ARM assembly parsing and encoding for VLD1 w/ writeback.

Three entry register list variation.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142876 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 53 insertions, 21 deletions

diff --git a/lib/Target/ARM/ARMBaseInstrInfo.cpp b/lib/Target/ARM/ARMBaseInstrInfo.cpp
index 211f937d95..caa500cbf0 100644
--- a/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -2428,7 +2428,8 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
     case ARM::VLD3d8_UPD:
     case ARM::VLD3d16_UPD:
     case ARM::VLD3d32_UPD:
-    case ARM::VLD1d64T_UPD:
+    case ARM::VLD1d64Twb_fixed:
+    case ARM::VLD1d64Twb_register:
     case ARM::VLD3q8_UPD:
     case ARM::VLD3q16_UPD:
     case ARM::VLD3q32_UPD:
@@ -2593,7 +2594,6 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
     case ARM::VLD3d8Pseudo_UPD:
     case ARM::VLD3d16Pseudo_UPD:
     case ARM::VLD3d32Pseudo_UPD:
-    case ARM::VLD1d64TPseudo_UPD:
     case ARM::VLD3q8Pseudo_UPD:
     case ARM::VLD3q16Pseudo_UPD:
     case ARM::VLD3q32Pseudo_UPD:
diff --git a/lib/Target/ARM/ARMExpandPseudoInsts.cpp b/lib/Target/ARM/ARMExpandPseudoInsts.cpp
index c8f9756f4d..459ba0ad5a 100644
--- a/lib/Target/ARM/ARMExpandPseudoInsts.cpp
+++ b/lib/Target/ARM/ARMExpandPseudoInsts.cpp
@@ -145,8 +145,6 @@ static const NEONLdStTableEntry NEONLdStTable[] = {
 { ARM::VLD1d64QPseudo,      ARM::VLD1d64Q,     true,  false, SingleSpc,  4, 1 ,false},
 { ARM::VLD1d64QPseudo_UPD,  ARM::VLD1d64Q_UPD, true,  true,  SingleSpc,  4, 1 ,false},
 { ARM::VLD1d64TPseudo,      ARM::VLD1d64T,     true,  false, SingleSpc,  3, 1 ,false},
-{ ARM::VLD1d64TPseudo_UPD,  ARM::VLD1d64T_UPD, true,  true,  SingleSpc,  3, 1 ,false},
-
 { ARM::VLD1q16Pseudo,       ARM::VLD1q16,      true,  false, SingleSpc,  2, 4 ,false},
 { ARM::VLD1q16PseudoWB_fixed, ARM::VLD1q16wb_fixed,true,false,SingleSpc, 2, 4 ,false},
 { ARM::VLD1q16PseudoWB_register, ARM::VLD1q16wb_register, true, true, SingleSpc, 2, 4 ,false},
@@ -1099,7 +1097,6 @@ bool ARMExpandPseudo::ExpandMI(MachineBasicBlock &MBB,
     case ARM::VLD3d8Pseudo_UPD:
     case ARM::VLD3d16Pseudo_UPD:
     case ARM::VLD3d32Pseudo_UPD:
-    case ARM::VLD1d64TPseudo_UPD:
     case ARM::VLD3q8Pseudo_UPD:
     case ARM::VLD3q16Pseudo_UPD:
     case ARM::VLD3q32Pseudo_UPD:
diff --git a/lib/Target/ARM/ARMInstrNEON.td b/lib/Target/ARM/ARMInstrNEON.td
index ff1a09a9ce..c280d61822 100644
--- a/lib/Target/ARM/ARMInstrNEON.td
+++ b/lib/Target/ARM/ARMInstrNEON.td
@@ -383,12 +383,24 @@ class VLD1D3<bits<4> op7_4, string Dt>
   let Inst{4} = Rn{4};
   let DecoderMethod = "DecodeVLDInstruction";
 }
-class VLD1D3WB<bits<4> op7_4, string Dt>
-  : NLdSt<0,0b10,0b0110,op7_4, (outs VecListThreeD:$Vd, GPR:$wb),
-          (ins addrmode6:$Rn, am6offset:$Rm), IIC_VLD1x3u, "vld1", Dt,
-          "$Vd, $Rn$Rm", "$Rn.addr = $wb", []> {
-  let Inst{4} = Rn{4};
-  let DecoderMethod = "DecodeVLDInstruction";
+multiclass VLD1D3WB<bits<4> op7_4, string Dt> {
+  def _fixed : NLdSt<0,0b10,0b0110, op7_4, (outs VecListThreeD:$Vd, GPR:$wb),
+                    (ins addrmode6:$Rn), IIC_VLD1x2u,
+                     "vld1", Dt, "$Vd, $Rn!",
+                     "$Rn.addr = $wb", []> {
+    let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
+    let Inst{5-4} = Rn{5-4};
+    let DecoderMethod = "DecodeVLDInstruction";
+    let AsmMatchConverter = "cvtVLDwbFixed";
+  }
+  def _register : NLdSt<0,0b10,0b0110,op7_4, (outs VecListThreeD:$Vd, GPR:$wb),
+                        (ins addrmode6:$Rn, rGPR:$Rm), IIC_VLD1x2u,
+                        "vld1", Dt, "$Vd, $Rn, $Rm",
+                        "$Rn.addr = $wb", []> {
+    let Inst{5-4} = Rn{5-4};
+    let DecoderMethod = "DecodeVLDInstruction";
+    let AsmMatchConverter = "cvtVLDwbRegister";
+  }
 }
 
 def VLD1d8T      : VLD1D3<{0,0,0,?}, "8">;
@@ -396,13 +408,12 @@ def VLD1d16T     : VLD1D3<{0,1,0,?}, "16">;
 def VLD1d32T     : VLD1D3<{1,0,0,?}, "32">;
 def VLD1d64T     : VLD1D3<{1,1,0,?}, "64">;
 
-def VLD1d8T_UPD  : VLD1D3WB<{0,0,0,?}, "8">;
-def VLD1d16T_UPD : VLD1D3WB<{0,1,0,?}, "16">;
-def VLD1d32T_UPD : VLD1D3WB<{1,0,0,?}, "32">;
-def VLD1d64T_UPD : VLD1D3WB<{1,1,0,?}, "64">;
+defm VLD1d8Twb  : VLD1D3WB<{0,0,0,?}, "8">;
+defm VLD1d16Twb : VLD1D3WB<{0,1,0,?}, "16">;
+defm VLD1d32Twb : VLD1D3WB<{1,0,0,?}, "32">;
+defm VLD1d64Twb : VLD1D3WB<{1,1,0,?}, "64">;
 
-def VLD1d64TPseudo     : VLDQQPseudo<IIC_VLD1x3>;
-def VLD1d64TPseudo_UPD : VLDQQWBPseudo<IIC_VLD1x3u>;
+def VLD1d64TPseudo : VLDQQPseudo<IIC_VLD1x3>;
 
 // ...with 4 registers
 class VLD1D4<bits<4> op7_4, string Dt>
diff --git a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
index d6b9260157..ddc5c99d36 100644
--- a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
+++ b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
@@ -2070,10 +2070,14 @@ static DecodeStatus DecodeVLDInstruction(llvm::MCInst &Inst, unsigned Insn,
     case ARM::VLD1q16wb_register:
     case ARM::VLD1q32wb_register:
     case ARM::VLD1q64wb_register:
-    case ARM::VLD1d8T_UPD:
-    case ARM::VLD1d16T_UPD:
-    case ARM::VLD1d32T_UPD:
-    case ARM::VLD1d64T_UPD:
+    case ARM::VLD1d8Twb_fixed:
+    case ARM::VLD1d8Twb_register:
+    case ARM::VLD1d16Twb_fixed:
+    case ARM::VLD1d16Twb_register:
+    case ARM::VLD1d32Twb_fixed:
+    case ARM::VLD1d32Twb_register:
+    case ARM::VLD1d64Twb_fixed:
+    case ARM::VLD1d64Twb_register:
     case ARM::VLD1d8Q_UPD:
     case ARM::VLD1d16Q_UPD:
     case ARM::VLD1d32Q_UPD:
diff --git a/test/MC/ARM/neon-vld-encoding.s b/test/MC/ARM/neon-vld-encoding.s
index ba45ea7724..08eb88403a 100644
--- a/test/MC/ARM/neon-vld-encoding.s
+++ b/test/MC/ARM/neon-vld-encoding.s
@@ -35,6 +35,16 @@
 	vld1.32	{d16, d17}, [r0], r5
 	vld1.64	{d16, d17}, [r0], r5
 
+	vld1.8 {d1, d2, d3}, [r3]!
+	vld1.16 {d4, d5, d6}, [r3, :64]!
+	vld1.32 {d5, d6, d7}, [r3]!
+	vld1.64 {d6, d7, d8}, [r3, :64]!
+
+	vld1.8 {d1, d2, d3}, [r3], r6
+	vld1.16 {d4, d5, d6}, [r3, :64], r6
+	vld1.32 {d5, d6, d7}, [r3], r6
+	vld1.64 {d6, d7, d8}, [r3, :64], r6
+
 @ CHECK: vld1.8 {d16}, [r0, :64]        @ encoding: [0x1f,0x07,0x60,0xf4]
 @ CHECK: vld1.16 {d16}, [r0]            @ encoding: [0x4f,0x07,0x60,0xf4]
 @ CHECK: vld1.32 {d16}, [r0]            @ encoding: [0x8f,0x07,0x60,0xf4]
@@ -70,6 +80,16 @@
 @ CHECK: vld1.32 {d16, d17}, [r0], r5   @ encoding: [0x85,0x0a,0x60,0xf4]
 @ CHECK: vld1.64 {d16, d17}, [r0], r5   @ encoding: [0xc5,0x0a,0x60,0xf4]
 
+@ CHECK: vld1.8	{d1, d2, d3}, [r3]!     @ encoding: [0x0d,0x16,0x23,0xf4]
+@ CHECK: vld1.16 {d4, d5, d6}, [r3, :64]! @ encoding: [0x5d,0x46,0x23,0xf4]
+@ CHECK: vld1.32 {d5, d6, d7}, [r3]!     @ encoding: [0x8d,0x56,0x23,0xf4]
+@ CHECK: vld1.64 {d6, d7, d8}, [r3, :64]! @ encoding: [0xdd,0x66,0x23,0xf4]
+
+@ CHECK: vld1.8	{d1, d2, d3}, [r3], r6  @ encoding: [0x06,0x16,0x23,0xf4]
+@ CHECK: vld1.16 {d4, d5, d6}, [r3, :64], r6 @ encoding: [0x56,0x46,0x23,0xf4]
+@ CHECK: vld1.32 {d5, d6, d7}, [r3], r6  @ encoding: [0x86,0x56,0x23,0xf4]
+@ CHECK: vld1.64 {d6, d7, d8}, [r3, :64], r6 @ encoding: [0xd6,0x66,0x23,0xf4]
+
 
 	vld2.8	{d16, d17}, [r0, :64]
 	vld2.16	{d16, d17}, [r0, :128]