[ARM] Add MVE interleaving load/store family.

This adds the family of loads and stores with names like VLD20.8 and
VST42.32, which load and store parts of multiple q-registers in such a
way that executing both VLD20 and VLD21, or all four of VLD40..VLD43,
will distribute 2 or 4 vectors' worth of memory data across the lanes
of the same number of registers but in a transposed order.

In addition to the Tablegen descriptions of the instructions
themselves, this patch also adds encode and decode support for the
QQPR and QQQQPR register classes (representing the range of loaded or
stored vector registers), and tweaks to the parsing system for lists
of vector registers to make it return the right format in this case
(since, unlike NEON, MVE regards q-registers as primitive, and not
just an alias for two d-registers).

llvm-svn: 364172

1 files changed, 36 insertions, 0 deletions

diff --git a/llvm/lib/Target/ARM/Disassembler/ARMDisassembler.cpp b/llvm/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
index acabfd32cd7..7ccf37ef0e6 100644
--- a/llvm/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
+++ b/llvm/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
@@ -220,6 +220,10 @@ static DecodeStatus DecodeQPRRegisterClass(MCInst &Inst, unsigned RegNo,
                                    uint64_t Address, const void *Decoder);
 static DecodeStatus DecodeMQPRRegisterClass(MCInst &Inst, unsigned RegNo,
                                    uint64_t Address, const void *Decoder);
+static DecodeStatus DecodeQQPRRegisterClass(MCInst &Inst, unsigned RegNo,
+                                   uint64_t Address, const void *Decoder);
+static DecodeStatus DecodeQQQQPRRegisterClass(MCInst &Inst, unsigned RegNo,
+                                   uint64_t Address, const void *Decoder);
 static DecodeStatus DecodeDPairRegisterClass(MCInst &Inst, unsigned RegNo,
                                    uint64_t Address, const void *Decoder);
 static DecodeStatus DecodeDPairSpacedRegisterClass(MCInst &Inst,
@@ -5940,6 +5944,38 @@ static DecodeStatus DecodeMQPRRegisterClass(MCInst &Inst, unsigned RegNo,
   return MCDisassembler::Success;
 }
 
+static const uint16_t QQPRDecoderTable[] = {
+     ARM::Q0_Q1,  ARM::Q1_Q2,  ARM::Q2_Q3,  ARM::Q3_Q4,
+     ARM::Q4_Q5,  ARM::Q5_Q6,  ARM::Q6_Q7
+};
+
+static DecodeStatus DecodeQQPRRegisterClass(MCInst &Inst, unsigned RegNo,
+                              uint64_t Address,
+                              const void *Decoder) {
+  if (RegNo > 6)
+    return MCDisassembler::Fail;
+
+  unsigned Register = QQPRDecoderTable[RegNo];
+  Inst.addOperand(MCOperand::createReg(Register));
+  return MCDisassembler::Success;
+}
+
+static const uint16_t QQQQPRDecoderTable[] = {
+     ARM::Q0_Q1_Q2_Q3,  ARM::Q1_Q2_Q3_Q4,  ARM::Q2_Q3_Q4_Q5,
+     ARM::Q3_Q4_Q5_Q6,  ARM::Q4_Q5_Q6_Q7
+};
+
+static DecodeStatus DecodeQQQQPRRegisterClass(MCInst &Inst, unsigned RegNo,
+                              uint64_t Address,
+                              const void *Decoder) {
+  if (RegNo > 4)
+    return MCDisassembler::Fail;
+
+  unsigned Register = QQQQPRDecoderTable[RegNo];
+  Inst.addOperand(MCOperand::createReg(Register));
+  return MCDisassembler::Success;
+}
+
 static DecodeStatus DecodeVPTMaskOperand(MCInst &Inst, unsigned Val,
                                          uint64_t Address,
                                          const void *Decoder) {