmla", "dddd", "dQd", OP_MLA>;
-def MLS     : IOpInst<"vmls", "dddd", "dQd", OP_MLS>;
+def MUL     : IOpInst<"vmul", "...", "dQd", OP_MUL>;
+def MLA     : IOpInst<"vmla", "....", "dQd", OP_MLA>;
+def MLS     : IOpInst<"vmls", "....", "dQd", OP_MLS>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Multiplication Extended
-def MULX : SInst<"vmulx", "ddd", "fdQfQd">;
+def MULX : SInst<"vmulx", "...", "fdQfQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Division
-def FDIV : IOpInst<"vdiv", "ddd",  "fdQfQd", OP_DIV>;
+def FDIV : IOpInst<"vdiv", "...",  "fdQfQd", OP_DIV>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Vector fused multiply-add operations
-def FMLA : SInst<"vfma", "dddd", "dQd">;
-def FMLS : SOpInst<"vfms", "dddd", "dQd", OP_FMLS>;
+def FMLA : SInst<"vfma", "....", "dQd">;
+def FMLS : SOpInst<"vfms", "....", "dQd", OP_FMLS>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // MUL, MLA, MLS, FMA, FMS definitions with scalar argument
-def VMUL_N_A64 : IOpInst<"vmul_n", "dds", "Qd", OP_MUL_N>;
+def VMUL_N_A64 : IOpInst<"vmul_n", "..1", "Qd", OP_MUL_N>;
 
-def FMLA_N : SOpInst<"vfma_n", "ddds", "dQd", OP_FMLA_N>;
-def FMLS_N : SOpInst<"vfms_n", "ddds", "fdQfQd", OP_FMLS_N>;
+def FMLA_N : SOpInst<"vfma_n", "...1", "dQd", OP_FMLA_N>;
+def FMLS_N : SOpInst<"vfms_n", "...1", "fdQfQd", OP_FMLS_N>;
 
-def MLA_N : SOpInst<"vmla_n", "ddds", "Qd", OP_MLA_N>;
-def MLS_N : SOpInst<"vmls_n", "ddds", "Qd", OP_MLS_N>;
+def MLA_N : SOpInst<"vmla_n", "...1", "Qd", OP_MLA_N>;
+def MLS_N : SOpInst<"vmls_n", "...1", "Qd", OP_MLS_N>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Logical operations
-def BSL : SInst<"vbsl", "dudd", "dPlQdQPl">;
+def BSL : SInst<"vbsl", ".U..", "dPlQdQPl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Absolute Difference
-def ABD  : SInst<"vabd", "ddd",  "dQd">;
+def ABD  : SInst<"vabd", "...",  "dQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // saturating absolute/negate
-def ABS    : SInst<"vabs", "dd", "dQdlQl">;
-def QABS   : SInst<"vqabs", "dd", "lQl">;
-def NEG    : SOpInst<"vneg", "dd", "dlQdQl", OP_NEG>;
-def QNEG   : SInst<"vqneg", "dd", "lQl">;
+def ABS    : SInst<"vabs", "..", "dQdlQl">;
+def QABS   : SInst<"vqabs", "..", "lQl">;
+def NEG    : SOpInst<"vneg", "..", "dlQdQl", OP_NEG>;
+def QNEG   : SInst<"vqneg", "..", "lQl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Signed Saturating Accumulated of Unsigned Value
-def SUQADD : SInst<"vuqadd", "ddu", "csilQcQsQiQl">;
+def SUQADD : SInst<"vuqadd", "..U", "csilQcQsQiQl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Unsigned Saturating Accumulated of Signed Value
-def USQADD : SInst<"vsqadd", "ddx", "UcUsUiUlQUcQUsQUiQUl">;
+def USQADD : SInst<"vsqadd", "..S", "UcUsUiUlQUcQUsQUiQUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Reciprocal/Sqrt
-def FRECPS  : IInst<"vrecps", "ddd", "dQd">;
-def FRSQRTS : IInst<"vrsqrts", "ddd", "dQd">;
-def FRECPE  : SInst<"vrecpe", "dd", "dQd">;
-def FRSQRTE : SInst<"vrsqrte", "dd", "dQd">;
-def FSQRT   : SInst<"vsqrt", "dd", "fdQfQd">;
+def FRECPS  : IInst<"vrecps", "...", "dQd">;
+def FRSQRTS : IInst<"vrsqrts", "...", "dQd">;
+def FRECPE  : SInst<"vrecpe", "..", "dQd">;
+def FRSQRTE : SInst<"vrsqrte", "..", "dQd">;
+def FSQRT   : SInst<"vsqrt", "..", "fdQfQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // bitwise reverse
-def RBIT : IInst<"vrbit", "dd", "cUcPcQcQUcQPc">;
+def RBIT : IInst<"vrbit", "..", "cUcPcQcQUcQPc">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Integer extract and narrow to high
-def XTN2 : SOpInst<"vmovn_high", "qhk", "silUsUiUl", OP_XTN>;
+def XTN2 : SOpInst<"vmovn_high", "(<Q)<Q", "silUsUiUl", OP_XTN>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Signed integer saturating extract and unsigned narrow to high
-def SQXTUN2 : SOpInst<"vqmovun_high", "emd", "HsHiHl", OP_SQXTUN>;
+def SQXTUN2 : SOpInst<"vqmovun_high", "(<U)(<q).", "HsHiHl", OP_SQXTUN>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Integer saturating extract and narrow to high
-def QXTN2 : SOpInst<"vqmovn_high", "qhk", "silUsUiUl", OP_QXTN>;
+def QXTN2 : SOpInst<"vqmovn_high", "(<Q)<Q", "silUsUiUl", OP_QXTN>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Converting vectors
 
-def VCVT_F32_F64 : SInst<"vcvt_f32_f64", "md", "Qd">;
-def VCVT_F64_F32 : SInst<"vcvt_f64_f32", "wd", "f">;
+def VCVT_F32_F64 : SInst<"vcvt_f32_f64", "(<q).", "Qd">;
+def VCVT_F64_F32 : SInst<"vcvt_f64_f32", "(>Q).", "f">;
 
-def VCVT_S64 : SInst<"vcvt_s64", "xd",  "dQd">;
-def VCVT_U64 : SInst<"vcvt_u64", "ud",  "dQd">;
-def VCVT_F64 : SInst<"vcvt_f64", "Fd",  "lUlQlQUl">;
+def VCVT_S64 : SInst<"vcvt_s64", "S.",  "dQd">;
+def VCVT_U64 : SInst<"vcvt_u64", "U.",  "dQd">;
+def VCVT_F64 : SInst<"vcvt_f64", "F(.!)",  "lUlQlQUl">;
 
-def VCVT_HIGH_F16_F32 : SOpInst<"vcvt_high_f16", "hmj", "Hf", OP_VCVT_NA_HI_F16>;
-def VCVT_HIGH_F32_F16 : SOpInst<"vcvt_high_f32", "wk", "h", OP_VCVT_EX_HI_F32>;
-def VCVT_HIGH_F32_F64 : SOpInst<"vcvt_high_f32", "qfj", "d", OP_VCVT_NA_HI_F32>;
-def VCVT_HIGH_F64_F32 : SOpInst<"vcvt_high_f64", "wj", "f", OP_VCVT_EX_HI_F64>;
+def VCVT_HIGH_F16_F32 : SOpInst<"vcvt_high_f16", "<(<q!)Q", "Hf", OP_VCVT_NA_HI_F16>;
+def VCVT_HIGH_F32_F16 : SOpInst<"vcvt_high_f32", "(>Q)(Q!)", "h", OP_VCVT_EX_HI_F32>;
+def VCVT_HIGH_F32_F64 : SOpInst<"vcvt_high_f32", "(<Q)(F<!)Q", "d", OP_VCVT_NA_HI_F32>;
+def VCVT_HIGH_F64_F32 : SOpInst<"vcvt_high_f64", "(>Q)(Q!)", "f", OP_VCVT_EX_HI_F64>;
 
-def VCVTX_F32_F64      : SInst<"vcvtx_f32", "fj",  "d">;
-def VCVTX_HIGH_F32_F64 : SOpInst<"vcvtx_high_f32", "qfj", "d", OP_VCVTX_HI>;
+def VCVTX_F32_F64      : SInst<"vcvtx_f32", "(F<)(Q!)",  "d">;
+def VCVTX_HIGH_F32_F64 : SOpInst<"vcvtx_high_f32", "(<Q)(F<!)Q", "d", OP_VCVTX_HI>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Comparison
-def FCAGE : IInst<"vcage", "udd", "dQd">;
-def FCAGT : IInst<"vcagt", "udd", "dQd">;
-def FCALE : IInst<"vcale", "udd", "dQd">;
-def FCALT : IInst<"vcalt", "udd", "dQd">;
-def CMTST  : WInst<"vtst", "udd", "lUlPlQlQUlQPl">;
-def CFMEQ  : SOpInst<"vceq", "udd", "lUldQdQlQUlPlQPl", OP_EQ>;
-def CFMGE  : SOpInst<"vcge", "udd", "lUldQdQlQUl", OP_GE>;
-def CFMLE  : SOpInst<"vcle", "udd", "lUldQdQlQUl", OP_LE>;
-def CFMGT  : SOpInst<"vcgt", "udd", "lUldQdQlQUl", OP_GT>;
-def CFMLT  : SOpInst<"vclt", "udd", "lUldQdQlQUl", OP_LT>;
-
-def CMEQ  : SInst<"vceqz", "ud",
+def FCAGE : IInst<"vcage", "U..", "dQd">;
+def FCAGT : IInst<"vcagt", "U..", "dQd">;
+def FCALE : IInst<"vcale", "U..", "dQd">;
+def FCALT : IInst<"vcalt", "U..", "dQd">;
+def CMTST  : WInst<"vtst", "U..", "lUlPlQlQUlQPl">;
+def CFMEQ  : SOpInst<"vceq", "U..", "lUldQdQlQUlPlQPl", OP_EQ>;
+def CFMGE  : SOpInst<"vcge", "U..", "lUldQdQlQUl", OP_GE>;
+def CFMLE  : SOpInst<"vcle", "U..", "lUldQdQlQUl", OP_LE>;
+def CFMGT  : SOpInst<"vcgt", "U..", "lUldQdQlQUl", OP_GT>;
+def CFMLT  : SOpInst<"vclt", "U..", "lUldQdQlQUl", OP_LT>;
+
+def CMEQ  : SInst<"vceqz", "U.",
                   "csilfUcUsUiUlPcPsPlQcQsQiQlQfQUcQUsQUiQUlQPcQPsdQdQPl">;
-def CMGE  : SInst<"vcgez", "ud", "csilfdQcQsQiQlQfQd">;
-def CMLE  : SInst<"vclez", "ud", "csilfdQcQsQiQlQfQd">;
-def CMGT  : SInst<"vcgtz", "ud", "csilfdQcQsQiQlQfQd">;
-def CMLT  : SInst<"vcltz", "ud", "csilfdQcQsQiQlQfQd">;
+def CMGE  : SInst<"vcgez", "U.", "csilfdQcQsQiQlQfQd">;
+def CMLE  : SInst<"vclez", "U.", "csilfdQcQsQiQlQfQd">;
+def CMGT  : SInst<"vcgtz", "U.", "csilfdQcQsQiQlQfQd">;
+def CMLT  : SInst<"vcltz", "U.", "csilfdQcQsQiQlQfQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Max/Min Integer
-def MAX : SInst<"vmax", "ddd", "dQd">;
-def MIN : SInst<"vmin", "ddd", "dQd">;
+def MAX : SInst<"vmax", "...", "dQd">;
+def MIN : SInst<"vmin", "...", "dQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Pairwise Max/Min
-def MAXP : SInst<"vpmax", "ddd", "QcQsQiQUcQUsQUiQfQd">;
-def MINP : SInst<"vpmin", "ddd", "QcQsQiQUcQUsQUiQfQd">;
+def MAXP : SInst<"vpmax", "...", "QcQsQiQUcQUsQUiQfQd">;
+def MINP : SInst<"vpmin", "...", "QcQsQiQUcQUsQUiQfQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Pairwise MaxNum/MinNum Floating Point
-def FMAXNMP : SInst<"vpmaxnm", "ddd", "fQfQd">;
-def FMINNMP : SInst<"vpminnm", "ddd", "fQfQd">;
+def FMAXNMP : SInst<"vpmaxnm", "...", "fQfQd">;
+def FMINNMP : SInst<"vpminnm", "...", "fQfQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Pairwise Addition
-def ADDP  : IInst<"vpadd", "ddd", "QcQsQiQlQUcQUsQUiQUlQfQd">;
+def ADDP  : IInst<"vpadd", "...", "QcQsQiQlQUcQUsQUiQUlQfQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Shifts by constant
 let isShift = 1 in {
 // Left shift long high
-def SHLL_HIGH_N    : SOpInst<"vshll_high_n", "ndi", "HcHsHiHUcHUsHUi",
+def SHLL_HIGH_N    : SOpInst<"vshll_high_n", ">.I", "HcHsHiHUcHUsHUi",
                              OP_LONG_HI>;
 
 ////////////////////////////////////////////////////////////////////////////////
-def SRI_N : WInst<"vsri_n", "dddi", "PlQPl">;
-def SLI_N : WInst<"vsli_n", "dddi", "PlQPl">;
+def SRI_N : WInst<"vsri_n", "...I", "PlQPl">;
+def SLI_N : WInst<"vsli_n", "...I", "PlQPl">;
 
 // Right shift narrow high
-def SHRN_HIGH_N    : IOpInst<"vshrn_high_n", "hmdi",
+def SHRN_HIGH_N    : IOpInst<"vshrn_high_n", "<(<q).I",
                              "HsHiHlHUsHUiHUl", OP_NARROW_HI>;
-def QSHRUN_HIGH_N  : SOpInst<"vqshrun_high_n", "hmdi",
+def QSHRUN_HIGH_N  : SOpInst<"vqshrun_high_n", "<(<q).I",
                              "HsHiHl", OP_NARROW_HI>;
-def RSHRN_HIGH_N   : IOpInst<"vrshrn_high_n", "hmdi",
+def RSHRN_HIGH_N   : IOpInst<"vrshrn_high_n", "<(<q).I",
                              "HsHiHlHUsHUiHUl", OP_NARROW_HI>;
-def QRSHRUN_HIGH_N : SOpInst<"vqrshrun_high_n", "hmdi",
+def QRSHRUN_HIGH_N : SOpInst<"vqrshrun_high_n", "<(<q).I",
                              "HsHiHl", OP_NARROW_HI>;
-def QSHRN_HIGH_N   : SOpInst<"vqshrn_high_n", "hmdi",
+def QSHRN_HIGH_N   : SOpInst<"vqshrn_high_n", "<(<q).I",
                              "HsHiHlHUsHUiHUl", OP_NARROW_HI>;
-def QRSHRN_HIGH_N  : SOpInst<"vqrshrn_high_n", "hmdi",
+def QRSHRN_HIGH_N  : SOpInst<"vqrshrn_high_n", "<(<q).I",
                              "HsHiHlHUsHUiHUl", OP_NARROW_HI>;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Converting vectors
-def VMOVL_HIGH   : SOpInst<"vmovl_high", "nd", "HcHsHiHUcHUsHUi", OP_MOVL_HI>;
+def VMOVL_HIGH   : SOpInst<"vmovl_high", ">.", "HcHsHiHUcHUsHUi", OP_MOVL_HI>;
 
 let isVCVT_N = 1 in {
-def CVTF_N_F64   : SInst<"vcvt_n_f64", "Fdi", "lUlQlQUl">;
-def FCVTZS_N_S64 : SInst<"vcvt_n_s64", "xdi", "dQd">;
-def FCVTZS_N_U64 : SInst<"vcvt_n_u64", "udi", "dQd">;
+def CVTF_N_F64   : SInst<"vcvt_n_f64", "F(.!)I", "lUlQlQUl">;
+def FCVTZS_N_S64 : SInst<"vcvt_n_s64", "S.I", "dQd">;
+def FCVTZS_N_U64 : SInst<"vcvt_n_u64", "U.I", "dQd">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // 3VDiff class using high 64-bit in operands
-def VADDL_HIGH   : SOpInst<"vaddl_high", "wkk", "csiUcUsUi", OP_ADDLHi>;
-def VADDW_HIGH   : SOpInst<"vaddw_high", "wwk", "csiUcUsUi", OP_ADDWHi>;
-def VSUBL_HIGH   : SOpInst<"vsubl_high", "wkk", "csiUcUsUi", OP_SUBLHi>;
-def VSUBW_HIGH   : SOpInst<"vsubw_high", "wwk", "csiUcUsUi", OP_SUBWHi>;
+def VADDL_HIGH   : SOpInst<"vaddl_high", "(>Q)QQ", "csiUcUsUi", OP_ADDLHi>;
+def VADDW_HIGH   : SOpInst<"vaddw_high", "(>Q)(>Q)Q", "csiUcUsUi", OP_ADDWHi>;
+def VSUBL_HIGH   : SOpInst<"vsubl_high", "(>Q)QQ", "csiUcUsUi", OP_SUBLHi>;
+def VSUBW_HIGH   : SOpInst<"vsubw_high", "(>Q)(>Q)Q", "csiUcUsUi", OP_SUBWHi>;
 
-def VABDL_HIGH   : SOpInst<"vabdl_high", "wkk",  "csiUcUsUi", OP_ABDLHi>;
-def VABAL_HIGH   : SOpInst<"vabal_high", "wwkk", "csiUcUsUi", OP_ABALHi>;
+def VABDL_HIGH   : SOpInst<"vabdl_high", "(>Q)QQ",  "csiUcUsUi", OP_ABDLHi>;
+def VABAL_HIGH   : SOpInst<"vabal_high", "(>Q)(>Q)QQ", "csiUcUsUi", OP_ABALHi>;
 
-def VMULL_HIGH   : SOpInst<"vmull_high", "wkk", "csiUcUsUiPc", OP_MULLHi>;
-def VMULL_HIGH_N : SOpInst<"vmull_high_n", "wks", "siUsUi", OP_MULLHi_N>;
-def VMLAL_HIGH   : SOpInst<"vmlal_high", "wwkk", "csiUcUsUi", OP_MLALHi>;
-def VMLAL_HIGH_N : SOpInst<"vmlal_high_n", "wwks", "siUsUi", OP_MLALHi_N>;
-def VMLSL_HIGH   : SOpInst<"vmlsl_high", "wwkk", "csiUcUsUi", OP_MLSLHi>;
-def VMLSL_HIGH_N : SOpInst<"vmlsl_high_n", "wwks", "siUsUi", OP_MLSLHi_N>;
+def VMULL_HIGH   : SOpInst<"vmull_high", "(>Q)QQ", "csiUcUsUiPc", OP_MULLHi>;
+def VMULL_HIGH_N : SOpInst<"vmull_high_n", "(>Q)Q1", "siUsUi", OP_MULLHi_N>;
+def VMLAL_HIGH   : SOpInst<"vmlal_high", "(>Q)(>Q)QQ", "csiUcUsUi", OP_MLALHi>;
+def VMLAL_HIGH_N : SOpInst<"vmlal_high_n", "(>Q)(>Q)Q1", "siUsUi", OP_MLALHi_N>;
+def VMLSL_HIGH   : SOpInst<"vmlsl_high", "(>Q)(>Q)QQ", "csiUcUsUi", OP_MLSLHi>;
+def VMLSL_HIGH_N : SOpInst<"vmlsl_high_n", "(>Q)(>Q)Q1", "siUsUi", OP_MLSLHi_N>;
 
-def VADDHN_HIGH  : SOpInst<"vaddhn_high", "qhkk", "silUsUiUl", OP_ADDHNHi>;
-def VRADDHN_HIGH : SOpInst<"vraddhn_high", "qhkk", "silUsUiUl", OP_RADDHNHi>;
-def VSUBHN_HIGH  : SOpInst<"vsubhn_high", "qhkk", "silUsUiUl", OP_SUBHNHi>;
-def VRSUBHN_HIGH : SOpInst<"vrsubhn_high", "qhkk", "silUsUiUl", OP_RSUBHNHi>;
+def VADDHN_HIGH  : SOpInst<"vaddhn_high", "(<Q)<QQ", "silUsUiUl", OP_ADDHNHi>;
+def VRADDHN_HIGH : SOpInst<"vraddhn_high", "(<Q)<QQ", "silUsUiUl", OP_RADDHNHi>;
+def VSUBHN_HIGH  : SOpInst<"vsubhn_high", "(<Q)<QQ", "silUsUiUl", OP_SUBHNHi>;
+def VRSUBHN_HIGH : SOpInst<"vrsubhn_high", "(<Q)<QQ", "silUsUiUl", OP_RSUBHNHi>;
 
-def VQDMULL_HIGH : SOpInst<"vqdmull_high", "wkk", "si", OP_QDMULLHi>;
-def VQDMULL_HIGH_N : SOpInst<"vqdmull_high_n", "wks", "si", OP_QDMULLHi_N>;
-def VQDMLAL_HIGH : SOpInst<"vqdmlal_high", "wwkk", "si", OP_QDMLALHi>;
-def VQDMLAL_HIGH_N : SOpInst<"vqdmlal_high_n", "wwks", "si", OP_QDMLALHi_N>;
-def VQDMLSL_HIGH : SOpInst<"vqdmlsl_high", "wwkk", "si", OP_QDMLSLHi>;
-def VQDMLSL_HIGH_N : SOpInst<"vqdmlsl_high_n", "wwks", "si", OP_QDMLSLHi_N>;
-def VMULL_P64    : SInst<"vmull", "rss", "Pl">;
-def VMULL_HIGH_P64 : SOpInst<"vmull_high", "rdd", "HPl", OP_MULLHi_P64>;
+def VQDMULL_HIGH : SOpInst<"vqdmull_high", "(>Q)QQ", "si", OP_QDMULLHi>;
+def VQDMULL_HIGH_N : SOpInst<"vqdmull_high_n", "(>Q)Q1", "si", OP_QDMULLHi_N>;
+def VQDMLAL_HIGH : SOpInst<"vqdmlal_high", "(>Q)(>Q)QQ", "si", OP_QDMLALHi>;
+def VQDMLAL_HIGH_N : SOpInst<"vqdmlal_high_n", "(>Q)(>Q)Q1", "si", OP_QDMLALHi_N>;
+def VQDMLSL_HIGH : SOpInst<"vqdmlsl_high", "(>Q)(>Q)QQ", "si", OP_QDMLSLHi>;
+def VQDMLSL_HIGH_N : SOpInst<"vqdmlsl_high_n", "(>Q)(>Q)Q1", "si", OP_QDMLSLHi_N>;
+def VMULL_P64    : SInst<"vmull", "(1>)11", "Pl">;
+def VMULL_HIGH_P64 : SOpInst<"vmull_high", "(1>)..", "HPl", OP_MULLHi_P64>;
 
 
 ////////////////////////////////////////////////////////////////////////////////
 // Extract or insert element from vector
-def GET_LANE : IInst<"vget_lane", "sdi", "dQdPlQPl">;
-def SET_LANE : IInst<"vset_lane", "dsdi", "dQdPlQPl">;
-def COPY_LANE : IOpInst<"vcopy_lane", "ddidi",
+def GET_LANE : IInst<"vget_lane", "1.I", "dQdPlQPl">;
+def SET_LANE : IInst<"vset_lane", ".1.I", "dQdPlQPl">;
+def COPY_LANE : IOpInst<"vcopy_lane", "..I.I",
                         "csilUcUsUiUlPcPsPlfd", OP_COPY_LN>;
-def COPYQ_LANE : IOpInst<"vcopy_lane", "ddigi",
+def COPYQ_LANE : IOpInst<"vcopy_lane", "..IqI",
                         "QcQsQiQlQUcQUsQUiQUlQPcQPsQfQdQPl", OP_COPY_LN>;
-def COPY_LANEQ : IOpInst<"vcopy_laneq", "ddiki",
+def COPY_LANEQ : IOpInst<"vcopy_laneq", "..IQI",
                      "csilPcPsPlUcUsUiUlfd", OP_COPY_LN>;
-def COPYQ_LANEQ : IOpInst<"vcopy_laneq", "ddidi",
+def COPYQ_LANEQ : IOpInst<"vcopy_laneq", "..I.I",
                      "QcQsQiQlQUcQUsQUiQUlQPcQPsQfQdQPl", OP_COPY_LN>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Set all lanes to same value
-def VDUP_LANE1: WOpInst<"vdup_lane", "dgi", "hdQhQdPlQPl", OP_DUP_LN>;
-def VDUP_LANE2: WOpInst<"vdup_laneq", "dji",
+def VDUP_LANE1: WOpInst<"vdup_lane", ".qI", "hdQhQdPlQPl", OP_DUP_LN>;
+def VDUP_LANE2: WOpInst<"vdup_laneq", ".QI",
                   "csilUcUsUiUlPcPshfdQcQsQiQlQPcQPsQUcQUsQUiQUlQhQfQdPlQPl",
                         OP_DUP_LN>;
-def DUP_N   : WOpInst<"vdup_n", "ds", "dQdPlQPl", OP_DUP>;
-def MOV_N   : WOpInst<"vmov_n", "ds", "dQdPlQPl", OP_DUP>;
+def DUP_N   : WOpInst<"vdup_n", ".1", "dQdPlQPl", OP_DUP>;
+def MOV_N   : WOpInst<"vmov_n", ".1", "dQdPlQPl", OP_DUP>;
 
 ////////////////////////////////////////////////////////////////////////////////
-def COMBINE : NoTestOpInst<"vcombine", "kdd", "dPl", OP_CONC>;
+def COMBINE : NoTestOpInst<"vcombine", "Q..", "dPl", OP_CONC>;
 
 ////////////////////////////////////////////////////////////////////////////////
 //Initialize a vector from bit pattern
-def CREATE : NoTestOpInst<"vcreate", "dl", "dPl", OP_CAST> {
+def CREATE : NoTestOpInst<"vcreate", ".(IU>)", "dPl", OP_CAST> {
   let BigEndianSafe = 1;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 
-def VMLA_LANEQ   : IOpInst<"vmla_laneq", "dddji",
+def VMLA_LANEQ   : IOpInst<"vmla_laneq", "...QI",
                            "siUsUifQsQiQUsQUiQf", OP_MLA_LN>;
-def VMLS_LANEQ   : IOpInst<"vmls_laneq", "dddji",
+def VMLS_LANEQ   : IOpInst<"vmls_laneq", "...QI",
                            "siUsUifQsQiQUsQUiQf", OP_MLS_LN>;
 
-def VFMA_LANE    : IInst<"vfma_lane", "dddgi", "fdQfQd">;
-def VFMA_LANEQ   : IInst<"vfma_laneq", "dddji", "fdQfQd"> {
+def VFMA_LANE    : IInst<"vfma_lane", "...qI", "fdQfQd">;
+def VFMA_LANEQ   : IInst<"vfma_laneq", "...QI", "fdQfQd"> {
   let isLaneQ = 1;
 }
-def VFMS_LANE    : IOpInst<"vfms_lane", "dddgi", "fdQfQd", OP_FMS_LN>;
-def VFMS_LANEQ   : IOpInst<"vfms_laneq", "dddji", "fdQfQd", OP_FMS_LNQ>;
+def VFMS_LANE    : IOpInst<"vfms_lane", "...qI", "fdQfQd", OP_FMS_LN>;
+def VFMS_LANEQ   : IOpInst<"vfms_laneq", "...QI", "fdQfQd", OP_FMS_LNQ>;
 
-def VMLAL_LANEQ  : SOpInst<"vmlal_laneq", "wwdki", "siUsUi", OP_MLAL_LN>;
-def VMLAL_HIGH_LANE   : SOpInst<"vmlal_high_lane", "wwkdi", "siUsUi",
+def VMLAL_LANEQ  : SOpInst<"vmlal_laneq", "(>Q)(>Q).QI", "siUsUi", OP_MLAL_LN>;
+def VMLAL_HIGH_LANE   : SOpInst<"vmlal_high_lane", "(>Q)(>Q)Q.I", "siUsUi",
                                 OP_MLALHi_LN>;
-def VMLAL_HIGH_LANEQ  : SOpInst<"vmlal_high_laneq", "wwkki", "siUsUi",
+def VMLAL_HIGH_LANEQ  : SOpInst<"vmlal_high_laneq", "(>Q)(>Q)QQI", "siUsUi",
                                 OP_MLALHi_LN>;
-def VMLSL_LANEQ  : SOpInst<"vmlsl_laneq", "wwdki", "siUsUi", OP_MLSL_LN>;
-def VMLSL_HIGH_LANE   : SOpInst<"vmlsl_high_lane", "wwkdi", "siUsUi",
+def VMLSL_LANEQ  : SOpInst<"vmlsl_laneq", "(>Q)(>Q).QI", "siUsUi", OP_MLSL_LN>;
+def VMLSL_HIGH_LANE   : SOpInst<"vmlsl_high_lane", "(>Q)(>Q)Q.I", "siUsUi",
                                 OP_MLSLHi_LN>;
-def VMLSL_HIGH_LANEQ  : SOpInst<"vmlsl_high_laneq", "wwkki", "siUsUi",
+def VMLSL_HIGH_LANEQ  : SOpInst<"vmlsl_high_laneq", "(>Q)(>Q)QQI", "siUsUi",
                                 OP_MLSLHi_LN>;
 
-def VQDMLAL_LANEQ  : SOpInst<"vqdmlal_laneq", "wwdki", "si", OP_QDMLAL_LN>;
-def VQDMLAL_HIGH_LANE   : SOpInst<"vqdmlal_high_lane", "wwkdi", "si",
+def VQDMLAL_LANEQ  : SOpInst<"vqdmlal_laneq", "(>Q)(>Q).QI", "si", OP_QDMLAL_LN>;
+def VQDMLAL_HIGH_LANE   : SOpInst<"vqdmlal_high_lane", "(>Q)(>Q)Q.I", "si",
                                 OP_QDMLALHi_LN>;
-def VQDMLAL_HIGH_LANEQ  : SOpInst<"vqdmlal_high_laneq", "wwkki", "si",
+def VQDMLAL_HIGH_LANEQ  : SOpInst<"vqdmlal_high_laneq", "(>Q)(>Q)QQI", "si",
                                 OP_QDMLALHi_LN>;
-def VQDMLSL_LANEQ  : SOpInst<"vqdmlsl_laneq", "wwdki", "si", OP_QDMLSL_LN>;
-def VQDMLSL_HIGH_LANE   : SOpInst<"vqdmlsl_high_lane", "wwkdi", "si",
+def VQDMLSL_LANEQ  : SOpInst<"vqdmlsl_laneq", "(>Q)(>Q).QI", "si", OP_QDMLSL_LN>;
+def VQDMLSL_HIGH_LANE   : SOpInst<"vqdmlsl_high_lane", "(>Q)(>Q)Q.I", "si",
                                 OP_QDMLSLHi_LN>;
-def VQDMLSL_HIGH_LANEQ  : SOpInst<"vqdmlsl_high_laneq", "wwkki", "si",
+def VQDMLSL_HIGH_LANEQ  : SOpInst<"vqdmlsl_high_laneq", "(>Q)(>Q)QQI", "si",
                                 OP_QDMLSLHi_LN>;
 
 // Newly add double parameter for vmul_lane in aarch64
 // Note: d type is handled by SCALAR_VMUL_LANE
-def VMUL_LANE_A64 : IOpInst<"vmul_lane", "ddgi", "Qd", OP_MUL_LN>;
+def VMUL_LANE_A64 : IOpInst<"vmul_lane", "..qI", "Qd", OP_MUL_LN>;
 
 // Note: d type is handled by SCALAR_VMUL_LANEQ
-def VMUL_LANEQ   : IOpInst<"vmul_laneq", "ddji",
+def VMUL_LANEQ   : IOpInst<"vmul_laneq", "..QI",
                            "sifUsUiQsQiQUsQUiQfQd", OP_MUL_LN>;
-def VMULL_LANEQ  : SOpInst<"vmull_laneq", "wdki", "siUsUi", OP_MULL_LN>;
-def VMULL_HIGH_LANE   : SOpInst<"vmull_high_lane", "wkdi", "siUsUi",
+def VMULL_LANEQ  : SOpInst<"vmull_laneq", "(>Q).QI", "siUsUi", OP_MULL_LN>;
+def VMULL_HIGH_LANE   : SOpInst<"vmull_high_lane", "(>Q)Q.I", "siUsUi",
                                 OP_MULLHi_LN>;
-def VMULL_HIGH_LANEQ  : SOpInst<"vmull_high_laneq", "wkki", "siUsUi",
+def VMULL_HIGH_LANEQ  : SOpInst<"vmull_high_laneq", "(>Q)QQI", "siUsUi",
                                 OP_MULLHi_LN>;
 
-def VQDMULL_LANEQ  : SOpInst<"vqdmull_laneq", "wdki", "si", OP_QDMULL_LN>;
-def VQDMULL_HIGH_LANE   : SOpInst<"vqdmull_high_lane", "wkdi", "si",
+def VQDMULL_LANEQ  : SOpInst<"vqdmull_laneq", "(>Q).QI", "si", OP_QDMULL_LN>;
+def VQDMULL_HIGH_LANE   : SOpInst<"vqdmull_high_lane", "(>Q)Q.I", "si",
                                   OP_QDMULLHi_LN>;
-def VQDMULL_HIGH_LANEQ  : SOpInst<"vqdmull_high_laneq", "wkki", "si",
+def VQDMULL_HIGH_LANEQ  : SOpInst<"vqdmull_high_laneq", "(>Q)QQI", "si",
                                   OP_QDMULLHi_LN>;
 
-def VQDMULH_LANEQ  : SOpInst<"vqdmulh_laneq", "ddji", "siQsQi", OP_QDMULH_LN>;
-def VQRDMULH_LANEQ : SOpInst<"vqrdmulh_laneq", "ddji", "siQsQi", OP_QRDMULH_LN>;
+def VQDMULH_LANEQ  : SOpInst<"vqdmulh_laneq", "..QI", "siQsQi", OP_QDMULH_LN>;
+def VQRDMULH_LANEQ : SOpInst<"vqrdmulh_laneq", "..QI", "siQsQi", OP_QRDMULH_LN>;
 
 let ArchGuard = "defined(__ARM_FEATURE_QRDMX) && defined(__aarch64__)" in {
-def VQRDMLAH_LANEQ : SOpInst<"vqrdmlah_laneq", "dddji", "siQsQi", OP_QRDMLAH_LN>;
-def VQRDMLSH_LANEQ : SOpInst<"vqrdmlsh_laneq", "dddji", "siQsQi", OP_QRDMLSH_LN>;
+def VQRDMLAH_LANEQ : SOpInst<"vqrdmlah_laneq", "...QI", "siQsQi", OP_QRDMLAH_LN>;
+def VQRDMLSH_LANEQ : SOpInst<"vqrdmlsh_laneq", "...QI", "siQsQi", OP_QRDMLSH_LN>;
 }
 
 // Note: d type implemented by SCALAR_VMULX_LANE
-def VMULX_LANE : IOpInst<"vmulx_lane", "ddgi", "fQfQd", OP_MULX_LN>;
+def VMULX_LANE : IOpInst<"vmulx_lane", "..qI", "fQfQd", OP_MULX_LN>;
 // Note: d type is implemented by SCALAR_VMULX_LANEQ
-def VMULX_LANEQ : IOpInst<"vmulx_laneq", "ddji", "fQfQd", OP_MULX_LN>;
+def VMULX_LANEQ : IOpInst<"vmulx_laneq", "..QI", "fQfQd", OP_MULX_LN>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Across vectors class
-def VADDLV  : SInst<"vaddlv", "rd", "csiUcUsUiQcQsQiQUcQUsQUi">;
-def VMAXV   : SInst<"vmaxv", "sd", "csifUcUsUiQcQsQiQUcQUsQUiQfQd">;
-def VMINV   : SInst<"vminv", "sd", "csifUcUsUiQcQsQiQUcQUsQUiQfQd">;
-def VADDV   : SInst<"vaddv", "sd", "csifUcUsUiQcQsQiQUcQUsQUiQfQdQlQUl">;
-def FMAXNMV : SInst<"vmaxnmv", "sd", "fQfQd">;
-def FMINNMV : SInst<"vminnmv", "sd", "fQfQd">;
+def VADDLV  : SInst<"vaddlv", "(1>).", "csiUcUsUiQcQsQiQUcQUsQUi">;
+def VMAXV   : SInst<"vmaxv", "1.", "csifUcUsUiQcQsQiQUcQUsQUiQfQd">;
+def VMINV   : SInst<"vminv", "1.", "csifUcUsUiQcQsQiQUcQUsQUiQfQd">;
+def VADDV   : SInst<"vaddv", "1.", "csifUcUsUiQcQsQiQUcQUsQUiQfQdQlQUl">;
+def FMAXNMV : SInst<"vmaxnmv", "1.", "fQfQd">;
+def FMINNMV : SInst<"vminnmv", "1.", "fQfQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Newly added Vector Extract for f64
-def VEXT_A64 : WInst<"vext", "dddi", "dQdPlQPl">;
+def VEXT_A64 : WInst<"vext", "...I", "dQdPlQPl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Crypto
 let ArchGuard = "__ARM_ARCH >= 8 && defined(__ARM_FEATURE_CRYPTO)" in {
-def AESE : SInst<"vaese", "ddd", "QUc">;
-def AESD : SInst<"vaesd", "ddd", "QUc">;
-def AESMC : SInst<"vaesmc", "dd", "QUc">;
-def AESIMC : SInst<"vaesimc", "dd", "QUc">;
-
-def SHA1H : SInst<"vsha1h", "ss", "Ui">;
-def SHA1SU1 : SInst<"vsha1su1", "ddd", "QUi">;
-def SHA256SU0 : SInst<"vsha256su0", "ddd", "QUi">;
-
-def SHA1C : SInst<"vsha1c", "ddsd", "QUi">;
-def SHA1P : SInst<"vsha1p", "ddsd", "QUi">;
-def SHA1M : SInst<"vsha1m", "ddsd", "QUi">;
-def SHA1SU0 : SInst<"vsha1su0", "dddd", "QUi">;
-def SHA256H : SInst<"vsha256h", "dddd", "QUi">;
-def SHA256H2 : SInst<"vsha256h2", "dddd", "QUi">;
-def SHA256SU1 : SInst<"vsha256su1", "dddd", "QUi">;
+def AESE : SInst<"vaese", "...", "QUc">;
+def AESD : SInst<"vaesd", "...", "QUc">;
+def AESMC : SInst<"vaesmc", "..", "QUc">;
+def AESIMC : SInst<"vaesimc", "..", "QUc">;
+
+def SHA1H : SInst<"vsha1h", "11", "Ui">;
+def SHA1SU1 : SInst<"vsha1su1", "...", "QUi">;
+def SHA256SU0 : SInst<"vsha256su0", "...", "QUi">;
+
+def SHA1C : SInst<"vsha1c", "..1.", "QUi">;
+def SHA1P : SInst<"vsha1p", "..1.", "QUi">;
+def SHA1M : SInst<"vsha1m", "..1.", "QUi">;
+def SHA1SU0 : SInst<"vsha1su0", "....", "QUi">;
+def SHA256H : SInst<"vsha256h", "....", "QUi">;
+def SHA256H2 : SInst<"vsha256h2", "....", "QUi">;
+def SHA256SU1 : SInst<"vsha256su1", "....", "QUi">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Float -> Int conversions with explicit rounding mode
 
 let ArchGuard = "__ARM_ARCH >= 8" in {
-def FCVTNS_S32 : SInst<"vcvtn_s32", "xd", "fQf">;
-def FCVTNU_S32 : SInst<"vcvtn_u32", "ud", "fQf">;
-def FCVTPS_S32 : SInst<"vcvtp_s32", "xd", "fQf">;
-def FCVTPU_S32 : SInst<"vcvtp_u32", "ud", "fQf">;
-def FCVTMS_S32 : SInst<"vcvtm_s32", "xd", "fQf">;
-def FCVTMU_S32 : SInst<"vcvtm_u32", "ud", "fQf">;
-def FCVTAS_S32 : SInst<"vcvta_s32", "xd", "fQf">;
-def FCVTAU_S32 : SInst<"vcvta_u32", "ud", "fQf">;
+def FCVTNS_S32 : SInst<"vcvtn_s32", "S.", "fQf">;
+def FCVTNU_S32 : SInst<"vcvtn_u32", "U.", "fQf">;
+def FCVTPS_S32 : SInst<"vcvtp_s32", "S.", "fQf">;
+def FCVTPU_S32 : SInst<"vcvtp_u32", "U.", "fQf">;
+def FCVTMS_S32 : SInst<"vcvtm_s32", "S.", "fQf">;
+def FCVTMU_S32 : SInst<"vcvtm_u32", "U.", "fQf">;
+def FCVTAS_S32 : SInst<"vcvta_s32", "S.", "fQf">;
+def FCVTAU_S32 : SInst<"vcvta_u32", "U.", "fQf">;
 }
 
 let ArchGuard = "__ARM_ARCH >= 8 && defined(__aarch64__)" in {
-def FCVTNS_S64 : SInst<"vcvtn_s64", "xd", "dQd">;
-def FCVTNU_S64 : SInst<"vcvtn_u64", "ud", "dQd">;
-def FCVTPS_S64 : SInst<"vcvtp_s64", "xd", "dQd">;
-def FCVTPU_S64 : SInst<"vcvtp_u64", "ud", "dQd">;
-def FCVTMS_S64 : SInst<"vcvtm_s64", "xd", "dQd">;
-def FCVTMU_S64 : SInst<"vcvtm_u64", "ud", "dQd">;
-def FCVTAS_S64 : SInst<"vcvta_s64", "xd", "dQd">;
-def FCVTAU_S64 : SInst<"vcvta_u64", "ud", "dQd">;
+def FCVTNS_S64 : SInst<"vcvtn_s64", "S.", "dQd">;
+def FCVTNU_S64 : SInst<"vcvtn_u64", "U.", "dQd">;
+def FCVTPS_S64 : SInst<"vcvtp_s64", "S.", "dQd">;
+def FCVTPU_S64 : SInst<"vcvtp_u64", "U.", "dQd">;
+def FCVTMS_S64 : SInst<"vcvtm_s64", "S.", "dQd">;
+def FCVTMU_S64 : SInst<"vcvtm_u64", "U.", "dQd">;
+def FCVTAS_S64 : SInst<"vcvta_s64", "S.", "dQd">;
+def FCVTAU_S64 : SInst<"vcvta_u64", "U.", "dQd">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Round to Integral
 
 let ArchGuard = "__ARM_ARCH >= 8 && defined(__ARM_FEATURE_DIRECTED_ROUNDING)" in {
-def FRINTN_S32 : SInst<"vrndn", "dd", "fQf">;
-def FRINTA_S32 : SInst<"vrnda", "dd", "fQf">;
-def FRINTP_S32 : SInst<"vrndp", "dd", "fQf">;
-def FRINTM_S32 : SInst<"vrndm", "dd", "fQf">;
-def FRINTX_S32 : SInst<"vrndx", "dd", "fQf">;
-def FRINTZ_S32 : SInst<"vrnd", "dd", "fQf">;
-def FRINTI_S32 : SInst<"vrndi", "dd", "fQf">;
+def FRINTN_S32 : SInst<"vrndn", "..", "fQf">;
+def FRINTA_S32 : SInst<"vrnda", "..", "fQf">;
+def FRINTP_S32 : SInst<"vrndp", "..", "fQf">;
+def FRINTM_S32 : SInst<"vrndm", "..", "fQf">;
+def FRINTX_S32 : SInst<"vrndx", "..", "fQf">;
+def FRINTZ_S32 : SInst<"vrnd", "..", "fQf">;
+def FRINTI_S32 : SInst<"vrndi", "..", "fQf">;
 }
 
 let ArchGuard = "__ARM_ARCH >= 8 && defined(__aarch64__) && defined(__ARM_FEATURE_DIRECTED_ROUNDING)" in {
-def FRINTN_S64 : SInst<"vrndn", "dd", "dQd">;
-def FRINTA_S64 : SInst<"vrnda", "dd", "dQd">;
-def FRINTP_S64 : SInst<"vrndp", "dd", "dQd">;
-def FRINTM_S64 : SInst<"vrndm", "dd", "dQd">;
-def FRINTX_S64 : SInst<"vrndx", "dd", "dQd">;
-def FRINTZ_S64 : SInst<"vrnd", "dd", "dQd">;
-def FRINTI_S64 : SInst<"vrndi", "dd", "dQd">;
+def FRINTN_S64 : SInst<"vrndn", "..", "dQd">;
+def FRINTA_S64 : SInst<"vrnda", "..", "dQd">;
+def FRINTP_S64 : SInst<"vrndp", "..", "dQd">;
+def FRINTM_S64 : SInst<"vrndm", "..", "dQd">;
+def FRINTX_S64 : SInst<"vrndx", "..", "dQd">;
+def FRINTZ_S64 : SInst<"vrnd", "..", "dQd">;
+def FRINTI_S64 : SInst<"vrndi", "..", "dQd">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // MaxNum/MinNum Floating Point
 
 let ArchGuard = "__ARM_ARCH >= 8 && defined(__ARM_FEATURE_NUMERIC_MAXMIN)" in {
-def FMAXNM_S32 : SInst<"vmaxnm", "ddd", "fQf">;
-def FMINNM_S32 : SInst<"vminnm", "ddd", "fQf">;
+def FMAXNM_S32 : SInst<"vmaxnm", "...", "fQf">;
+def FMINNM_S32 : SInst<"vminnm", "...", "fQf">;
 }
 
 let ArchGuard = "__ARM_ARCH >= 8 && defined(__aarch64__) && defined(__ARM_FEATURE_NUMERIC_MAXMIN)" in {
-def FMAXNM_S64 : SInst<"vmaxnm", "ddd", "dQd">;
-def FMINNM_S64 : SInst<"vminnm", "ddd", "dQd">;
+def FMAXNM_S64 : SInst<"vmaxnm", "...", "dQd">;
+def FMINNM_S64 : SInst<"vminnm", "...", "dQd">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Permutation
-def VTRN1 : SOpInst<"vtrn1", "ddd",
+def VTRN1 : SOpInst<"vtrn1", "...",
                     "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_TRN1>;
-def VZIP1 : SOpInst<"vzip1", "ddd",
+def VZIP1 : SOpInst<"vzip1", "...",
                     "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_ZIP1>;
-def VUZP1 : SOpInst<"vuzp1", "ddd",
+def VUZP1 : SOpInst<"vuzp1", "...",
                     "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_UZP1>;
-def VTRN2 : SOpInst<"vtrn2", "ddd",
+def VTRN2 : SOpInst<"vtrn2", "...",
                     "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_TRN2>;
-def VZIP2 : SOpInst<"vzip2", "ddd",
+def VZIP2 : SOpInst<"vzip2", "...",
                     "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_ZIP2>;
-def VUZP2 : SOpInst<"vuzp2", "ddd",
+def VUZP2 : SOpInst<"vuzp2", "...",
                     "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPsQPl", OP_UZP2>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Table lookup
 let InstName = "vtbl" in {
-def VQTBL1_A64 : WInst<"vqtbl1", "dju",  "UccPcQUcQcQPc">;
-def VQTBL2_A64 : WInst<"vqtbl2", "dBu",  "UccPcQUcQcQPc">;
-def VQTBL3_A64 : WInst<"vqtbl3", "dCu",  "UccPcQUcQcQPc">;
-def VQTBL4_A64 : WInst<"vqtbl4", "dDu",  "UccPcQUcQcQPc">;
+def VQTBL1_A64 : WInst<"vqtbl1", ".QU",  "UccPcQUcQcQPc">;
+def VQTBL2_A64 : WInst<"vqtbl2", ".(2Q)U",  "UccPcQUcQcQPc">;
+def VQTBL3_A64 : WInst<"vqtbl3", ".(3Q)U",  "UccPcQUcQcQPc">;
+def VQTBL4_A64 : WInst<"vqtbl4", ".(4Q)U",  "UccPcQUcQcQPc">;
 }
 let InstName = "vtbx" in {
-def VQTBX1_A64 : WInst<"vqtbx1", "ddju", "UccPcQUcQcQPc">;
-def VQTBX2_A64 : WInst<"vqtbx2", "ddBu", "UccPcQUcQcQPc">;
-def VQTBX3_A64 : WInst<"vqtbx3", "ddCu", "UccPcQUcQcQPc">;
-def VQTBX4_A64 : WInst<"vqtbx4", "ddDu", "UccPcQUcQcQPc">;
+def VQTBX1_A64 : WInst<"vqtbx1", "..QU", "UccPcQUcQcQPc">;
+def VQTBX2_A64 : WInst<"vqtbx2", "..(2Q)U", "UccPcQUcQcQPc">;
+def VQTBX3_A64 : WInst<"vqtbx3", "..(3Q)U", "UccPcQUcQcQPc">;
+def VQTBX4_A64 : WInst<"vqtbx4", "..(4Q)U", "UccPcQUcQcQPc">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
@@ -1095,7 +1096,7 @@ def VQTBX4_A64 : WInst<"vqtbx4", "ddDu", "UccPcQUcQcQPc">;
 // itself during generation so, unlike all other intrinsics, this one should
 // include *all* types, not just additional ones.
 def VVREINTERPRET
-  : NoTestOpInst<"vreinterpret", "dd",
+  : NoTestOpInst<"vreinterpret", "..",
        "csilUcUsUiUlhfdPcPsPlQcQsQiQlQUcQUsQUiQUlQhQfQdQPcQPsQPlQPk", OP_REINT> {
   let CartesianProductOfTypes = 1;
   let BigEndianSafe = 1;
@@ -1107,332 +1108,332 @@ def VVREINTERPRET
 // Scalar Arithmetic
 
 // Scalar Addition
-def SCALAR_ADD : SInst<"vadd", "sss",  "SlSUl">;
+def SCALAR_ADD : SInst<"vadd", "111",  "SlSUl">;
 // Scalar  Saturating Add
-def SCALAR_QADD   : SInst<"vqadd", "sss", "ScSsSiSlSUcSUsSUiSUl">;
+def SCALAR_QADD   : SInst<"vqadd", "111", "ScSsSiSlSUcSUsSUiSUl">;
 
 // Scalar Subtraction
-def SCALAR_SUB : SInst<"vsub", "sss",  "SlSUl">;
+def SCALAR_SUB : SInst<"vsub", "111",  "SlSUl">;
 // Scalar  Saturating Sub
-def SCALAR_QSUB   : SInst<"vqsub", "sss", "ScSsSiSlSUcSUsSUiSUl">;
+def SCALAR_QSUB   : SInst<"vqsub", "111", "ScSsSiSlSUcSUsSUiSUl">;
 
 let InstName = "vmov" in {
-def VGET_HIGH_A64 : NoTestOpInst<"vget_high", "dk", "dPl", OP_HI>;
-def VGET_LOW_A64  : NoTestOpInst<"vget_low", "dk", "dPl", OP_LO>;
+def VGET_HIGH_A64 : NoTestOpInst<"vget_high", ".Q", "dPl", OP_HI>;
+def VGET_LOW_A64  : NoTestOpInst<"vget_low", ".Q", "dPl", OP_LO>;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Shift
 // Scalar Shift Left
-def SCALAR_SHL: SInst<"vshl", "sss", "SlSUl">;
+def SCALAR_SHL: SInst<"vshl", "111", "SlSUl">;
 // Scalar Saturating Shift Left
-def SCALAR_QSHL: SInst<"vqshl", "sss", "ScSsSiSlSUcSUsSUiSUl">;
+def SCALAR_QSHL: SInst<"vqshl", "111", "ScSsSiSlSUcSUsSUiSUl">;
 // Scalar Saturating Rounding Shift Left
-def SCALAR_QRSHL: SInst<"vqrshl", "sss", "ScSsSiSlSUcSUsSUiSUl">;
+def SCALAR_QRSHL: SInst<"vqrshl", "111", "ScSsSiSlSUcSUsSUiSUl">;
 // Scalar Shift Rounding Left
-def SCALAR_RSHL: SInst<"vrshl", "sss", "SlSUl">;
+def SCALAR_RSHL: SInst<"vrshl", "111", "SlSUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Shift (Immediate)
 let isScalarShift = 1 in {
 // Signed/Unsigned Shift Right (Immediate)
-def SCALAR_SSHR_N: SInst<"vshr_n", "ssi", "SlSUl">;
+def SCALAR_SSHR_N: SInst<"vshr_n", "11I", "SlSUl">;
 // Signed/Unsigned Rounding Shift Right (Immediate)
-def SCALAR_SRSHR_N: SInst<"vrshr_n", "ssi", "SlSUl">;
+def SCALAR_SRSHR_N: SInst<"vrshr_n", "11I", "SlSUl">;
 
 // Signed/Unsigned Shift Right and Accumulate (Immediate)
-def SCALAR_SSRA_N: SInst<"vsra_n", "sssi", "SlSUl">;
+def SCALAR_SSRA_N: SInst<"vsra_n", "111I", "SlSUl">;
 // Signed/Unsigned Rounding Shift Right and Accumulate (Immediate)
-def SCALAR_SRSRA_N: SInst<"vrsra_n", "sssi", "SlSUl">;
+def SCALAR_SRSRA_N: SInst<"vrsra_n", "111I", "SlSUl">;
 
 // Shift Left (Immediate)
-def SCALAR_SHL_N: SInst<"vshl_n", "ssi", "SlSUl">;
+def SCALAR_SHL_N: SInst<"vshl_n", "11I", "SlSUl">;
 // Signed/Unsigned Saturating Shift Left (Immediate)
-def SCALAR_SQSHL_N: SInst<"vqshl_n", "ssi", "ScSsSiSlSUcSUsSUiSUl">;
+def SCALAR_SQSHL_N: SInst<"vqshl_n", "11I", "ScSsSiSlSUcSUsSUiSUl">;
 // Signed Saturating Shift Left Unsigned (Immediate)
-def SCALAR_SQSHLU_N: SInst<"vqshlu_n", "ssi", "ScSsSiSl">;
+def SCALAR_SQSHLU_N: SInst<"vqshlu_n", "11I", "ScSsSiSl">;
 
 // Shift Right And Insert (Immediate)
-def SCALAR_SRI_N: SInst<"vsri_n", "sssi", "SlSUl">;
+def SCALAR_SRI_N: SInst<"vsri_n", "111I", "SlSUl">;
 // Shift Left And Insert (Immediate)
-def SCALAR_SLI_N: SInst<"vsli_n", "sssi", "SlSUl">;
+def SCALAR_SLI_N: SInst<"vsli_n", "111I", "SlSUl">;
 
 let isScalarNarrowShift = 1 in {
   // Signed/Unsigned Saturating Shift Right Narrow (Immediate)
-  def SCALAR_SQSHRN_N: SInst<"vqshrn_n", "zsi", "SsSiSlSUsSUiSUl">;
+  def SCALAR_SQSHRN_N: SInst<"vqshrn_n", "(1<)1I", "SsSiSlSUsSUiSUl">;
   // Signed/Unsigned Saturating Rounded Shift Right Narrow (Immediate)
-  def SCALAR_SQRSHRN_N: SInst<"vqrshrn_n", "zsi", "SsSiSlSUsSUiSUl">;
+  def SCALAR_SQRSHRN_N: SInst<"vqrshrn_n", "(1<)1I", "SsSiSlSUsSUiSUl">;
   // Signed Saturating Shift Right Unsigned Narrow (Immediate)
-  def SCALAR_SQSHRUN_N: SInst<"vqshrun_n", "zsi", "SsSiSl">;
+  def SCALAR_SQSHRUN_N: SInst<"vqshrun_n", "(1<)1I", "SsSiSl">;
   // Signed Saturating Rounded Shift Right Unsigned Narrow (Immediate)
-  def SCALAR_SQRSHRUN_N: SInst<"vqrshrun_n", "zsi", "SsSiSl">;
+  def SCALAR_SQRSHRUN_N: SInst<"vqrshrun_n", "(1<)1I", "SsSiSl">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Signed/Unsigned Fixed-point Convert To Floating-Point (Immediate)
-def SCALAR_SCVTF_N_F32: SInst<"vcvt_n_f32", "ysi", "SiSUi">;
-def SCALAR_SCVTF_N_F64: SInst<"vcvt_n_f64", "osi", "SlSUl">;
+def SCALAR_SCVTF_N_F32: SInst<"vcvt_n_f32", "(1F)(1!)I", "SiSUi">;
+def SCALAR_SCVTF_N_F64: SInst<"vcvt_n_f64", "(1F)(1!)I", "SlSUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Convert To Signed/Unsigned Fixed-point (Immediate)
-def SCALAR_FCVTZS_N_S32 : SInst<"vcvt_n_s32", "$si", "Sf">;
-def SCALAR_FCVTZU_N_U32 : SInst<"vcvt_n_u32", "bsi", "Sf">;
-def SCALAR_FCVTZS_N_S64 : SInst<"vcvt_n_s64", "$si", "Sd">;
-def SCALAR_FCVTZU_N_U64 : SInst<"vcvt_n_u64", "bsi", "Sd">;
+def SCALAR_FCVTZS_N_S32 : SInst<"vcvt_n_s32", "(1S)1I", "Sf">;
+def SCALAR_FCVTZU_N_U32 : SInst<"vcvt_n_u32", "(1U)1I", "Sf">;
+def SCALAR_FCVTZS_N_S64 : SInst<"vcvt_n_s64", "(1S)1I", "Sd">;
+def SCALAR_FCVTZU_N_U64 : SInst<"vcvt_n_u64", "(1U)1I", "Sd">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Round to Integral
 let ArchGuard = "__ARM_ARCH >= 8 && defined(__ARM_FEATURE_DIRECTED_ROUNDING)" in {
-def SCALAR_FRINTN_S32 : SInst<"vrndn", "ss", "Sf">;
+def SCALAR_FRINTN_S32 : SInst<"vrndn", "11", "Sf">;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Reduce Pairwise Addition (Scalar and Floating Point)
-def SCALAR_ADDP  : SInst<"vpadd", "sd", "SfSHlSHdSHUl">;
+def SCALAR_ADDP  : SInst<"vpadd", "1.", "SfSHlSHdSHUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Reduce Floating Point Pairwise Max/Min
-def SCALAR_FMAXP : SInst<"vpmax", "sd", "SfSQd">;
+def SCALAR_FMAXP : SInst<"vpmax", "1.", "SfSQd">;
 
-def SCALAR_FMINP : SInst<"vpmin", "sd", "SfSQd">;
+def SCALAR_FMINP : SInst<"vpmin", "1.", "SfSQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Reduce Floating Point Pairwise maxNum/minNum
-def SCALAR_FMAXNMP : SInst<"vpmaxnm", "sd", "SfSQd">;
-def SCALAR_FMINNMP : SInst<"vpminnm", "sd", "SfSQd">;
+def SCALAR_FMAXNMP : SInst<"vpmaxnm", "1.", "SfSQd">;
+def SCALAR_FMINNMP : SInst<"vpminnm", "1.", "SfSQd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Integer Saturating Doubling Multiply Half High
-def SCALAR_SQDMULH : SInst<"vqdmulh", "sss", "SsSi">;
+def SCALAR_SQDMULH : SInst<"vqdmulh", "111", "SsSi">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Integer Saturating Rounding Doubling Multiply Half High
-def SCALAR_SQRDMULH : SInst<"vqrdmulh", "sss", "SsSi">;
+def SCALAR_SQRDMULH : SInst<"vqrdmulh", "111", "SsSi">;
 
 let ArchGuard = "defined(__ARM_FEATURE_QRDMX) && defined(__aarch64__)" in {
 ////////////////////////////////////////////////////////////////////////////////
 // Signed Saturating Rounding Doubling Multiply Accumulate Returning High Half
-def SCALAR_SQRDMLAH : SOpInst<"vqrdmlah", "ssss", "SsSi", OP_QRDMLAH>;
+def SCALAR_SQRDMLAH : SOpInst<"vqrdmlah", "1111", "SsSi", OP_QRDMLAH>;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Signed Saturating Rounding Doubling Multiply Subtract Returning High Half
-def SCALAR_SQRDMLSH : SOpInst<"vqrdmlsh", "ssss", "SsSi", OP_QRDMLSH>;
+def SCALAR_SQRDMLSH : SOpInst<"vqrdmlsh", "1111", "SsSi", OP_QRDMLSH>;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Multiply Extended
-def SCALAR_FMULX : IInst<"vmulx", "sss", "SfSd">;
+def SCALAR_FMULX : IInst<"vmulx", "111", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Reciprocal Step
-def SCALAR_FRECPS : IInst<"vrecps", "sss", "SfSd">;
+def SCALAR_FRECPS : IInst<"vrecps", "111", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Reciprocal Square Root Step
-def SCALAR_FRSQRTS : IInst<"vrsqrts", "sss", "SfSd">;
+def SCALAR_FRSQRTS : IInst<"vrsqrts", "111", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Signed Integer Convert To Floating-point
-def SCALAR_SCVTFS : SInst<"vcvt_f32", "ys", "Si">;
-def SCALAR_SCVTFD : SInst<"vcvt_f64", "os", "Sl">;
+def SCALAR_SCVTFS : SInst<"vcvt_f32", "(1F)(1!)", "Si">;
+def SCALAR_SCVTFD : SInst<"vcvt_f64", "(1F)(1!)", "Sl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Unsigned Integer Convert To Floating-point
-def SCALAR_UCVTFS : SInst<"vcvt_f32", "ys", "SUi">;
-def SCALAR_UCVTFD : SInst<"vcvt_f64", "os", "SUl">;
+def SCALAR_UCVTFS : SInst<"vcvt_f32", "(1F)(1!)", "SUi">;
+def SCALAR_UCVTFD : SInst<"vcvt_f64", "(1F)(1!)", "SUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Converts
-def SCALAR_FCVTXN  : IInst<"vcvtx_f32", "ys", "Sd">;
-def SCALAR_FCVTNSS : SInst<"vcvtn_s32", "$s", "Sf">;
-def SCALAR_FCVTNUS : SInst<"vcvtn_u32", "bs", "Sf">;
-def SCALAR_FCVTNSD : SInst<"vcvtn_s64", "$s", "Sd">;
-def SCALAR_FCVTNUD : SInst<"vcvtn_u64", "bs", "Sd">;
-def SCALAR_FCVTMSS : SInst<"vcvtm_s32", "$s", "Sf">;
-def SCALAR_FCVTMUS : SInst<"vcvtm_u32", "bs", "Sf">;
-def SCALAR_FCVTMSD : SInst<"vcvtm_s64", "$s", "Sd">;
-def SCALAR_FCVTMUD : SInst<"vcvtm_u64", "bs", "Sd">;
-def SCALAR_FCVTASS : SInst<"vcvta_s32", "$s", "Sf">;
-def SCALAR_FCVTAUS : SInst<"vcvta_u32", "bs", "Sf">;
-def SCALAR_FCVTASD : SInst<"vcvta_s64", "$s", "Sd">;
-def SCALAR_FCVTAUD : SInst<"vcvta_u64", "bs", "Sd">;
-def SCALAR_FCVTPSS : SInst<"vcvtp_s32", "$s", "Sf">;
-def SCALAR_FCVTPUS : SInst<"vcvtp_u32", "bs", "Sf">;
-def SCALAR_FCVTPSD : SInst<"vcvtp_s64", "$s", "Sd">;
-def SCALAR_FCVTPUD : SInst<"vcvtp_u64", "bs", "Sd">;
-def SCALAR_FCVTZSS : SInst<"vcvt_s32", "$s", "Sf">;
-def SCALAR_FCVTZUS : SInst<"vcvt_u32", "bs", "Sf">;
-def SCALAR_FCVTZSD : SInst<"vcvt_s64", "$s", "Sd">;
-def SCALAR_FCVTZUD : SInst<"vcvt_u64", "bs", "Sd">;
+def SCALAR_FCVTXN  : IInst<"vcvtx_f32", "(1F<)(1!)", "Sd">;
+def SCALAR_FCVTNSS : SInst<"vcvtn_s32", "(1S)1", "Sf">;
+def SCALAR_FCVTNUS : SInst<"vcvtn_u32", "(1U)1", "Sf">;
+def SCALAR_FCVTNSD : SInst<"vcvtn_s64", "(1S)1", "Sd">;
+def SCALAR_FCVTNUD : SInst<"vcvtn_u64", "(1U)1", "Sd">;
+def SCALAR_FCVTMSS : SInst<"vcvtm_s32", "(1S)1", "Sf">;
+def SCALAR_FCVTMUS : SInst<"vcvtm_u32", "(1U)1", "Sf">;
+def SCALAR_FCVTMSD : SInst<"vcvtm_s64", "(1S)1", "Sd">;
+def SCALAR_FCVTMUD : SInst<"vcvtm_u64", "(1U)1", "Sd">;
+def SCALAR_FCVTASS : SInst<"vcvta_s32", "(1S)1", "Sf">;
+def SCALAR_FCVTAUS : SInst<"vcvta_u32", "(1U)1", "Sf">;
+def SCALAR_FCVTASD : SInst<"vcvta_s64", "(1S)1", "Sd">;
+def SCALAR_FCVTAUD : SInst<"vcvta_u64", "(1U)1", "Sd">;
+def SCALAR_FCVTPSS : SInst<"vcvtp_s32", "(1S)1", "Sf">;
+def SCALAR_FCVTPUS : SInst<"vcvtp_u32", "(1U)1", "Sf">;
+def SCALAR_FCVTPSD : SInst<"vcvtp_s64", "(1S)1", "Sd">;
+def SCALAR_FCVTPUD : SInst<"vcvtp_u64", "(1U)1", "Sd">;
+def SCALAR_FCVTZSS : SInst<"vcvt_s32", "(1S)1", "Sf">;
+def SCALAR_FCVTZUS : SInst<"vcvt_u32", "(1U)1", "Sf">;
+def SCALAR_FCVTZSD : SInst<"vcvt_s64", "(1S)1", "Sd">;
+def SCALAR_FCVTZUD : SInst<"vcvt_u64", "(1U)1", "Sd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Reciprocal Estimate
-def SCALAR_FRECPE : IInst<"vrecpe", "ss", "SfSd">;
+def SCALAR_FRECPE : IInst<"vrecpe", "11", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Reciprocal Exponent
-def SCALAR_FRECPX : IInst<"vrecpx", "ss", "SfSd">;
+def SCALAR_FRECPX : IInst<"vrecpx", "11", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Reciprocal Square Root Estimate
-def SCALAR_FRSQRTE : IInst<"vrsqrte", "ss", "SfSd">;
+def SCALAR_FRSQRTE : IInst<"vrsqrte", "11", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Integer Comparison
-def SCALAR_CMEQ : SInst<"vceq", "sss", "SlSUl">;
-def SCALAR_CMEQZ : SInst<"vceqz", "ss", "SlSUl">;
-def SCALAR_CMGE : SInst<"vcge", "sss", "Sl">;
-def SCALAR_CMGEZ : SInst<"vcgez", "ss", "Sl">;
-def SCALAR_CMHS : SInst<"vcge", "sss", "SUl">;
-def SCALAR_CMLE : SInst<"vcle", "sss", "SlSUl">;
-def SCALAR_CMLEZ : SInst<"vclez", "ss", "Sl">;
-def SCALAR_CMLT : SInst<"vclt", "sss", "SlSUl">;
-def SCALAR_CMLTZ : SInst<"vcltz", "ss", "Sl">;
-def SCALAR_CMGT : SInst<"vcgt", "sss", "Sl">;
-def SCALAR_CMGTZ : SInst<"vcgtz", "ss", "Sl">;
-def SCALAR_CMHI : SInst<"vcgt", "sss", "SUl">;
-def SCALAR_CMTST : SInst<"vtst", "sss", "SlSUl">;
+def SCALAR_CMEQ : SInst<"vceq", "111", "SlSUl">;
+def SCALAR_CMEQZ : SInst<"vceqz", "11", "SlSUl">;
+def SCALAR_CMGE : SInst<"vcge", "111", "Sl">;
+def SCALAR_CMGEZ : SInst<"vcgez", "11", "Sl">;
+def SCALAR_CMHS : SInst<"vcge", "111", "SUl">;
+def SCALAR_CMLE : SInst<"vcle", "111", "SlSUl">;
+def SCALAR_CMLEZ : SInst<"vclez", "11", "Sl">;
+def SCALAR_CMLT : SInst<"vclt", "111", "SlSUl">;
+def SCALAR_CMLTZ : SInst<"vcltz", "11", "Sl">;
+def SCALAR_CMGT : SInst<"vcgt", "111", "Sl">;
+def SCALAR_CMGTZ : SInst<"vcgtz", "11", "Sl">;
+def SCALAR_CMHI : SInst<"vcgt", "111", "SUl">;
+def SCALAR_CMTST : SInst<"vtst", "111", "SlSUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Comparison
-def SCALAR_FCMEQ : IInst<"vceq", "bss", "SfSd">;
-def SCALAR_FCMEQZ : IInst<"vceqz", "bs", "SfSd">;
-def SCALAR_FCMGE : IInst<"vcge", "bss", "SfSd">;
-def SCALAR_FCMGEZ : IInst<"vcgez", "bs", "SfSd">;
-def SCALAR_FCMGT : IInst<"vcgt", "bss", "SfSd">;
-def SCALAR_FCMGTZ : IInst<"vcgtz", "bs", "SfSd">;
-def SCALAR_FCMLE : IInst<"vcle", "bss", "SfSd">;
-def SCALAR_FCMLEZ : IInst<"vclez", "bs", "SfSd">;
-def SCALAR_FCMLT : IInst<"vclt", "bss", "SfSd">;
-def SCALAR_FCMLTZ : IInst<"vcltz", "bs", "SfSd">;
+def SCALAR_FCMEQ : IInst<"vceq", "(1U)11", "SfSd">;
+def SCALAR_FCMEQZ : IInst<"vceqz", "(1U)1", "SfSd">;
+def SCALAR_FCMGE : IInst<"vcge", "(1U)11", "SfSd">;
+def SCALAR_FCMGEZ : IInst<"vcgez", "(1U)1", "SfSd">;
+def SCALAR_FCMGT : IInst<"vcgt", "(1U)11", "SfSd">;
+def SCALAR_FCMGTZ : IInst<"vcgtz", "(1U)1", "SfSd">;
+def SCALAR_FCMLE : IInst<"vcle", "(1U)11", "SfSd">;
+def SCALAR_FCMLEZ : IInst<"vclez", "(1U)1", "SfSd">;
+def SCALAR_FCMLT : IInst<"vclt", "(1U)11", "SfSd">;
+def SCALAR_FCMLTZ : IInst<"vcltz", "(1U)1", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Absolute Compare Mask Greater Than Or Equal
-def SCALAR_FACGE : IInst<"vcage", "bss", "SfSd">;
-def SCALAR_FACLE : IInst<"vcale", "bss", "SfSd">;
+def SCALAR_FACGE : IInst<"vcage", "(1U)11", "SfSd">;
+def SCALAR_FACLE : IInst<"vcale", "(1U)11", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Floating-point Absolute Compare Mask Greater Than
-def SCALAR_FACGT : IInst<"vcagt", "bss", "SfSd">;
-def SCALAR_FACLT : IInst<"vcalt", "bss", "SfSd">;
+def SCALAR_FACGT : IInst<"vcagt", "(1U)11", "SfSd">;
+def SCALAR_FACLT : IInst<"vcalt", "(1U)11", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Absolute Value
-def SCALAR_ABS : SInst<"vabs", "ss", "Sl">;
+def SCALAR_ABS : SInst<"vabs", "11", "Sl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Absolute Difference
-def SCALAR_ABD : IInst<"vabd", "sss", "SfSd">;
+def SCALAR_ABD : IInst<"vabd", "111", "SfSd">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Signed Saturating Absolute Value
-def SCALAR_SQABS : SInst<"vqabs", "ss", "ScSsSiSl">;
+def SCALAR_SQABS : SInst<"vqabs", "11", "ScSsSiSl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Negate
-def SCALAR_NEG : SInst<"vneg", "ss", "Sl">;
+def SCALAR_NEG : SInst<"vneg", "11", "Sl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Signed Saturating Negate
-def SCALAR_SQNEG : SInst<"vqneg", "ss", "ScSsSiSl">;
+def SCALAR_SQNEG : SInst<"vqneg", "11", "ScSsSiSl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Signed Saturating Accumulated of Unsigned Value
-def SCALAR_SUQADD : SInst<"vuqadd", "ssb", "ScSsSiSl">;
+def SCALAR_SUQADD : SInst<"vuqadd", "11(1U)", "ScSsSiSl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Unsigned Saturating Accumulated of Signed Value
-def SCALAR_USQADD : SInst<"vsqadd", "ss$", "SUcSUsSUiSUl">;
+def SCALAR_USQADD : SInst<"vsqadd", "11(1S)", "SUcSUsSUiSUl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Signed Saturating Doubling Multiply-Add Long
-def SCALAR_SQDMLAL : SInst<"vqdmlal", "rrss", "SsSi">;
+def SCALAR_SQDMLAL : SInst<"vqdmlal", "(1>)(1>)11", "SsSi">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Signed Saturating Doubling Multiply-Subtract Long
-def SCALAR_SQDMLSL : SInst<"vqdmlsl", "rrss", "SsSi">;
+def SCALAR_SQDMLSL : SInst<"vqdmlsl", "(1>)(1>)11", "SsSi">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Signed Saturating Doubling Multiply Long
-def SCALAR_SQDMULL : SInst<"vqdmull", "rss", "SsSi">;
+def SCALAR_SQDMULL : SInst<"vqdmull", "(1>)11", "SsSi">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Signed Saturating Extract Unsigned Narrow
-def SCALAR_SQXTUN : SInst<"vqmovun", "zs", "SsSiSl">;
+def SCALAR_SQXTUN : SInst<"vqmovun", "(1<)1", "SsSiSl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Signed Saturating Extract Narrow
-def SCALAR_SQXTN : SInst<"vqmovn", "zs", "SsSiSl">;
+def SCALAR_SQXTN : SInst<"vqmovn", "(1<)1", "SsSiSl">;
 
 ////////////////////////////////////////////////////////////////////////////////
 // Scalar Unsigned Saturating Extract Narrow
-def SCALAR_UQXTN : SInst<"vqmovn", "zs", "SUsSUiSUl">;
+def SCALAR_UQXTN : SInst<"vqmovn", "(1<)1", "SUsSUiSUl">;
 
 // Scalar Floating Point  multiply (scalar, by element)
-def SCALAR_FMUL_LANE : IOpInst<"vmul_lane", "ssdi", "SfSd", OP_SCALAR_MUL_LN>;
-def SCALAR_FMUL_LANEQ : IOpInst<"vmul_laneq", "ssji", "SfSd", OP_SCALAR_MUL_LN>;
+def SCALAR_FMUL_LANE : IOpInst<"vmul_lane", "11.I", "SfSd", OP_SCALAR_MUL_LN>;
+def SCALAR_FMUL_LANEQ : IOpInst<"vmul_laneq", "11QI", "SfSd", OP_SCALAR_MUL_LN>;
 
 // Scalar Floating Point  multiply extended (scalar, by element)
-def SCALAR_FMULX_LANE : IOpInst<"vmulx_lane", "ssdi", "SfSd", OP_SCALAR_MULX_LN>;
-def SCALAR_FMULX_LANEQ : IOpInst<"vmulx_laneq", "ssji", "SfSd", OP_SCALAR_MULX_LN>;
+def SCALAR_FMULX_LANE : IOpInst<"vmulx_lane", "11.I", "SfSd", OP_SCALAR_MULX_LN>;
+def SCALAR_FMULX_LANEQ : IOpInst<"vmulx_laneq", "11QI", "SfSd", OP_SCALAR_MULX_LN>;
 
-def SCALAR_VMUL_N : IInst<"vmul_n", "dds", "d">;
+def SCALAR_VMUL_N : IInst<"vmul_n", "..1", "d">;
 
 // VMUL_LANE_A64 d type implemented using scalar mul lane
-def SCALAR_VMUL_LANE : IInst<"vmul_lane", "ddgi", "d">;
+def SCALAR_VMUL_LANE : IInst<"vmul_lane", "..qI", "d">;
 
 // VMUL_LANEQ d type implemented using scalar mul lane
-def SCALAR_VMUL_LANEQ   : IInst<"vmul_laneq", "ddji", "d"> {
+def SCALAR_VMUL_LANEQ   : IInst<"vmul_laneq", "..QI", "d"> {
   let isLaneQ = 1;
 }
 
 // VMULX_LANE d type implemented using scalar vmulx_lane
-def SCALAR_VMULX_LANE : IOpInst<"vmulx_lane", "ddgi", "d", OP_SCALAR_VMULX_LN>;
+def SCALAR_VMULX_LANE : IOpInst<"vmulx_lane", "..qI", "d", OP_SCALAR_VMULX_LN>;
 
 // VMULX_LANEQ d type implemented using scalar vmulx_laneq
-def SCALAR_VMULX_LANEQ : IOpInst<"vmulx_laneq", "ddji", "d", OP_SCALAR_VMULX_LNQ>;
+def SCALAR_VMULX_LANEQ : IOpInst<"vmulx_laneq", "..QI", "d", OP_SCALAR_VMULX_LNQ>;
 
 // Scalar Floating Point fused multiply-add (scalar, by element)
-def SCALAR_FMLA_LANE : IInst<"vfma_lane", "sssdi", "SfSd">;
-def SCALAR_FMLA_LANEQ : IInst<"vfma_laneq", "sssji", "SfSd">;
+def SCALAR_FMLA_LANE : IInst<"vfma_lane", "111.I", "SfSd">;
+def SCALAR_FMLA_LANEQ : IInst<"vfma_laneq", "111QI", "SfSd">;
 
 // Scalar Floating Point fused multiply-subtract (scalar, by element)
-def SCALAR_FMLS_LANE : IOpInst<"vfms_lane", "sssdi", "SfSd", OP_FMS_LN>;
-def SCALAR_FMLS_LANEQ : IOpInst<"vfms_laneq", "sssji", "SfSd", OP_FMS_LNQ>;
+def SCALAR_FMLS_LANE : IOpInst<"vfms_lane", "111.I", "SfSd", OP_FMS_LN>;
+def SCALAR_FMLS_LANEQ : IOpInst<"vfms_laneq", "111QI", "SfSd", OP_FMS_LNQ>;
 
 // Signed Saturating Doubling Multiply Long (scalar by element)
-def SCALAR_SQDMULL_LANE : SOpInst<"vqdmull_lane", "rsdi", "SsSi", OP_SCALAR_QDMULL_LN>;
-def SCALAR_SQDMULL_LANEQ : SOpInst<"vqdmull_laneq", "rsji", "SsSi", OP_SCALAR_QDMULL_LN>;
+def SCALAR_SQDMULL_LANE : SOpInst<"vqdmull_lane", "(1>)1.I", "SsSi", OP_SCALAR_QDMULL_LN>;
+def SCALAR_SQDMULL_LANEQ : SOpInst<"vqdmull_laneq", "(1>)1QI", "SsSi", OP_SCALAR_QDMULL_LN>;
 
 // Signed Saturating Doubling Multiply-Add Long (scalar by element)
-def SCALAR_SQDMLAL_LANE : SInst<"vqdmlal_lane", "rrsdi", "SsSi">;
-def SCALAR_SQDMLAL_LANEQ : SInst<"vqdmlal_laneq", "rrsji", "SsSi">;
+def SCALAR_SQDMLAL_LANE : SInst<"vqdmlal_lane", "(1>)(1>)1.I", "SsSi">;
+def SCALAR_SQDMLAL_LANEQ : SInst<"vqdmlal_laneq", "(1>)(1>)1QI", "SsSi">;
 
 // Signed Saturating Doubling Multiply-Subtract Long (scalar by element)
-def SCALAR_SQDMLS_LANE : SInst<"vqdmlsl_lane", "rrsdi", "SsSi">;
-def SCALAR_SQDMLS_LANEQ : SInst<"vqdmlsl_laneq", "rrsji", "SsSi">;
+def SCALAR_SQDMLS_LANE : SInst<"vqdmlsl_lane", "(1>)(1>)1.I", "SsSi">;
+def SCALAR_SQDMLS_LANEQ : SInst<"vqdmlsl_laneq", "(1>)(1>)1QI", "SsSi">;
 
 // Scalar Integer Saturating Doubling Multiply Half High (scalar by element)
-def SCALAR_SQDMULH_LANE : SOpInst<"vqdmulh_lane", "ssdi", "SsSi", OP_SCALAR_QDMULH_LN>;
-def SCALAR_SQDMULH_LANEQ : SOpInst<"vqdmulh_laneq", "ssji", "SsSi", OP_SCALAR_QDMULH_LN>;
+def SCALAR_SQDMULH_LANE : SOpInst<"vqdmulh_lane", "11.I", "SsSi", OP_SCALAR_QDMULH_LN>;
+def SCALAR_SQDMULH_LANEQ : SOpInst<"vqdmulh_laneq", "11QI", "SsSi", OP_SCALAR_QDMULH_LN>;
 
 // Scalar Integer Saturating Rounding Doubling Multiply Half High
-def SCALAR_SQRDMULH_LANE : SOpInst<"vqrdmulh_lane", "ssdi", "SsSi", OP_SCALAR_QRDMULH_LN>;
-def SCALAR_SQRDMULH_LANEQ : SOpInst<"vqrdmulh_laneq", "ssji", "SsSi", OP_SCALAR_QRDMULH_LN>;
+def SCALAR_SQRDMULH_LANE : SOpInst<"vqrdmulh_lane", "11.I", "SsSi", OP_SCALAR_QRDMULH_LN>;
+def SCALAR_SQRDMULH_LANEQ : SOpInst<"vqrdmulh_laneq", "11QI", "SsSi", OP_SCALAR_QRDMULH_LN>;
 
 let ArchGuard = "defined(__ARM_FEATURE_QRDMX) && defined(__aarch64__)" in {
 // Signed Saturating Rounding Doubling Multiply Accumulate Returning High Half
-def SCALAR_SQRDMLAH_LANE : SOpInst<"vqrdmlah_lane", "sssdi", "SsSi", OP_SCALAR_QRDMLAH_LN>;
-def SCALAR_SQRDMLAH_LANEQ : SOpInst<"vqrdmlah_laneq", "sssji", "SsSi", OP_SCALAR_QRDMLAH_LN>;
+def SCALAR_SQRDMLAH_LANE : SOpInst<"vqrdmlah_lane", "111.I", "SsSi", OP_SCALAR_QRDMLAH_LN>;
+def SCALAR_SQRDMLAH_LANEQ : SOpInst<"vqrdmlah_laneq", "111QI", "SsSi", OP_SCALAR_QRDMLAH_LN>;
 
 // Signed Saturating Rounding Doubling Multiply Subtract Returning High Half
-def SCALAR_SQRDMLSH_LANE : SOpInst<"vqrdmlsh_lane", "sssdi", "SsSi", OP_SCALAR_QRDMLSH_LN>;
-def SCALAR_SQRDMLSH_LANEQ : SOpInst<"vqrdmlsh_laneq", "sssji", "SsSi", OP_SCALAR_QRDMLSH_LN>;
+def SCALAR_SQRDMLSH_LANE : SOpInst<"vqrdmlsh_lane", "111.I", "SsSi", OP_SCALAR_QRDMLSH_LN>;
+def SCALAR_SQRDMLSH_LANEQ : SOpInst<"vqrdmlsh_laneq", "111QI", "SsSi", OP_SCALAR_QRDMLSH_LN>;
 }
 
-def SCALAR_VDUP_LANE : IInst<"vdup_lane", "sdi", "ScSsSiSlSfSdSUcSUsSUiSUlSPcSPs">;
-def SCALAR_VDUP_LANEQ : IInst<"vdup_laneq", "sji", "ScSsSiSlSfSdSUcSUsSUiSUlSPcSPs">;
+def SCALAR_VDUP_LANE : IInst<"vdup_lane", "1.I", "ScSsSiSlSfSdSUcSUsSUiSUlSPcSPs">;
+def SCALAR_VDUP_LANEQ : IInst<"vdup_laneq", "1QI", "ScSsSiSlSfSdSUcSUsSUiSUlSPcSPs">;
 }
 
 // ARMv8.2-A FP16 vector intrinsics for A32/A64.
@@ -1441,234 +1442,234 @@ let ArchGuard = "defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC)" in {
   // ARMv8.2-A FP16 one-operand vector intrinsics.
 
   // Comparison
-  def CMEQH    : SInst<"vceqz", "ud", "hQh">;
-  def CMGEH    : SInst<"vcgez", "ud", "hQh">;
-  def CMGTH    : SInst<"vcgtz", "ud", "hQh">;
-  def CMLEH    : SInst<"vclez", "ud", "hQh">;
-  def CMLTH    : SInst<"vcltz", "ud", "hQh">;
+  def CMEQH    : SInst<"vceqz", "U.", "hQh">;
+  def CMGEH    : SInst<"vcgez", "U.", "hQh">;
+  def CMGTH    : SInst<"vcgtz", "U.", "hQh">;
+  def CMLEH    : SInst<"vclez", "U.", "hQh">;
+  def CMLTH    : SInst<"vcltz", "U.", "hQh">;
 
   // Vector conversion
-  def VCVT_F16     : SInst<"vcvt_f16", "Hd",  "sUsQsQUs">;
-  def VCVT_S16     : SInst<"vcvt_s16", "xd",  "hQh">;
-  def VCVT_U16     : SInst<"vcvt_u16", "ud",  "hQh">;
-  def VCVTA_S16    : SInst<"vcvta_s16", "xd", "hQh">;
-  def VCVTA_U16    : SInst<"vcvta_u16", "ud", "hQh">;
-  def VCVTM_S16    : SInst<"vcvtm_s16", "xd", "hQh">;
-  def VCVTM_U16    : SInst<"vcvtm_u16", "ud", "hQh">;
-  def VCVTN_S16    : SInst<"vcvtn_s16", "xd", "hQh">;
-  def VCVTN_U16    : SInst<"vcvtn_u16", "ud", "hQh">;
-  def VCVTP_S16    : SInst<"vcvtp_s16", "xd", "hQh">;
-  def VCVTP_U16    : SInst<"vcvtp_u16", "ud", "hQh">;
+  def VCVT_F16     : SInst<"vcvt_f16", "F(.!)",  "sUsQsQUs">;
+  def VCVT_S16     : SInst<"vcvt_s16", "S.",  "hQh">;
+  def VCVT_U16     : SInst<"vcvt_u16", "U.",  "hQh">;
+  def VCVTA_S16    : SInst<"vcvta_s16", "S.", "hQh">;
+  def VCVTA_U16    : SInst<"vcvta_u16", "U.", "hQh">;
+  def VCVTM_S16    : SInst<"vcvtm_s16", "S.", "hQh">;
+  def VCVTM_U16    : SInst<"vcvtm_u16", "U.", "hQh">;
+  def VCVTN_S16    : SInst<"vcvtn_s16", "S.", "hQh">;
+  def VCVTN_U16    : SInst<"vcvtn_u16", "U.", "hQh">;
+  def VCVTP_S16    : SInst<"vcvtp_s16", "S.", "hQh">;
+  def VCVTP_U16    : SInst<"vcvtp_u16", "U.", "hQh">;
 
   // Vector rounding
   let ArchGuard = "__ARM_ARCH >= 8 && defined(__ARM_FEATURE_DIRECTED_ROUNDING) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC)" in {
-    def FRINTZH      : SInst<"vrnd",  "dd", "hQh">;
-    def FRINTNH      : SInst<"vrndn", "dd", "hQh">;
-    def FRINTAH      : SInst<"vrnda", "dd", "hQh">;
-    def FRINTPH      : SInst<"vrndp", "dd", "hQh">;
-    def FRINTMH      : SInst<"vrndm", "dd", "hQh">;
-    def FRINTXH      : SInst<"vrndx", "dd", "hQh">;
+    def FRINTZH      : SInst<"vrnd",  "..", "hQh">;
+    def FRINTNH      : SInst<"vrndn", "..", "hQh">;
+    def FRINTAH      : SInst<"vrnda", "..", "hQh">;
+    def FRINTPH      : SInst<"vrndp", "..", "hQh">;
+    def FRINTMH      : SInst<"vrndm", "..", "hQh">;
+    def FRINTXH      : SInst<"vrndx", "..", "hQh">;
   }
 
   // Misc.
-  def VABSH        : SInst<"vabs", "dd", "hQh">;
-  def VNEGH        : SOpInst<"vneg", "dd", "hQh", OP_NEG>;
-  def VRECPEH      : SInst<"vrecpe", "dd", "hQh">;
-  def FRSQRTEH     : SInst<"vrsqrte", "dd", "hQh">;
+  def VABSH        : SInst<"vabs", "..", "hQh">;
+  def VNEGH        : SOpInst<"vneg", "..", "hQh", OP_NEG>;
+  def VRECPEH      : SInst<"vrecpe", "..", "hQh">;
+  def FRSQRTEH     : SInst<"vrsqrte", "..", "hQh">;
 
   // ARMv8.2-A FP16 two-operands vector intrinsics.
 
   // Misc.
-  def VADDH        : SOpInst<"vadd", "ddd", "hQh", OP_ADD>;
-  def VABDH        : SInst<"vabd", "ddd",  "hQh">;
-  def VSUBH         : SOpInst<"vsub", "ddd", "hQh", OP_SUB>;
+  def VADDH        : SOpInst<"vadd", "...", "hQh", OP_ADD>;
+  def VABDH        : SInst<"vabd", "...",  "hQh">;
+  def VSUBH         : SOpInst<"vsub", "...", "hQh", OP_SUB>;
 
   // Comparison
   let InstName = "vacge" in {
-    def VCAGEH     : SInst<"vcage", "udd", "hQh">;
-    def VCALEH     : SInst<"vcale", "udd", "hQh">;
+    def VCAGEH     : SInst<"vcage", "U..", "hQh">;
+    def VCALEH     : SInst<"vcale", "U..", "hQh">;
   }
   let InstName = "vacgt" in {
-    def VCAGTH     : SInst<"vcagt", "udd", "hQh">;
-    def VCALTH     : SInst<"vcalt", "udd", "hQh">;
+    def VCAGTH     : SInst<"vcagt", "U..", "hQh">;
+    def VCALTH     : SInst<"vcalt", "U..", "hQh">;
   }
-  def VCEQH        : SOpInst<"vceq", "udd", "hQh", OP_EQ>;
-  def VCGEH        : SOpInst<"vcge", "udd", "hQh", OP_GE>;
-  def VCGTH        : SOpInst<"vcgt", "udd", "hQh", OP_GT>;
+  def VCEQH        : SOpInst<"vceq", "U..", "hQh", OP_EQ>;
+  def VCGEH        : SOpInst<"vcge", "U..", "hQh", OP_GE>;
+  def VCGTH        : SOpInst<"vcgt", "U..", "hQh", OP_GT>;
   let InstName = "vcge" in
-    def VCLEH      : SOpInst<"vcle", "udd", "hQh", OP_LE>;
+    def VCLEH      : SOpInst<"vcle", "U..", "hQh", OP_LE>;
   let InstName = "vcgt" in
-    def VCLTH      : SOpInst<"vclt", "udd", "hQh", OP_LT>;
+    def VCLTH      : SOpInst<"vclt", "U..", "hQh", OP_LT>;
 
   // Vector conversion
   let isVCVT_N = 1 in {
-    def VCVT_N_F16 : SInst<"vcvt_n_f16", "Hdi", "sUsQsQUs">;
-    def VCVT_N_S16 : SInst<"vcvt_n_s16", "xdi", "hQh">;
-    def VCVT_N_U16 : SInst<"vcvt_n_u16", "udi", "hQh">;
+    def VCVT_N_F16 : SInst<"vcvt_n_f16", "F(.!)I", "sUsQsQUs">;
+    def VCVT_N_S16 : SInst<"vcvt_n_s16", "S.I", "hQh">;
+    def VCVT_N_U16 : SInst<"vcvt_n_u16", "U.I", "hQh">;
   }
 
   // Max/Min
-  def VMAXH         : SInst<"vmax", "ddd", "hQh">;
-  def VMINH         : SInst<"vmin", "ddd", "hQh">;
+  def VMAXH         : SInst<"vmax", "...", "hQh">;
+  def VMINH         : SInst<"vmin", "...", "hQh">;
   let ArchGuard = "__ARM_ARCH >= 8 && defined(__ARM_FEATURE_NUMERIC_MAXMIN) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC)" in {
-    def FMAXNMH       : SInst<"vmaxnm", "ddd", "hQh">;
-    def FMINNMH       : SInst<"vminnm", "ddd", "hQh">;
+    def FMAXNMH       : SInst<"vmaxnm", "...", "hQh">;
+    def FMINNMH       : SInst<"vminnm", "...", "hQh">;
   }
 
   // Multiplication/Division
-  def VMULH         : SOpInst<"vmul", "ddd", "hQh", OP_MUL>;
+  def VMULH         : SOpInst<"vmul", "...", "hQh", OP_MUL>;
 
   // Pairwise addition
-  def VPADDH        : SInst<"vpadd", "ddd", "h">;
+  def VPADDH        : SInst<"vpadd", "...", "h">;
 
   // Pairwise Max/Min
-  def VPMAXH        : SInst<"vpmax", "ddd", "h">;
-  def VPMINH        : SInst<"vpmin", "ddd", "h">;
+  def VPMAXH        : SInst<"vpmax", "...", "h">;
+  def VPMINH        : SInst<"vpmin", "...", "h">;
 
   // Reciprocal/Sqrt
-  def VRECPSH       : SInst<"vrecps", "ddd", "hQh">;
-  def VRSQRTSH      : SInst<"vrsqrts", "ddd", "hQh">;
+  def VRECPSH       : SInst<"vrecps", "...", "hQh">;
+  def VRSQRTSH      : SInst<"vrsqrts", "...", "hQh">;
 
   // ARMv8.2-A FP16 three-operands vector intrinsics.
 
   // Vector fused multiply-add operations
-  def VFMAH        : SInst<"vfma", "dddd", "hQh">;
-  def VFMSH        : SOpInst<"vfms", "dddd", "hQh", OP_FMLS>;
+  def VFMAH        : SInst<"vfma", "....", "hQh">;
+  def VFMSH        : SOpInst<"vfms", "....", "hQh", OP_FMLS>;
 
   // ARMv8.2-A FP16 lane vector intrinsics.
 
   // Mul lane
-  def VMUL_LANEH    : IOpInst<"vmul_lane", "ddgi", "hQh", OP_MUL_LN>;
-  def VMUL_NH       : IOpInst<"vmul_n", "dds", "hQh", OP_MUL_N>;
+  def VMUL_LANEH    : IOpInst<"vmul_lane", "..qI", "hQh", OP_MUL_LN>;
+  def VMUL_NH       : IOpInst<"vmul_n", "..1", "hQh", OP_MUL_N>;
 
   // Data processing intrinsics - section 5
 
   // Logical operations
   let isHiddenLInst = 1 in
-  def VBSLH    : SInst<"vbsl", "dudd", "hQh">;
+  def VBSLH    : SInst<"vbsl", ".U..", "hQh">;
 
   // Transposition operations
-  def VZIPH    : WInst<"vzip", "2dd", "hQh">;
-  def VUZPH    : WInst<"vuzp", "2dd", "hQh">;
-  def VTRNH    : WInst<"vtrn", "2dd", "hQh">;
+  def VZIPH    : WInst<"vzip", "2..", "hQh">;
+  def VUZPH    : WInst<"vuzp", "2..", "hQh">;
+  def VTRNH    : WInst<"vtrn", "2..", "hQh">;
 
 
   let ArchGuard = "!defined(__aarch64__)" in {
     // Set all lanes to same value.
     // Already implemented prior to ARMv8.2-A.
-    def VMOV_NH  : WOpInst<"vmov_n", "ds", "hQh", OP_DUP>;
-    def VDUP_NH  : WOpInst<"vdup_n", "ds", "hQh", OP_DUP>;
-    def VDUP_LANE1H : WOpInst<"vdup_lane", "dgi", "hQh", OP_DUP_LN>;
+    def VMOV_NH  : WOpInst<"vmov_n", ".1", "hQh", OP_DUP>;
+    def VDUP_NH  : WOpInst<"vdup_n", ".1", "hQh", OP_DUP>;
+    def VDUP_LANE1H : WOpInst<"vdup_lane", ".qI", "hQh", OP_DUP_LN>;
   }
 
   // Vector Extract
-  def VEXTH      : WInst<"vext", "dddi", "hQh">;
+  def VEXTH      : WInst<"vext", "...I", "hQh">;
 
   // Reverse vector elements
-  def VREV64H    : WOpInst<"vrev64", "dd", "hQh", OP_REV64>;
+  def VREV64H    : WOpInst<"vrev64", "..", "hQh", OP_REV64>;
 }
 
 // ARMv8.2-A FP16 vector intrinsics for A64 only.
 let ArchGuard = "defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(__aarch64__)" in {
 
   // Vector rounding
-  def FRINTIH      : SInst<"vrndi", "dd", "hQh">;
+  def FRINTIH      : SInst<"vrndi", "..", "hQh">;
 
   // Misc.
-  def FSQRTH       : SInst<"vsqrt", "dd", "hQh">;
+  def FSQRTH       : SInst<"vsqrt", "..", "hQh">;
 
   // Multiplication/Division
-  def MULXH         : SInst<"vmulx", "ddd", "hQh">;
-  def FDIVH         : IOpInst<"vdiv", "ddd",  "hQh", OP_DIV>;
+  def MULXH         : SInst<"vmulx", "...", "hQh">;
+  def FDIVH         : IOpInst<"vdiv", "...",  "hQh", OP_DIV>;
 
   // Pairwise addition
-  def VPADDH1       : SInst<"vpadd", "ddd", "Qh">;
+  def VPADDH1       : SInst<"vpadd", "...", "Qh">;
 
   // Pairwise Max/Min
-  def VPMAXH1       : SInst<"vpmax", "ddd", "Qh">;
-  def VPMINH1       : SInst<"vpmin", "ddd", "Qh">;
+  def VPMAXH1       : SInst<"vpmax", "...", "Qh">;
+  def VPMINH1       : SInst<"vpmin", "...", "Qh">;
 
   // Pairwise MaxNum/MinNum
-  def FMAXNMPH      : SInst<"vpmaxnm", "ddd", "hQh">;
-  def FMINNMPH      : SInst<"vpminnm", "ddd", "hQh">;
+  def FMAXNMPH      : SInst<"vpmaxnm", "...", "hQh">;
+  def FMINNMPH      : SInst<"vpminnm", "...", "hQh">;
 
   // ARMv8.2-A FP16 lane vector intrinsics.
 
   // FMA lane
-  def VFMA_LANEH   : IInst<"vfma_lane", "dddgi", "hQh">;
-  def VFMA_LANEQH  : IInst<"vfma_laneq", "dddji", "hQh">;
+  def VFMA_LANEH   : IInst<"vfma_lane", "...qI", "hQh">;
+  def VFMA_LANEQH  : IInst<"vfma_laneq", "...QI", "hQh">;
 
   // FMA lane with scalar argument
-  def FMLA_NH      : SOpInst<"vfma_n", "ddds", "hQh", OP_FMLA_N>;
+  def FMLA_NH      : SOpInst<"vfma_n", "...1", "hQh", OP_FMLA_N>;
   // Scalar floating point fused multiply-add (scalar, by element)
-  def SCALAR_FMLA_LANEH  : IInst<"vfma_lane", "sssdi", "Sh">;
-  def SCALAR_FMLA_LANEQH : IInst<"vfma_laneq", "sssji", "Sh">;
+  def SCALAR_FMLA_LANEH  : IInst<"vfma_lane", "111.I", "Sh">;
+  def SCALAR_FMLA_LANEQH : IInst<"vfma_laneq", "111QI", "Sh">;
 
   // FMS lane
-  def VFMS_LANEH   : IOpInst<"vfms_lane", "dddgi", "hQh", OP_FMS_LN>;
-  def VFMS_LANEQH  : IOpInst<"vfms_laneq", "dddji", "hQh", OP_FMS_LNQ>;
+  def VFMS_LANEH   : IOpInst<"vfms_lane", "...qI", "hQh", OP_FMS_LN>;
+  def VFMS_LANEQH  : IOpInst<"vfms_laneq", "...QI", "hQh", OP_FMS_LNQ>;
   // FMS lane with scalar argument
-  def FMLS_NH      : SOpInst<"vfms_n", "ddds", "hQh", OP_FMLS_N>;
+  def FMLS_NH      : SOpInst<"vfms_n", "...1", "hQh", OP_FMLS_N>;
   // Scalar floating foint fused multiply-subtract (scalar, by element)
-  def SCALAR_FMLS_LANEH  : IOpInst<"vfms_lane", "sssdi", "Sh", OP_FMS_LN>;
-  def SCALAR_FMLS_LANEQH : IOpInst<"vfms_laneq", "sssji", "Sh", OP_FMS_LNQ>;
+  def SCALAR_FMLS_LANEH  : IOpInst<"vfms_lane", "111.I", "Sh", OP_FMS_LN>;
+  def SCALAR_FMLS_LANEQH : IOpInst<"vfms_laneq", "111QI", "Sh", OP_FMS_LNQ>;
 
   // Mul lane
-  def VMUL_LANEQH   : IOpInst<"vmul_laneq", "ddji", "hQh", OP_MUL_LN>;
+  def VMUL_LANEQH   : IOpInst<"vmul_laneq", "..QI", "hQh", OP_MUL_LN>;
   // Scalar floating point  multiply (scalar, by element)
-  def SCALAR_FMUL_LANEH  : IOpInst<"vmul_lane", "ssdi", "Sh", OP_SCALAR_MUL_LN>;
-  def SCALAR_FMUL_LANEQH : IOpInst<"vmul_laneq", "ssji", "Sh", OP_SCALAR_MUL_LN>;
+  def SCALAR_FMUL_LANEH  : IOpInst<"vmul_lane", "11.I", "Sh", OP_SCALAR_MUL_LN>;
+  def SCALAR_FMUL_LANEQH : IOpInst<"vmul_laneq", "11QI", "Sh", OP_SCALAR_MUL_LN>;
 
   // Mulx lane
-  def VMULX_LANEH   : IOpInst<"vmulx_lane", "ddgi", "hQh", OP_MULX_LN>;
-  def VMULX_LANEQH  : IOpInst<"vmulx_laneq", "ddji", "hQh", OP_MULX_LN>;
-  def VMULX_NH      : IOpInst<"vmulx_n", "dds", "hQh", OP_MULX_N>;
+  def VMULX_LANEH   : IOpInst<"vmulx_lane", "..qI", "hQh", OP_MULX_LN>;
+  def VMULX_LANEQH  : IOpInst<"vmulx_laneq", "..QI", "hQh", OP_MULX_LN>;
+  def VMULX_NH      : IOpInst<"vmulx_n", "..1", "hQh", OP_MULX_N>;
   // Scalar floating point  mulx (scalar, by element)
-  def SCALAR_FMULX_LANEH : IInst<"vmulx_lane", "ssdi", "Sh">;
-  def SCALAR_FMULX_LANEQH : IInst<"vmulx_laneq", "ssji", "Sh">;
+  def SCALAR_FMULX_LANEH : IInst<"vmulx_lane", "11.I", "Sh">;
+  def SCALAR_FMULX_LANEQH : IInst<"vmulx_laneq", "11QI", "Sh">;
 
   // ARMv8.2-A FP16 reduction vector intrinsics.
-  def VMAXVH   : SInst<"vmaxv", "sd", "hQh">;
-  def VMINVH   : SInst<"vminv", "sd", "hQh">;
-  def FMAXNMVH : SInst<"vmaxnmv", "sd", "hQh">;
-  def FMINNMVH : SInst<"vminnmv", "sd", "hQh">;
+  def VMAXVH   : SInst<"vmaxv", "1.", "hQh">;
+  def VMINVH   : SInst<"vminv", "1.", "hQh">;
+  def FMAXNMVH : SInst<"vmaxnmv", "1.", "hQh">;
+  def FMINNMVH : SInst<"vminnmv", "1.", "hQh">;
 
   // Permutation
-  def VTRN1H     : SOpInst<"vtrn1", "ddd", "hQh", OP_TRN1>;
-  def VZIP1H     : SOpInst<"vzip1", "ddd", "hQh", OP_ZIP1>;
-  def VUZP1H     : SOpInst<"vuzp1", "ddd", "hQh", OP_UZP1>;
-  def VTRN2H     : SOpInst<"vtrn2", "ddd", "hQh", OP_TRN2>;
-  def VZIP2H     : SOpInst<"vzip2", "ddd", "hQh", OP_ZIP2>;
-  def VUZP2H     : SOpInst<"vuzp2", "ddd", "hQh", OP_UZP2>;
-
-  def SCALAR_VDUP_LANEH  : IInst<"vdup_lane", "sdi", "Sh">;
-  def SCALAR_VDUP_LANEQH : IInst<"vdup_laneq", "sji", "Sh">;
+  def VTRN1H     : SOpInst<"vtrn1", "...", "hQh", OP_TRN1>;
+  def VZIP1H     : SOpInst<"vzip1", "...", "hQh", OP_ZIP1>;
+  def VUZP1H     : SOpInst<"vuzp1", "...", "hQh", OP_UZP1>;
+  def VTRN2H     : SOpInst<"vtrn2", "...", "hQh", OP_TRN2>;
+  def VZIP2H     : SOpInst<"vzip2", "...", "hQh", OP_ZIP2>;
+  def VUZP2H     : SOpInst<"vuzp2", "...", "hQh", OP_UZP2>;
+
+  def SCALAR_VDUP_LANEH  : IInst<"vdup_lane", "1.I", "Sh">;
+  def SCALAR_VDUP_LANEQH : IInst<"vdup_laneq", "1QI", "Sh">;
 }
 
 // v8.2-A dot product instructions.
 let ArchGuard = "defined(__ARM_FEATURE_DOTPROD)" in {
-  def DOT : SInst<"vdot", "dd88", "iQiUiQUi">;
-  def DOT_LANE : SOpInst<"vdot_lane", "dd87i", "iUiQiQUi", OP_DOT_LN>;
+  def DOT : SInst<"vdot", "..(<<)(<<)", "iQiUiQUi">;
+  def DOT_LANE : SOpInst<"vdot_lane", "..(<<)(<<q)I", "iUiQiQUi", OP_DOT_LN>;
 }
 let ArchGuard = "defined(__ARM_FEATURE_DOTPROD) && defined(__aarch64__)" in {
   // Variants indexing into a 128-bit vector are A64 only.
-  def UDOT_LANEQ : SOpInst<"vdot_laneq", "dd89i", "iUiQiQUi", OP_DOT_LNQ>;
+  def UDOT_LANEQ : SOpInst<"vdot_laneq", "..(<<)(<<Q)I", "iUiQiQUi", OP_DOT_LNQ>;
 }
 
 // v8.2-A FP16 fused multiply-add long instructions.
 let ArchGuard = "defined(__ARM_FEATURE_FP16FML) && defined(__aarch64__)" in {
-  def VFMLAL_LOW  : SInst<"vfmlal_low",  "nndd", "hQh">;
-  def VFMLSL_LOW  : SInst<"vfmlsl_low",  "nndd", "hQh">;
-  def VFMLAL_HIGH : SInst<"vfmlal_high", "nndd", "hQh">;
-  def VFMLSL_HIGH : SInst<"vfmlsl_high", "nndd", "hQh">;
-
-  def VFMLAL_LANE_LOW  : SOpInst<"vfmlal_lane_low",  "ffH0i", "hQh", OP_FMLAL_LN>;
-  def VFMLSL_LANE_LOW  : SOpInst<"vfmlsl_lane_low",  "ffH0i", "hQh", OP_FMLSL_LN>;
-  def VFMLAL_LANE_HIGH : SOpInst<"vfmlal_lane_high", "ffH0i", "hQh", OP_FMLAL_LN_Hi>;
-  def VFMLSL_LANE_HIGH : SOpInst<"vfmlsl_lane_high", "ffH0i", "hQh", OP_FMLSL_LN_Hi>;
-
-  def VFMLAL_LANEQ_LOW  : SOpInst<"vfmlal_laneq_low",  "ffH1i", "hQh", OP_FMLAL_LN>;
-  def VFMLSL_LANEQ_LOW  : SOpInst<"vfmlsl_laneq_low",  "ffH1i", "hQh", OP_FMLSL_LN>;
-  def VFMLAL_LANEQ_HIGH : SOpInst<"vfmlal_laneq_high", "ffH1i", "hQh", OP_FMLAL_LN_Hi>;
-  def VFMLSL_LANEQ_HIGH : SOpInst<"vfmlsl_laneq_high", "ffH1i", "hQh", OP_FMLSL_LN_Hi>;
+  def VFMLAL_LOW  : SInst<"vfmlal_low",  ">>..", "hQh">;
+  def VFMLSL_LOW  : SInst<"vfmlsl_low",  ">>..", "hQh">;
+  def VFMLAL_HIGH : SInst<"vfmlal_high", ">>..", "hQh">;
+  def VFMLSL_HIGH : SInst<"vfmlsl_high", ">>..", "hQh">;
+
+  def VFMLAL_LANE_LOW  : SOpInst<"vfmlal_lane_low",  "(F>)(F>)F(Fq)I", "hQh", OP_FMLAL_LN>;
+  def VFMLSL_LANE_LOW  : SOpInst<"vfmlsl_lane_low",  "(F>)(F>)F(Fq)I", "hQh", OP_FMLSL_LN>;
+  def VFMLAL_LANE_HIGH : SOpInst<"vfmlal_lane_high", "(F>)(F>)F(Fq)I", "hQh", OP_FMLAL_LN_Hi>;
+  def VFMLSL_LANE_HIGH : SOpInst<"vfmlsl_lane_high", "(F>)(F>)F(Fq)I", "hQh", OP_FMLSL_LN_Hi>;
+
+  def VFMLAL_LANEQ_LOW  : SOpInst<"vfmlal_laneq_low",  "(F>)(F>)F(FQ)I", "hQh", OP_FMLAL_LN>;
+  def VFMLSL_LANEQ_LOW  : SOpInst<"vfmlsl_laneq_low",  "(F>)(F>)F(FQ)I", "hQh", OP_FMLSL_LN>;
+  def VFMLAL_LANEQ_HIGH : SOpInst<"vfmlal_laneq_high", "(F>)(F>)F(FQ)I", "hQh", OP_FMLAL_LN_Hi>;
+  def VFMLSL_LANEQ_HIGH : SOpInst<"vfmlsl_laneq_high", "(F>)(F>)F(FQ)I", "hQh", OP_FMLSL_LN_Hi>;
 }

diff  --git a/clang/include/clang/Basic/arm_neon_incl.td b/clang/include/clang/Basic/arm_neon_incl.td
index 984ed787037f..28b00d162a00 100644
--- a/clang/include/clang/Basic/arm_neon_incl.td
+++ b/clang/include/clang/Basic/arm_neon_incl.td
@@ -198,10 +198,8 @@ def OP_UNAVAILABLE : Operation {
 //
 // The prototype is a string that defines the return type of the intrinsic
 // and the type of each argument. The return type and every argument gets a
-// "modifier" that can change in some way the "base type" of the intrinsic.
-//
-// The modifier 'd' means "default" and does not modify the base type in any
-// way. The available modifiers are given below.
+// set of "modifiers" that can change in some way the "base type" of the
+// intrinsic.
 //
 // Typespecs
 // ---------
@@ -226,41 +224,34 @@ def OP_UNAVAILABLE : Operation {
 // -------------------
 // prototype: return (arg, arg, ...)
 //
-// v: void
-// t: best-fit integer (int/poly args)
-// x: signed integer   (int/float args)
-// u: unsigned integer (int/float args)
-// f: float (int args)
-// F: double (int args)
-// H: half (int args)
-// 0: half (int args), ignore 'Q' size modifier.
-// 1: half (int args), force 'Q' size modifier.
-// d: default
-// g: default, ignore 'Q' size modifier.
-// j: default, force 'Q' size modifier.
-// w: double width elements, same num elts
-// n: double width elements, half num elts
-// h: half width elements, double num elts
-// q: half width elements, quad num elts
-// e: half width elements, double num elts, unsigned
-// m: half width elements, same num elts
-// i: constant int
-// l: constant uint64
-// s: scalar of element type
-// z: scalar of half width element type, signed
-// r: scalar of double width element type, signed
-// b: scalar of unsigned integer/long type (int/float args)
-// $: scalar of signed integer/long type (int/float args)
-// y: scalar of float
-// o: scalar of double
-// k: default elt width, double num elts
-// 2,3,4: array of default vectors
-// B,C,D: array of default elts, force 'Q' size modifier.
-// p: pointer type
-// c: const pointer type
-// 7: vector of 8-bit elements, ignore 'Q' size modifier
-// 8: vector of 8-bit elements, same width as default type
-// 9: vector of 8-bit elements, force 'Q' size modifier
+// Each type modifier is either a single character, or a group surrounded by
+// parentheses.
+//
+// .: default
+// v: change to void category.
+// S: change to signed integer category.
+// U: change to unsigned integer category.
+// F: change to floating category.
+// P: change to polynomial category.
+// p: change polynomial to equivalent integer category. Otherwise nop.
+//
+// >: double element width (vector size unchanged).
+// <: half element width (vector size unchanged).
+//
+// 1: change to scalar.
+// 2: change to struct of two vectors.
+// 3: change to struct of three vectors.
+// 4: change to struct of four vectors.
+//
+// *: make a pointer argument.
+// c: make a constant argument (for pointers).
+//
+// Q: force 128-bit width.
+// q: force 64-bit width.
+//
+// I: make 32-bit signed scalar immediate
+// !: make this the key type passed to CGBuiltin.cpp in a polymorphic call.
+
 
 // Every intrinsic subclasses Inst.
 class Inst <string n, string p, string t, Operation o> {

diff  --git a/clang/test/CodeGen/aarch64-neon-intrinsics.c b/clang/test/CodeGen/aarch64-neon-intrinsics.c
index b29d877dd8ec..7744b4f4a159 100644
--- a/clang/test/CodeGen/aarch64-neon-intrinsics.c
+++ b/clang/test/CodeGen/aarch64-neon-intrinsics.c
@@ -17756,8 +17756,6 @@ float32_t test_vminnmv_f32(float32x2_t a) {
 }
 
 // CHECK-LABEL: @test_vpaddq_s64(
-// CHECK:   [[TMP0:%.*]] = bitcast <2 x i64> %a to <16 x i8>
-// CHECK:   [[TMP1:%.*]] = bitcast <2 x i64> %b to <16 x i8>
 // CHECK:   [[VPADDQ_V2_I:%.*]] = call <2 x i64> @llvm.aarch64.neon.addp.v2i64(<2 x i64> %a, <2 x i64> %b)
 // CHECK:   [[VPADDQ_V3_I:%.*]] = bitcast <2 x i64> [[VPADDQ_V2_I]] to <16 x i8>
 // CHECK:   ret <2 x i64> [[VPADDQ_V2_I]]
@@ -17766,8 +17764,6 @@ int64x2_t test_vpaddq_s64(int64x2_t a, int64x2_t b) {
 }
 
 // CHECK-LABEL: @test_vpaddq_u64(
-// CHECK:   [[TMP0:%.*]] = bitcast <2 x i64> %a to <16 x i8>
-// CHECK:   [[TMP1:%.*]] = bitcast <2 x i64> %b to <16 x i8>
 // CHECK:   [[VPADDQ_V2_I:%.*]] = call <2 x i64> @llvm.aarch64.neon.addp.v2i64(<2 x i64> %a, <2 x i64> %b)
 // CHECK:   [[VPADDQ_V3_I:%.*]] = bitcast <2 x i64> [[VPADDQ_V2_I]] to <16 x i8>
 // CHECK:   ret <2 x i64> [[VPADDQ_V2_I]]

diff  --git a/clang/test/CodeGen/arm_neon_intrinsics.c b/clang/test/CodeGen/arm_neon_intrinsics.c
index 5c34d1c37de0..0ec1198f9901 100644
--- a/clang/test/CodeGen/arm_neon_intrinsics.c
+++ b/clang/test/CodeGen/arm_neon_intrinsics.c
@@ -2147,6 +2147,13 @@ int8x8_t test_vcreate_s8(uint64_t a) {
   return vclz_s8(vcreate_s8(a));
 }
 
+// CHECK-LABEL: @test_vcreate_imm
+// CHECK: [[RES:%.*]] = bitcast i64 0 to <4 x i16>
+// CHECK: ret <4 x i16> [[RES]]
+int16x4_t test_vcreate_imm(void) {
+  return vcreate_s16(0);
+}
+
 // CHECK-LABEL: @test_vcreate_s16(
 // CHECK:   [[TMP0:%.*]] = bitcast i64 %a to <4 x i16>
 // CHECK:   [[TMP1:%.*]] = bitcast <4 x i16> [[TMP0]] to <8 x i8>

diff  --git a/clang/utils/TableGen/NeonEmitter.cpp b/clang/utils/TableGen/NeonEmitter.cpp
index cdf761b00c61..a0f3fb2ddc08 100644
--- a/clang/utils/TableGen/NeonEmitter.cpp
+++ b/clang/utils/TableGen/NeonEmitter.cpp
@@ -161,11 +161,11 @@ class Type {
         Pointer(false), ScalarForMangling(false), NoManglingQ(false),
         Bitwidth(0), ElementBitwidth(0), NumVectors(0) {}
 
-  Type(TypeSpec TS, char CharMod)
+  Type(TypeSpec TS, StringRef CharMods)
       : TS(std::move(TS)), Kind(Void), Immediate(false),
         Constant(false), Pointer(false), ScalarForMangling(false),
         NoManglingQ(false), Bitwidth(0), ElementBitwidth(0), NumVectors(0) {
-    applyModifier(CharMod);
+    applyModifiers(CharMods);
   }
 
   /// Returns a type representing "void".
@@ -181,13 +181,15 @@ class Type {
   bool noManglingQ() const { return NoManglingQ; }
 
   bool isPointer() const { return Pointer; }
+  bool isValue() const { return !isVoid() && !isPointer(); }
+  bool isScalar() const { return isValue() && NumVectors == 0; }
+  bool isVector() const { return isValue() && NumVectors > 0; }
+  bool isConstPointer() const { return Constant; }
   bool isFloating() const { return Kind == Float; }
   bool isInteger() const { return Kind == SInt || Kind == UInt; }
   bool isPoly() const { return Kind == Poly; }
   bool isSigned() const { return Kind == SInt; }
   bool isImmediate() const { return Immediate; }
-  bool isScalar() const { return NumVectors == 0; }
-  bool isVector() const { return NumVectors > 0; }
   bool isFloat() const { return isFloating() && ElementBitwidth == 32; }
   bool isDouble() const { return isFloating() && ElementBitwidth == 64; }
   bool isHalf() const { return isFloating() && ElementBitwidth == 16; }
@@ -205,11 +207,11 @@ class Type {
   // Mutator functions
   //
   void makeUnsigned() {
-    assert(isInteger() && "not a potentially signed type");
+    assert(!isVoid() && "not a potentially signed type");
     Kind = UInt;
   }
   void makeSigned() {
-    assert(isInteger() && "not a potentially signed type");
+    assert(!isVoid() && "not a potentially signed type");
     Kind = SInt;
   }
 
@@ -267,8 +269,8 @@ class Type {
   /// seen. This is needed by applyModifier as some modifiers
   /// only take effect if the type size was changed by "Q" or "H".
   void applyTypespec(bool &Quad);
-  /// Applies a prototype modifiers to the type.
-  void applyModifier(char Mod);
+  /// Applies prototype modifiers to the type.
+  void applyModifiers(StringRef Mods);
 };
 
 //===----------------------------------------------------------------------===//
@@ -299,8 +301,8 @@ class Intrinsic {
 
   /// The Record this intrinsic was created from.
   Record *R;
-  /// The unmangled name and prototype.
-  std::string Name, Proto;
+  /// The unmangled name.
+  std::string Name;
   /// The input and output typespecs. InTS == OutTS except when
   /// CartesianProductOfTypes is 1 - this is the case for vreinterpret.
   TypeSpec OutTS, InTS;
@@ -323,6 +325,8 @@ class Intrinsic {
 
   /// The types of return value [0] and parameters [1..].
   std::vector<Type> Types;
+  /// The index of the key type passed to CGBuiltin.cpp for polymorphic calls.
+  int PolymorphicKeyType;
   /// The local variables defined.
   std::map<std::string, Variable> Variables;
   /// NeededEarly - set if any other intrinsic depends on this intrinsic.
@@ -358,34 +362,39 @@ class Intrinsic {
   Intrinsic(Record *R, StringRef Name, StringRef Proto, TypeSpec OutTS,
             TypeSpec InTS, ClassKind CK, ListInit *Body, NeonEmitter &Emitter,
             StringRef Guard, bool IsUnavailable, bool BigEndianSafe)
-      : R(R), Name(Name.str()), Proto(Proto.str()), OutTS(OutTS), InTS(InTS),
-        CK(CK), Body(Body), Guard(Guard.str()), IsUnavailable(IsUnavailable),
-        BigEndianSafe(BigEndianSafe), NeededEarly(false), UseMacro(false),
-        BaseType(OutTS, 'd'), InBaseType(InTS, 'd'), Emitter(Emitter) {
-    // If this builtin takes an immediate argument, we need to #define it rather
-    // than use a standard declaration, so that SemaChecking can range check
-    // the immediate passed by the user.
-    if (Proto.find('i') != std::string::npos)
-      UseMacro = true;
-
-    // Pointer arguments need to use macros to avoid hiding aligned attributes
-    // from the pointer type.
-    if (Proto.find('p') != std::string::npos ||
-        Proto.find('c') != std::string::npos)
-      UseMacro = true;
-
-    // It is not permitted to pass or return an __fp16 by value, so intrinsics
-    // taking a scalar float16_t must be implemented as macros.
-    if (OutTS.find('h') != std::string::npos &&
-        Proto.find('s') != std::string::npos)
-      UseMacro = true;
-
+      : R(R), Name(Name.str()), OutTS(OutTS), InTS(InTS), CK(CK), Body(Body),
+        Guard(Guard.str()), IsUnavailable(IsUnavailable),
+        BigEndianSafe(BigEndianSafe), PolymorphicKeyType(0), NeededEarly(false),
+        UseMacro(false), BaseType(OutTS, "."), InBaseType(InTS, "."),
+        Emitter(Emitter) {
     // Modify the TypeSpec per-argument to get a concrete Type, and create
     // known variables for each.
     // Types[0] is the return value.
-    Types.emplace_back(OutTS, Proto[0]);
-    for (unsigned I = 1; I < Proto.size(); ++I)
-      Types.emplace_back(InTS, Proto[I]);
+    unsigned Pos = 0;
+    Types.emplace_back(OutTS, getNextModifiers(Proto, Pos));
+    StringRef Mods = getNextModifiers(Proto, Pos);
+    while (!Mods.empty()) {
+      Types.emplace_back(InTS, Mods);
+      if (Mods.find("!") != StringRef::npos)
+        PolymorphicKeyType = Types.size() - 1;
+
+      Mods = getNextModifiers(Proto, Pos);
+    }
+
+    for (auto Type : Types) {
+      // If this builtin takes an immediate argument, we need to #define it rather
+      // than use a standard declaration, so that SemaChecking can range check
+      // the immediate passed by the user.
+
+      // Pointer arguments need to use macros to avoid hiding aligned attributes
+      // from the pointer type.
+
+      // It is not permitted to pass or return an __fp16 by value, so intrinsics
+      // taking a scalar float16_t must be implemented as macros.
+      if (Type.isImmediate() || Type.isPointer() ||
+          (Type.isScalar() && Type.isHalf()))
+        UseMacro = true;
+    }
   }
 
   /// Get the Record that this intrinsic is based off.
@@ -401,23 +410,24 @@ class Intrinsic {
 
   /// Return true if the intrinsic takes an immediate operand.
   bool hasImmediate() const {
-    return Proto.find('i') != std::string::npos;
+    return std::any_of(Types.begin(), Types.end(),
+                       [](const Type &T) { return T.isImmediate(); });
   }
 
   /// Return the parameter index of the immediate operand.
   unsigned getImmediateIdx() const {
-    assert(hasImmediate());
-    unsigned Idx = Proto.find('i');
-    assert(Idx > 0 && "Can't return an immediate!");
-    return Idx - 1;
+    for (unsigned Idx = 0; Idx < Types.size(); ++Idx)
+      if (Types[Idx].isImmediate())
+        return Idx - 1;
+    llvm_unreachable("Intrinsic has no immediate");
   }
 
-  unsigned getNumParams() const { return Proto.size() - 1; }
+
+  unsigned getNumParams() const { return Types.size() - 1; }
   Type getReturnType() const { return Types[0]; }
   Type getParamType(unsigned I) const { return Types[I + 1]; }
   Type getBaseType() const { return BaseType; }
-  /// Return the raw prototype string.
-  std::string getProto() const { return Proto; }
+  Type getPolymorphicKeyType() const { return Types[PolymorphicKeyType]; }
 
   /// Return true if the prototype has a scalar argument.
   bool protoHasScalar() const;
@@ -471,6 +481,8 @@ class Intrinsic {
   void indexBody();
 
 private:
+  StringRef getNextModifiers(StringRef Proto, unsigned &Pos) const;
+
   std::string mangleName(std::string Name, ClassKind CK) const;
 
   void initVariables();
@@ -614,10 +626,14 @@ std::string Type::builtin_str() const {
   if (isVoid())
     return "v";
 
-  if (Pointer)
+  if (isPointer()) {
     // All pointers are void pointers.
-    S += "v";
-  else if (isInteger())
+    S = "v";
+    if (isConstPointer())
+      S += "C";
+    S += "*";
+    return S;
+  } else if (isInteger())
     switch (ElementBitwidth) {
     case 8: S += "c"; break;
     case 16: S += "s"; break;
@@ -634,10 +650,11 @@ std::string Type::builtin_str() const {
     default: llvm_unreachable("Unhandled case!");
     }
 
+  // FIXME: NECESSARY???????????????????????????????????????????????????????????????????????
   if (isChar() && !isPointer() && isSigned())
     // Make chars explicitly signed.
     S = "S" + S;
-  else if (!isPointer() && isInteger() && !isSigned())
+  else if (isInteger() && !isSigned())
     S = "U" + S;
 
   // Constant indices are "int", but have the "constant expression" modifier.
@@ -646,11 +663,8 @@ std::string Type::builtin_str() const {
     S = "I" + S;
   }
 
-  if (isScalar()) {
-    if (Constant) S += "C";
-    if (Pointer) S += "*";
+  if (isScalar())
     return S;
-  }
 
   std::string Ret;
   for (unsigned I = 0; I < NumVectors; ++I)
@@ -812,202 +826,77 @@ void Type::applyTypespec(bool &Quad) {
   Bitwidth = Quad ? 128 : 64;
 }
 
-void Type::applyModifier(char Mod) {
+void Type::applyModifiers(StringRef Mods) {
   bool AppliedQuad = false;
   applyTypespec(AppliedQuad);
 
-  switch (Mod) {
-  case 'v':
-    Kind = Void;
-    break;
-  case 't':
-    if (isPoly())
+  for (char Mod : Mods) {
+    switch (Mod) {
+    case '.':
+      break;
+    case 'v':
+      Kind = Void;
+      break;
+    case 'S':
+      Kind = SInt;
+      break;
+    case 'U':
       Kind = UInt;
-    break;
-  case 'b':
-    Kind = UInt;
-    NumVectors = 0;
-    Bitwidth = ElementBitwidth;
-    break;
-  case '$':
-    Kind = SInt;
-    NumVectors = 0;
-    Bitwidth = ElementBitwidth;
-    break;
-  case 'u':
-    Kind = UInt;
-    break;
-  case 'x':
-    assert(!isPoly() && "'u' can't be used with poly types!");
-    Kind = SInt;
-    break;
-  case 'o':
-    Bitwidth = ElementBitwidth = 64;
-    NumVectors = 0;
-    Kind = Float;
-    break;
-  case 'y':
-    Bitwidth = ElementBitwidth = 32;
-    NumVectors = 0;
-    Kind = Float;
-    break;
-  case 'Y':
-    Bitwidth = ElementBitwidth = 16;
-    NumVectors = 0;
-    Kind = Float;
-    break;
-  case 'I':
-    Bitwidth = ElementBitwidth = 32;
-    NumVectors = 0;
-    Kind = SInt;
-    break;
-  case 'L':
-    Bitwidth = ElementBitwidth = 64;
-    NumVectors = 0;
-    Kind = SInt;
-    break;
-  case 'U':
-    Bitwidth = ElementBitwidth = 32;
-    NumVectors = 0;
-    Kind = UInt;
-    break;
-  case 'O':
-    Bitwidth = ElementBitwidth = 64;
-    NumVectors = 0;
-    Kind = UInt;
-    break;
-  case 'f':
-    Kind = Float;
-    ElementBitwidth = 32;
-    break;
-  case 'F':
-    Kind = Float;
-    ElementBitwidth = 64;
-    break;
-  case 'H':
-    Kind = Float;
-    ElementBitwidth = 16;
-    break;
-  case '0':
-    Kind = Float;
-    if (AppliedQuad)
-      Bitwidth /= 2;
-    ElementBitwidth = 16;
-    break;
-  case '1':
-    Kind = Float;
-    if (!AppliedQuad)
-      Bitwidth *= 2;
-    ElementBitwidth = 16;
-    break;
-  case 'g':
-    if (AppliedQuad)
-      Bitwidth /= 2;
-    break;
-  case 'j':
-    if (!AppliedQuad)
-      Bitwidth *= 2;
-    break;
-  case 'w':
-    ElementBitwidth *= 2;
-    Bitwidth *= 2;
-    break;
-  case 'n':
-    ElementBitwidth *= 2;
-    break;
-  case 'i':
-    Kind = SInt;
-    ElementBitwidth = Bitwidth = 32;
-    NumVectors = 0;
-    Immediate = true;
-    break;
-  case 'l':
-    Kind = UInt;
-    ElementBitwidth = Bitwidth = 64;
-    NumVectors = 0;
-    Immediate = true;
-    break;
-  case 'z':
-    ElementBitwidth /= 2;
-    Bitwidth = ElementBitwidth;
-    NumVectors = 0;
-    break;
-  case 'r':
-    ElementBitwidth *= 2;
-    Bitwidth = ElementBitwidth;
-    NumVectors = 0;
-    break;
-  case 's':
-    Bitwidth = ElementBitwidth;
-    NumVectors = 0;
-    break;
-  case 'k':
-    Bitwidth *= 2;
-    break;
-  case 'c':
-    Constant = true;
-    LLVM_FALLTHROUGH;
-  case 'p':
-    Pointer = true;
-    Bitwidth = ElementBitwidth;
-    NumVectors = 0;
-    break;
-  case 'h':
-    ElementBitwidth /= 2;
-    break;
-  case 'q':
-    ElementBitwidth /= 2;
-    Bitwidth *= 2;
-    break;
-  case 'e':
-    ElementBitwidth /= 2;
-    Kind = UInt;
-    break;
-  case 'm':
-    ElementBitwidth /= 2;
-    Bitwidth /= 2;
-    break;
-  case 'd':
-    break;
-  case '2':
-    NumVectors = 2;
-    break;
-  case '3':
-    NumVectors = 3;
-    break;
-  case '4':
-    NumVectors = 4;
-    break;
-  case 'B':
-    NumVectors = 2;
-    if (!AppliedQuad)
-      Bitwidth *= 2;
-    break;
-  case 'C':
-    NumVectors = 3;
-    if (!AppliedQuad)
-      Bitwidth *= 2;
-    break;
-  case 'D':
-    NumVectors = 4;
-    if (!AppliedQuad)
-      Bitwidth *= 2;
-    break;
-  case '7':
-    if (AppliedQuad)
-      Bitwidth /= 2;
-    ElementBitwidth = 8;
-    break;
-  case '8':
-    ElementBitwidth = 8;
-    break;
-  case '9':
-    if (!AppliedQuad)
-      Bitwidth *= 2;
-    ElementBitwidth = 8;
-    break;
-  default:
-    llvm_unreachable("Unhandled character!");
+      break;
+    case 'F':
+      Kind = Float;
+      break;
+    case 'P':
+      Kind = Poly;
+      break;
+    case '>':
+      assert(ElementBitwidth < 128);
+      ElementBitwidth *= 2;
+      break;
+    case '<':
+      assert(ElementBitwidth > 8);
+      ElementBitwidth /= 2;
+      break;
+    case '1':
+      NumVectors = 0;
+      break;
+    case '2':
+      NumVectors = 2;
+      break;
+    case '3':
+      NumVectors = 3;
+      break;
+    case '4':
+      NumVectors = 4;
+      break;
+    case '*':
+      Pointer = true;
+      break;
+    case 'c':
+      Constant = true;
+      break;
+    case 'Q':
+      Bitwidth = 128;
+      break;
+    case 'q':
+      Bitwidth = 64;
+      break;
+    case 'I':
+      Kind = SInt;
+      ElementBitwidth = Bitwidth = 32;
+      NumVectors = 0;
+      Immediate = true;
+      break;
+    case 'p':
+      if (isPoly())
+        Kind = UInt;
+      break;
+    case '!':
+      // Key type, handled elsewhere.
+      break;
+    default:
+      llvm_unreachable("Unhandled character!");
+    }
   }
 }
 
@@ -1015,6 +904,19 @@ void Type::applyModifier(char Mod) {
 // Intrinsic implementation
 //===----------------------------------------------------------------------===//
 
+StringRef Intrinsic::getNextModifiers(StringRef Proto, unsigned &Pos) const {
+  if (Proto.size() == Pos)
+    return StringRef();
+  else if (Proto[Pos] != '(')
+    return Proto.substr(Pos++, 1);
+
+  size_t Start = Pos + 1;
+  size_t End = Proto.find(')', Start);
+  assert_with_loc(End != StringRef::npos, "unmatched modifier group paren");
+  Pos = End + 1;
+  return Proto.slice(Start, End);
+}
+
 std::string Intrinsic::getInstTypeCode(Type T, ClassKind CK) const {
   char typeCode = '\0';
   bool printNumber = true;
@@ -1053,17 +955,13 @@ std::string Intrinsic::getInstTypeCode(Type T, ClassKind CK) const {
   return S;
 }
 
-static bool isFloatingPointProtoModifier(char Mod) {
-  return Mod == 'F' || Mod == 'f' || Mod == 'H' || Mod == 'Y' || Mod == 'I';
-}
-
 std::string Intrinsic::getBuiltinTypeStr() {
   ClassKind LocalCK = getClassKind(true);
   std::string S;
 
   Type RetT = getReturnType();
   if ((LocalCK == ClassI || LocalCK == ClassW) && RetT.isScalar() &&
-      !RetT.isFloating() && !RetT.isVoid())
+      !RetT.isFloating())
     RetT.makeInteger(RetT.getElementSizeInBits(), false);
 
   // Since the return value must be one type, return a vector type of the
@@ -1078,7 +976,7 @@ std::string Intrinsic::getBuiltinTypeStr() {
     if (!RetT.isScalar() && RetT.isInteger() && !RetT.isSigned())
       RetT.makeSigned();
 
-    if (LocalCK == ClassB && !RetT.isVoid() && !RetT.isScalar())
+    if (LocalCK == ClassB && RetT.isValue() && !RetT.isScalar())
       // Cast to vector of 8-bit elements.
       RetT.makeInteger(8, true);
 
@@ -1194,7 +1092,7 @@ void Intrinsic::initVariables() {
 
   // Modify the TypeSpec per-argument to get a concrete Type, and create
   // known variables for each.
-  for (unsigned I = 1; I < Proto.size(); ++I) {
+  for (unsigned I = 1; I < Types.size(); ++I) {
     char NameC = '0' + (I - 1);
     std::string Name = "p";
     Name.push_back(NameC);
@@ -1315,7 +1213,7 @@ void Intrinsic::emitShadowedArgs() {
   for (unsigned I = 0; I < getNumParams(); ++I) {
     // Do not create a temporary for an immediate argument.
     // That would defeat the whole point of using a macro!
-    if (hasImmediate() && Proto[I+1] == 'i')
+    if (getParamType(I).isImmediate())
       continue;
     // Do not create a temporary for pointer arguments. The input
     // pointer may have an alignment hint.
@@ -1339,13 +1237,9 @@ void Intrinsic::emitShadowedArgs() {
 }
 
 bool Intrinsic::protoHasScalar() const {
-  return (Proto.find('s') != std::string::npos ||
-          Proto.find('z') != std::string::npos ||
-          Proto.find('r') != std::string::npos ||
-          Proto.find('b') != std::string::npos ||
-          Proto.find('$') != std::string::npos ||
-          Proto.find('y') != std::string::npos ||
-          Proto.find('o') != std::string::npos);
+  return std::any_of(Types.begin(), Types.end(), [](const Type &T) {
+    return T.isScalar() && !T.isImmediate();
+  });
 }
 
 void Intrinsic::emitBodyAsBuiltinCall() {
@@ -1408,13 +1302,7 @@ void Intrinsic::emitBodyAsBuiltinCall() {
 
   // Extra constant integer to hold type class enum for this function, e.g. s8
   if (getClassKind(true) == ClassB) {
-    Type ThisTy = getReturnType();
-    if (Proto[0] == 'v' || isFloatingPointProtoModifier(Proto[0]))
-      ThisTy = getParamType(0);
-    if (ThisTy.isPointer())
-      ThisTy = getParamType(1);
-
-    S += utostr(ThisTy.getNeonEnum());
+    S += utostr(getPolymorphicKeyType().getNeonEnum());
   } else {
     // Remove extraneous ", ".
     S.pop_back();
@@ -2019,9 +1907,9 @@ void NeonEmitter::createIntrinsic(Record *R,
   std::vector<std::pair<TypeSpec, TypeSpec>> NewTypeSpecs;
   for (auto TS : TypeSpecs) {
     if (CartesianProductOfTypes) {
-      Type DefaultT(TS, 'd');
+      Type DefaultT(TS, ".");
       for (auto SrcTS : TypeSpecs) {
-        Type DefaultSrcT(SrcTS, 'd');
+        Type DefaultSrcT(SrcTS, ".");
         if (TS == SrcTS ||
             DefaultSrcT.getSizeInBits() != DefaultT.getSizeInBits())
           continue;
@@ -2101,31 +1989,19 @@ void NeonEmitter::genOverloadTypeCheckCode(raw_ostream &OS,
       continue;
 
     uint64_t Mask = 0ULL;
-    Type Ty = Def->getReturnType();
-    if (Def->getProto()[0] == 'v' ||
-        isFloatingPointProtoModifier(Def->getProto()[0]))
-      Ty = Def->getParamType(0);
-    if (Ty.isPointer())
-      Ty = Def->getParamType(1);
-
-    Mask |= 1ULL << Ty.getNeonEnum();
+    Mask |= 1ULL << Def->getPolymorphicKeyType().getNeonEnum();
 
     // Check if the function has a pointer or const pointer argument.
-    std::string Proto = Def->getProto();
     int PtrArgNum = -1;
     bool HasConstPtr = false;
     for (unsigned I = 0; I < Def->getNumParams(); ++I) {
-      char ArgType = Proto[I + 1];
-      if (ArgType == 'c') {
-        HasConstPtr = true;
+      const auto &Type = Def->getParamType(I);
+      if (Type.isPointer()) {
         PtrArgNum = I;
-        break;
-      }
-      if (ArgType == 'p') {
-        PtrArgNum = I;
-        break;
+        HasConstPtr = Type.isConstPointer();
       }
     }
+
     // For sret builtins, adjust the pointer argument index.
     if (PtrArgNum >= 0 && Def->getReturnType().getNumVectors() > 1)
       PtrArgNum += 1;
@@ -2349,7 +2225,7 @@ void NeonEmitter::run(raw_ostream &OS) {
   bool InIfdef = false;
   for (auto &TS : TDTypeVec) {
     bool IsA64 = false;
-    Type T(TS, 'd');
+    Type T(TS, ".");
     if (T.isDouble() || (T.isPoly() && T.getElementSizeInBits() == 64))
       IsA64 = true;
 
@@ -2382,7 +2258,7 @@ void NeonEmitter::run(raw_ostream &OS) {
   for (unsigned NumMembers = 2; NumMembers <= 4; ++NumMembers) {
     for (auto &TS : TDTypeVec) {
       bool IsA64 = false;
-      Type T(TS, 'd');
+      Type T(TS, ".");
       if (T.isDouble() || (T.isPoly() && T.getElementSizeInBits() == 64))
         IsA64 = true;
 
@@ -2395,8 +2271,8 @@ void NeonEmitter::run(raw_ostream &OS) {
         InIfdef = true;
       }
 
-      char M = '2' + (NumMembers - 2);
-      Type VT(TS, M);
+      const char Mods[] = { static_cast<char>('2' + (NumMembers - 2)), 0};
+      Type VT(TS, Mods);
       OS << "typedef struct " << VT.str() << " {\n";
       OS << "  " << T.str() << " val";
       OS << "[" << NumMembers << "]";

diff  --git a/clang/utils/convert_arm_neon.py b/clang/utils/convert_arm_neon.py
new file mode 100644
index 000000000000..c4b364529457
--- /dev/null
+++ b/clang/utils/convert_arm_neon.py
@@ -0,0 +1,172 @@
+#!/usr/bin/env python3
+
+# This script was committed on 20/11/2019 and it would probably make sense to remove
+# it after the next release branches.
+
+# This script is pipe based and converts an arm_neon.td (or arm_fp16.td) file
+# using the old single-char type modifiers to an equivalent new-style form where
+# each modifier is orthogonal and they can be composed.
+#
+# It was used to directly generate the .td files on master, so if you have any
+# local additions I would suggest implementing any modifiers here, and running
+# it over your entire pre-merge .td files rather than trying to resolve any
+# conflicts manually.
+
+import re, sys
+MOD_MAP = {
+    'v': 'v',
+    'x': 'S',
+    'u': 'U',
+    'd': '.',
+    'g': 'q',
+    'j': 'Q',
+    'w': '>Q',
+    'n': '>',
+    'h': '<',
+    'q': '<Q',
+    'e': '<U',
+    'm': '<q',
+    'i': 'I',
+    'l': 'IU>',
+    's': '1',
+    'z': '1<',
+    'r': '1>',
+    'b': '1U',
+    '$': '1S',
+    'k': 'Q',
+    '2': '2',
+    '3': '3',
+    '4': '4',
+    'B': '2Q',
+    'C': '3Q',
+    'D': '4Q',
+    'p': '*',
+    'c': 'c*',
+    '7': '<<q',
+    '8': '<<',
+    '9': '<<Q',
+    't': 'p'
+    }
+
+
+def typespec_elt_size(typespec):
+    if 'c' in typespec:
+        return 8
+    elif 's' in typespec or 'h' in typespec:
+        return 16
+    elif 'i' in typespec or 'f' in typespec:
+        return 32
+    elif 'l' in typespec or 'd' in typespec:
+        return 64
+    elif 'k' in typespec:
+        return 128
+
+def get_resize(cur, desired):
+    res = ''
+    while cur < desired:
+        res += '>'
+        cur *= 2
+    while cur > desired:
+        res += '<'
+        cur /= 2
+    return res
+
+
+def remap_protocol(proto, typespec, name):
+    key_type = 0
+
+    # Conversions like to see the integer type so they know signedness.
+    if 'vcvt' in name and '_f' in name and name != 'vcvt_f32_f64' and name != 'vcvt_f64_f32':
+        key_type = 1
+    default_width = typespec_elt_size(typespec)
+    inconsistent_width = False
+    for elt in typespec:
+        new_width = typespec_elt_size(elt)
+        if new_width and new_width != default_width:
+            inconsistent_width = True
+
+    res = ''
+    for i, c in enumerate(proto):
+        # void and pointers make for bad discriminators in CGBuiltin.cpp.
+        if c in 'vcp':
+                key_type += 1
+
+        if c in MOD_MAP:
+            cur_mod = MOD_MAP[c]
+        elif inconsistent_width:
+            # Otherwise it's a fixed output width modifier.
+            sys.stderr.write(f'warning: {name} uses fixed output size but has inconsistent input widths: {proto} {typespec}\n')
+
+        if c == 'Y':
+            # y: scalar of half float
+            resize = get_resize(default_width, 16)
+            cur_mod = f'1F{resize}'
+        elif c == 'y':
+            # y: scalar of float
+            resize = get_resize(default_width, 32)
+            cur_mod = f'1F{resize}'
+        elif c == 'o':
+            # o: scalar of double
+            resize = get_resize(default_width, 64)
+            cur_mod = f'1F{resize}'
+        elif c == 'I':
+            # I: scalar of 32-bit signed
+            resize = get_resize(default_width, 32)
+            cur_mod = f'1S{resize}'
+        elif c == 'L':
+            # L: scalar of 64-bit signed
+            resize = get_resize(default_width, 64)
+            cur_mod = f'1S{resize}'
+        elif c == 'U':
+            # I: scalar of 32-bit unsigned
+            resize = get_resize(default_width, 32)
+            cur_mod = f'1U{resize}'
+        elif c == 'O':
+            # O: scalar of 64-bit unsigned
+            resize = get_resize(default_width, 64)
+            cur_mod = f'1U{resize}'
+        elif c == 'f':
+            # f: float (int args)
+            resize = get_resize(default_width, 32)
+            cur_mod = f'F{resize}'
+        elif c == 'F':
+            # F: double (int args)
+            resize = get_resize(default_width, 64)
+            cur_mod = f'F{resize}'
+        elif c == 'H':
+            # H: half (int args)
+            resize = get_resize(default_width, 16)
+            cur_mod = f'F{resize}'
+        elif c == '0':
+            # 0: half (int args), ignore 'Q' size modifier.
+            resize = get_resize(default_width, 16)
+            cur_mod = f'Fq{resize}'
+        elif c == '1':
+            # 1: half (int args), force 'Q' size modifier.
+            resize = get_resize(default_width, 16)
+            cur_mod = f'FQ{resize}'
+
+        if len(cur_mod) == 0:
+            raise Exception(f'WTF: {c} in {name}')
+
+        if key_type != 0 and key_type == i:
+            cur_mod += '!'
+
+        if len(cur_mod) == 1:
+            res += cur_mod
+        else:
+            res += '(' + cur_mod + ')'
+
+    return res
+
+def replace_insts(m):
+    start, end = m.span('proto')
+    start -= m.start()
+    end -= m.start()
+    new_proto = remap_protocol(m['proto'], m['kinds'], m['name'])
+    return m.group()[:start] + new_proto + m.group()[end:]
+
+INST = re.compile(r'Inst<"(?P<name>.*?)",\s*"(?P<proto>.*?)",\s*"(?P<kinds>.*?)"')
+
+new_td = INST.sub(replace_insts, sys.stdin.read())
+sys.stdout.write(new_td)


        


More information about the cfe-commits mailing list