[X86] Clzero intrinsic and its addition under znver1

This patch does the following.

1. Adds an Intrinsic int_x86_clzero which works with __builtin_ia32_clzero
2. Identifies clzero feature using cpuid info. (Function:8000_0008, Checks if EBX[0]=1)
3. Adds the clzero feature under znver1 architecture.
4. The custom inserter is added in Lowering.
5. A testcase is added to check the intrinsic.
6. The clzero instruction is added to assembler test.

Patch by Ganesh Gopalasubramanian with a couple formatting tweaks, a disassembler test, and using update_llc_test.py from me.

Differential revision: https://reviews.llvm.org/D29385

llvm-svn: 294558

include/llvm/IR/IntrinsicsX86.td

@@ -6495,3 +6495,10 @@ let TargetPrefix = "x86" in {
       : GCCBuiltin<"__builtin_ia32_mwaitx">,
         Intrinsic<[], [ llvm_i32_ty, llvm_i32_ty, llvm_i32_ty ], []>;
 }
+
+//===----------------------------------------------------------------------===//
+// Cache-line zero
+let TargetPrefix = "x86" in {
+  def int_x86_clzero : GCCBuiltin<"__builtin_ia32_clzero">,
+      Intrinsic<[], [llvm_ptr_ty], []>;
+}

lib/Support/Host.cpp

@@ -1353,6 +1353,10 @@ bool sys::getHostCPUFeatures(StringMap<bool> &Features) {
   Features["tbm"] = HasExtLeaf1 && ((ECX >> 21) & 1);
   Features["mwaitx"] = HasExtLeaf1 && ((ECX >> 29) & 1);
 
+  bool HasExtLeaf8 = MaxExtLevel >= 0x80000008 &&
+                     !getX86CpuIDAndInfoEx(0x80000008,0x0, &EAX, &EBX, &ECX, &EDX);
+  Features["clzero"] = HasExtLeaf8 && ((EBX >> 0) & 1);
+
   bool HasLeaf7 =
       MaxLevel >= 7 && !getX86CpuIDAndInfoEx(0x7, 0x0, &EAX, &EBX, &ECX, &EDX);
 

lib/Target/X86/X86.td

@@ -202,6 +202,8 @@ def FeatureLAHFSAHF : SubtargetFeature<"sahf", "HasLAHFSAHF", "true",
                                        "Support LAHF and SAHF instructions">;
 def FeatureMWAITX  : SubtargetFeature<"mwaitx", "HasMWAITX", "true",
                                       "Enable MONITORX/MWAITX timer functionality">;
+def FeatureCLZERO  : SubtargetFeature<"clzero", "HasCLZERO", "true",
+                                      "Enable Cache Line Zero">;
 def FeatureMPX     : SubtargetFeature<"mpx", "HasMPX", "true",
                                       "Support MPX instructions">;
 def FeatureLEAForSP : SubtargetFeature<"lea-sp", "UseLeaForSP", "true",
@@ -765,6 +767,7 @@ def: ProcessorModel<"znver1", BtVer2Model, [
   FeatureBMI,
   FeatureBMI2,
   FeatureCLFLUSHOPT,
+  FeatureCLZERO,
   FeatureCMPXCHG16B,
   FeatureF16C,
   FeatureFMA,

lib/Target/X86/X86ISelLowering.cpp

@@ -24418,6 +24418,26 @@ static MachineBasicBlock *emitMonitor(MachineInstr &MI, MachineBasicBlock *BB,
   return BB;
 }
 
+static MachineBasicBlock *emitClzero(MachineInstr *MI, MachineBasicBlock *BB,
+                                      const X86Subtarget &Subtarget) {
+  DebugLoc dl = MI->getDebugLoc();
+  const TargetInstrInfo *TII = Subtarget.getInstrInfo();
+  // Address into RAX/EAX
+  unsigned MemOpc = Subtarget.is64Bit() ? X86::LEA64r : X86::LEA32r;
+  unsigned MemReg = Subtarget.is64Bit() ? X86::RAX : X86::EAX;
+  MachineInstrBuilder MIB = BuildMI(*BB, MI, dl, TII->get(MemOpc), MemReg);
+  for (int i = 0; i < X86::AddrNumOperands; ++i)
+    MIB.add(MI->getOperand(i));
+
+  // The instruction doesn't actually take any operands though.
+  BuildMI(*BB, MI, dl, TII->get(X86::CLZEROr));
+
+  MI->eraseFromParent(); // The pseudo is gone now.
+  return BB;
+}
+
+
+
 MachineBasicBlock *
 X86TargetLowering::EmitVAARG64WithCustomInserter(MachineInstr &MI,
                                                  MachineBasicBlock *MBB) const {
@@ -26038,6 +26058,11 @@ X86TargetLowering::EmitInstrWithCustomInserter(MachineInstr &MI,
     return emitMonitor(MI, BB, Subtarget, X86::MONITORrrr);
   case X86::MONITORX:
     return emitMonitor(MI, BB, Subtarget, X86::MONITORXrrr);
+
+  // Cache line zero
+  case X86::CLZERO:
+    return emitClzero(&MI, BB, Subtarget);
+
   // PKU feature
   case X86::WRPKRU:
     return emitWRPKRU(MI, BB, Subtarget);

lib/Target/X86/X86InstrInfo.td

@@ -859,6 +859,7 @@ def HasRDSEED    : Predicate<"Subtarget->hasRDSEED()">;
 def HasPrefetchW : Predicate<"Subtarget->hasPRFCHW()">;
 def HasLAHFSAHF  : Predicate<"Subtarget->hasLAHFSAHF()">;
 def HasMWAITX    : Predicate<"Subtarget->hasMWAITX()">;
+def HasCLZERO    : Predicate<"Subtarget->hasCLZERO()">;
 def FPStackf32   : Predicate<"!Subtarget->hasSSE1()">;
 def FPStackf64   : Predicate<"!Subtarget->hasSSE2()">;
 def HasMPX       : Predicate<"Subtarget->hasMPX()">;
@@ -2456,8 +2457,19 @@ def : InstAlias<"monitorx\t{%rax, %rcx, %rdx|rdx, rcx, rax}", (MONITORXrrr)>,
 //===----------------------------------------------------------------------===//
 // CLZERO Instruction
 //
-let Uses = [EAX] in
-def CLZEROr : I<0x01, MRM_FC, (outs), (ins), "clzero", []>, TB;
+let SchedRW = [WriteSystem] in {
+  let Uses = [EAX] in
+  def CLZEROr : I<0x01, MRM_FC, (outs), (ins), "clzero", [], IIC_SSE_CLZERO>,
+                TB, Requires<[HasCLZERO]>;
+
+  let usesCustomInserter = 1 in {
+  def CLZERO : PseudoI<(outs), (ins i32mem:$src1),
+                       [(int_x86_clzero addr:$src1)]>, Requires<[HasCLZERO]>;
+  }
+} // SchedRW
+
+def : InstAlias<"clzero\t{%eax|eax}", (CLZEROr)>, Requires<[Not64BitMode]>;
+def : InstAlias<"clzero\t{%rax|rax}", (CLZEROr)>, Requires<[In64BitMode]>;
 
 //===----------------------------------------------------------------------===//
 // Pattern fragments to auto generate TBM instructions.

lib/Target/X86/X86Schedule.td

@@ -366,6 +366,7 @@ def IIC_SSE_MWAIT : InstrItinClass;
 def IIC_SSE_MONITOR : InstrItinClass;
 def IIC_SSE_MWAITX : InstrItinClass;
 def IIC_SSE_MONITORX : InstrItinClass;
+def IIC_SSE_CLZERO : InstrItinClass;
 
 def IIC_SSE_PREFETCH : InstrItinClass;
 def IIC_SSE_PAUSE : InstrItinClass;

lib/Target/X86/X86Subtarget.cpp

@@ -289,6 +289,7 @@ void X86Subtarget::initializeEnvironment() {
   HasRDSEED = false;
   HasLAHFSAHF = false;
   HasMWAITX = false;
+  HasCLZERO = false;
   HasMPX = false;
   IsBTMemSlow = false;
   IsPMULLDSlow = false;

lib/Target/X86/X86Subtarget.h

@@ -175,6 +175,9 @@ protected:
   /// Processor has MONITORX/MWAITX instructions.
   bool HasMWAITX;
 
+  /// Processor has Cache Line Zero instruction
+  bool HasCLZERO;
+
   /// Processor has Prefetch with intent to Write instruction
   bool HasPFPREFETCHWT1;
 
@@ -460,6 +463,7 @@ public:
   bool hasRDSEED() const { return HasRDSEED; }
   bool hasLAHFSAHF() const { return HasLAHFSAHF; }
   bool hasMWAITX() const { return HasMWAITX; }
+  bool hasCLZERO() const { return HasCLZERO; }
   bool isBTMemSlow() const { return IsBTMemSlow; }
   bool isSHLDSlow() const { return IsSHLDSlow; }
   bool isPMULLDSlow() const { return IsPMULLDSlow; }

test/CodeGen/X86/clzero.ll

@@ -0,0 +1,23 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-linux -mattr=+clzero | FileCheck %s --check-prefix=X64
+; RUN: llc < %s -mtriple=i386-pc-linux -mattr=+clzero | FileCheck %s --check-prefix=X32
+
+define void @foo(i8* %p) #0 {
+; X64-LABEL: foo:
+; X64:       # BB#0: # %entry
+; X64-NEXT:    leaq (%rdi), %rax
+; X64-NEXT:    clzero
+; X64-NEXT:    retq
+;
+; X32-LABEL: foo:
+; X32:       # BB#0: # %entry
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    leal (%eax), %eax
+; X32-NEXT:    clzero
+; X32-NEXT:    retl
+entry:
+  tail call void @llvm.x86.clzero(i8* %p) #1
+  ret void
+}
+
+declare void @llvm.x86.clzero(i8*) #1

test/MC/Disassembler/X86/x86-32.txt

@@ -129,6 +129,9 @@
 # CHECK: invlpga
 0x0f 0x01 0xdf
 
+# CHECK: clzero
+0x0f,0x01,0xfc
+
 # CHECK: movl $0, -4(%ebp)
 0xc7 0x45 0xfc 0x00 0x00 0x00 0x00
 

test/MC/X86/x86-32.s

@@ -444,6 +444,14 @@ cmovnae	%bx,%bx
 // CHECK:  encoding: [0x0f,0x21,0xf8]
         movl %dr7,%eax
 
+// CHECK:       clzero
+// CHECK:  encoding: [0x0f,0x01,0xfc]
+                clzero
+
+// CHECK:       clzero
+// CHECK:  encoding: [0x0f,0x01,0xfc]
+                clzero %eax
+
 // radr://8017522
 // CHECK: wait
 // CHECK:  encoding: [0x9b]

test/MC/X86/x86-64.s

@@ -1502,6 +1502,14 @@ vmovq %xmm0, %rax
 // CHECK:  encoding: [0x0f,0x01,0xfb]
         	mwaitx %rax, %rcx, %rbx
 
+// CHECK:       clzero
+// CHECK:  encoding: [0x0f,0x01,0xfc]
+                clzero
+
+// CHECK:       clzero
+// CHECK:  encoding: [0x0f,0x01,0xfc]
+                clzero %rax
+
 // CHECK: 	movl %r15d, (%r15,%r15)
 // CHECK:  encoding: [0x47,0x89,0x3c,0x3f]
 movl %r15d, (%r15,%r15)