Partial support for Intel SHA Extensions (sha1rnds4)

Add basic assembly/disassembly support for the first Intel SHA
instruction 'sha1rnds4'. Also includes feature flag, and test cases.

Support for the remaining instructions will follow in a separate patch.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190611 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/X86/X86.td

@@ -137,6 +137,9 @@ def FeatureHLE     : SubtargetFeature<"hle", "HasHLE", "true",
                                       "Support HLE">;
 def FeatureADX     : SubtargetFeature<"adx", "HasADX", "true",
                                       "Support ADX instructions">;
+def FeatureSHA     : SubtargetFeature<"sha", "HasSHA", "true",
+                                      "Enable SHA instructions",
+                                      [FeatureSSE2]>;
 def FeaturePRFCHW  : SubtargetFeature<"prfchw", "HasPRFCHW", "true",
                                       "Support PRFCHW instructions">;
 def FeatureRDSEED  : SubtargetFeature<"rdseed", "HasRDSEED", "true",

lib/Target/X86/X86InstrInfo.td

@@ -675,6 +675,7 @@ def HasRTM       : Predicate<"Subtarget->hasRTM()">;
 def HasHLE       : Predicate<"Subtarget->hasHLE()">;
 def HasTSX       : Predicate<"Subtarget->hasRTM() || Subtarget->hasHLE()">;
 def HasADX       : Predicate<"Subtarget->hasADX()">;
+def HasSHA       : Predicate<"Subtarget->hasSHA()">;
 def HasPRFCHW    : Predicate<"Subtarget->hasPRFCHW()">;
 def HasRDSEED    : Predicate<"Subtarget->hasRDSEED()">;
 def HasPrefetchW : Predicate<"Subtarget->has3DNow() || Subtarget->hasPRFCHW()">;

lib/Target/X86/X86InstrSSE.td

@@ -7320,6 +7320,22 @@ let Constraints = "$src1 = $dst" in {
                          REX_W;
 }
 
+//===----------------------------------------------------------------------===//
+// SHA-NI Instructions
+//===----------------------------------------------------------------------===//
+
+let Constraints = "$src1 = $dst", hasSideEffects = 0, Predicates = [HasSHA] in {
+  def SHA1RNDS4rri : Ii8<0xCC, MRMSrcReg, (outs VR128:$dst),
+                         (ins VR128:$src1, VR128:$src2, i8imm:$src3),
+                         "sha1rnds4\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                         []>, TA;
+  let mayLoad = 1 in
+  def SHA1RNDS4rmi : Ii8<0xCC, MRMSrcMem, (outs VR128:$dst),
+                         (ins VR128:$src1, i128mem:$src2, i8imm:$src3),
+                         "sha1rnds4\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                         []>, TA;
+}
+
 //===----------------------------------------------------------------------===//
 // AES-NI Instructions
 //===----------------------------------------------------------------------===//

lib/Target/X86/X86Subtarget.cpp

@@ -375,6 +375,10 @@ void X86Subtarget::AutoDetectSubtargetFeatures() {
         HasCDI = true;
         ToggleFeature(X86::FeatureCDI);
       }
+      if (IsIntel && ((EBX >> 29) & 0x1)) {
+        HasSHA = true;
+        ToggleFeature(X86::FeatureSHA);
+      }
     }
   }
 }
@@ -497,6 +501,7 @@ void X86Subtarget::initializeEnvironment() {
   HasCDI = false;
   HasPFI = false;
   HasADX = false;
+  HasSHA = false;
   HasPRFCHW = false;
   HasRDSEED = false;
   IsBTMemSlow = false;

lib/Target/X86/X86Subtarget.h

@@ -127,6 +127,9 @@ protected:
   /// HasADX - Processor has ADX instructions.
   bool HasADX;
 
+  /// HasSHA - Processor has SHA instructions.
+  bool HasSHA;
+
   /// HasPRFCHW - Processor has PRFCHW instructions.
   bool HasPRFCHW;
 
@@ -281,6 +284,7 @@ public:
   bool hasRTM() const { return HasRTM; }
   bool hasHLE() const { return HasHLE; }
   bool hasADX() const { return HasADX; }
+  bool hasSHA() const { return HasSHA; }
   bool hasPRFCHW() const { return HasPRFCHW; }
   bool hasRDSEED() const { return HasRDSEED; }
   bool isBTMemSlow() const { return IsBTMemSlow; }

test/MC/Disassembler/X86/x86-64.txt

@@ -157,3 +157,9 @@
 
 # CHECK: movabsq %rax, -6066930261531658096
 0x48 0xa3 0x90 0x78 0x56 0x34 0x12 0xef 0xcd 0xab
+
+# CHECK: sha1rnds4 $1, %xmm1, %xmm2
+0x0f 0x3a 0xcc 0xd1 0x01
+
+# CHECK: sha1rnds4 $1, (%rax), %xmm2
+0x0f 0x3a 0xcc 0x10 0x01

test/MC/X86/x86_64-encoding.s

@@ -120,6 +120,14 @@ movd %mm1, %edx
 // CHECK:  fixup A - offset: 5, value: CPI1_0-4
 pshufb	CPI1_0(%rip), %xmm1
 
+// CHECK: sha1rnds4 $1, %xmm1, %xmm2
+// CHECK:   encoding: [0x0f,0x3a,0xcc,0xd1,0x01]
+sha1rnds4 $1, %xmm1, %xmm2
+
+// CHECK: sha1rnds4 $1, (%rax), %xmm2
+// CHECK:   encoding: [0x0f,0x3a,0xcc,0x10,0x01]
+sha1rnds4 $1, (%rax), %xmm2
+
 // CHECK: movq  57005(,%riz), %rbx
 // CHECK: encoding: [0x48,0x8b,0x1c,0x25,0xad,0xde,0x00,0x00]
           movq  57005(,%riz), %rbx