AVX512: Implemented encoding and intrinsics for VMOVSHDUP/VMOVSLDUP instructions.

[oota-llvm.git] / lib / Target / X86 / X86RegisterInfo.td

diff --git a/lib/Target/X86/X86RegisterInfo.td b/lib/Target/X86/X86RegisterInfo.td
index 45a676a0d038862d54a127fcc71a01d59d2f0af0..de32968a62e836ea8ccd50476dd837d1aa3e6c9b 100644 (file)
--- a/lib/Target/X86/X86RegisterInfo.td
+++ b/lib/Target/X86/X86RegisterInfo.td
@@ -225,15 +225,15 @@ let SubRegIndices = [sub_ymm] in {
   }
 }
 
-  // Mask Registers, used by AVX-512 instructions.
-  def K0 : X86Reg<"k0", 0>, DwarfRegNum<[118, -2, -2]>;
-  def K1 : X86Reg<"k1", 1>, DwarfRegNum<[119, -2, -2]>;
-  def K2 : X86Reg<"k2", 2>, DwarfRegNum<[120, -2, -2]>;
-  def K3 : X86Reg<"k3", 3>, DwarfRegNum<[121, -2, -2]>;
-  def K4 : X86Reg<"k4", 4>, DwarfRegNum<[122, -2, -2]>;
-  def K5 : X86Reg<"k5", 5>, DwarfRegNum<[123, -2, -2]>;
-  def K6 : X86Reg<"k6", 6>, DwarfRegNum<[124, -2, -2]>;
-  def K7 : X86Reg<"k7", 7>, DwarfRegNum<[125, -2, -2]>;
+// Mask Registers, used by AVX-512 instructions.
+def K0 : X86Reg<"k0", 0>, DwarfRegNum<[118, -2, -2]>;
+def K1 : X86Reg<"k1", 1>, DwarfRegNum<[119, -2, -2]>;
+def K2 : X86Reg<"k2", 2>, DwarfRegNum<[120, -2, -2]>;
+def K3 : X86Reg<"k3", 3>, DwarfRegNum<[121, -2, -2]>;
+def K4 : X86Reg<"k4", 4>, DwarfRegNum<[122, -2, -2]>;
+def K5 : X86Reg<"k5", 5>, DwarfRegNum<[123, -2, -2]>;
+def K6 : X86Reg<"k6", 6>, DwarfRegNum<[124, -2, -2]>;
+def K7 : X86Reg<"k7", 7>, DwarfRegNum<[125, -2, -2]>;
 
 // Floating point stack registers. These don't map one-to-one to the FP
 // pseudo registers, but we still mark them as aliasing FP registers. That
@@ -302,6 +302,11 @@ def CR15 : X86Reg<"cr15", 15>;
 def EIZ : X86Reg<"eiz", 4>;
 def RIZ : X86Reg<"riz", 4>;
 
+// Bound registers, used in MPX instructions
+def BND0 : X86Reg<"bnd0",   0>;
+def BND1 : X86Reg<"bnd1",   1>;
+def BND2 : X86Reg<"bnd2",   2>;
+def BND3 : X86Reg<"bnd3",   3>;
 
 //===----------------------------------------------------------------------===//
 // Register Class Definitions... now that we have all of the pieces, define the
@@ -325,7 +330,7 @@ def GR8 : RegisterClass<"X86", [i8],  8,
                              R8B, R9B, R10B, R11B, R14B, R15B, R12B, R13B)> {
   let AltOrders = [(sub GR8, AH, BH, CH, DH)];
   let AltOrderSelect = [{
-    return MF.getTarget().getSubtarget<X86Subtarget>().is64Bit();
+    return MF.getSubtarget<X86Subtarget>().is64Bit();
   }];
 }
 
@@ -377,7 +382,7 @@ def GR8_NOREX : RegisterClass<"X86", [i8], 8,
                               (add AL, CL, DL, AH, CH, DH, BL, BH)> {
   let AltOrders = [(sub GR8_NOREX, AH, BH, CH, DH)];
   let AltOrderSelect = [{
-    return MF.getTarget().getSubtarget<X86Subtarget>().is64Bit();
+    return MF.getSubtarget<X86Subtarget>().is64Bit();
   }];
 }
 // GR16_NOREX - GR16 registers which do not require a REX prefix.
@@ -454,8 +459,8 @@ def FPCCR : RegisterClass<"X86", [i16], 16, (add FPSW)> {
 }
 
 // AVX-512 vector/mask registers.
-def VR512 : RegisterClass<"X86", [v16f32, v8f64, v64i8, v32i16, v16i32, v8i64], 512,
-    (sequence "ZMM%u", 0, 31)>;
+def VR512 : RegisterClass<"X86", [v16f32, v8f64, v64i8, v32i16, v16i32, v8i64],
+                          512, (sequence "ZMM%u", 0, 31)>;
 
 // Scalar AVX-512 floating point registers.
 def FR32X : RegisterClass<"X86", [f32], 32, (sequence "XMM%u", 0, 31)>;
@@ -464,9 +469,9 @@ def FR64X : RegisterClass<"X86", [f64], 64, (add FR32X)>;
 
 // Extended VR128 and VR256 for AVX-512 instructions
 def VR128X : RegisterClass<"X86", [v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
-                          128, (add FR32X)>;
+                           128, (add FR32X)>;
 def VR256X : RegisterClass<"X86", [v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
-                          256, (sequence "YMM%u", 0, 31)>;
+                           256, (sequence "YMM%u", 0, 31)>;
 
 // Mask registers
 def VK1     : RegisterClass<"X86", [i1],    8,  (sequence "K%u", 0, 7)> {let Size = 8;}
@@ -484,3 +489,6 @@ def VK8WM   : RegisterClass<"X86", [v8i1],  8,  (sub VK8, K0)> {let Size = 8;}
 def VK16WM  : RegisterClass<"X86", [v16i1], 16, (add VK8WM)>   {let Size = 16;}
 def VK32WM  : RegisterClass<"X86", [v32i1], 32, (add VK16WM)> {let Size = 32;}
 def VK64WM  : RegisterClass<"X86", [v64i1], 64, (add VK32WM)> {let Size = 64;}
+
+// Bound registers
+def BNDR : RegisterClass<"X86", [v2i64], 128, (sequence "BND%u", 0, 3)>;