vendor/llvm/llvm-trunk-r366426

1 files changed, 107 insertions, 57 deletions

diff --git a/lib/Target/X86/X86MacroFusion.cpp b/lib/Target/X86/X86MacroFusion.cpp
index 5c09597d0442..c6da4b09dd60 100644
--- a/lib/Target/X86/X86MacroFusion.cpp
+++ b/lib/Target/X86/X86MacroFusion.cpp
@@ -1,9 +1,8 @@
 //===- X86MacroFusion.cpp - X86 Macro Fusion ------------------------------===//
 //
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
@@ -19,59 +18,29 @@
 
 using namespace llvm;
 
-/// Check if the instr pair, FirstMI and SecondMI, should be fused
-/// together. Given SecondMI, when FirstMI is unspecified, then check if
-/// SecondMI may be part of a fused pair at all.
-static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
-                                   const TargetSubtargetInfo &TSI,
-                                   const MachineInstr *FirstMI,
-                                   const MachineInstr &SecondMI) {
-  const X86Subtarget &ST = static_cast<const X86Subtarget&>(TSI);
-  // Check if this processor supports macro-fusion.
-  if (!ST.hasMacroFusion())
-    return false;
+namespace {
 
-  enum {
-    FuseTest,
-    FuseCmp,
-    FuseInc
-  } FuseKind;
+// The classification for the first instruction.
+enum class FirstInstrKind { Test, Cmp, And, ALU, IncDec, Invalid };
 
-  unsigned FirstOpcode = FirstMI
-                         ? FirstMI->getOpcode()
-                         : static_cast<unsigned>(X86::INSTRUCTION_LIST_END);
-  unsigned SecondOpcode = SecondMI.getOpcode();
+// The classification for the second instruction (jump).
+enum class JumpKind {
+  // JE, JL, JG and variants.
+  ELG,
+  // JA, JB and variants.
+  AB,
+  // JS, JP, JO and variants.
+  SPO,
+  // Not a fusable jump.
+  Invalid,
+};
 
-  switch (SecondOpcode) {
-  default:
-    return false;
-  case X86::JE_1:
-  case X86::JNE_1:
-  case X86::JL_1:
-  case X86::JLE_1:
-  case X86::JG_1:
-  case X86::JGE_1:
-    FuseKind = FuseInc;
-    break;
-  case X86::JB_1:
-  case X86::JBE_1:
-  case X86::JA_1:
-  case X86::JAE_1:
-    FuseKind = FuseCmp;
-    break;
-  case X86::JS_1:
-  case X86::JNS_1:
-  case X86::JP_1:
-  case X86::JNP_1:
-  case X86::JO_1:
-  case X86::JNO_1:
-    FuseKind = FuseTest;
-    break;
-  }
+} // namespace
 
-  switch (FirstOpcode) {
+static FirstInstrKind classifyFirst(const MachineInstr &MI) {
+  switch (MI.getOpcode()) {
   default:
-    return false;
+    return FirstInstrKind::Invalid;
   case X86::TEST8rr:
   case X86::TEST16rr:
   case X86::TEST32rr:
@@ -84,6 +53,7 @@ static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
   case X86::TEST16mr:
   case X86::TEST32mr:
   case X86::TEST64mr:
+    return FirstInstrKind::Test;
   case X86::AND16ri:
   case X86::AND16ri8:
   case X86::AND16rm:
@@ -99,7 +69,7 @@ static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
   case X86::AND8ri:
   case X86::AND8rm:
   case X86::AND8rr:
-    return true;
+    return FirstInstrKind::And;
   case X86::CMP16ri:
   case X86::CMP16ri8:
   case X86::CMP16rm:
@@ -119,6 +89,7 @@ static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
   case X86::CMP8rm:
   case X86::CMP8rr:
   case X86::CMP8mr:
+    return FirstInstrKind::Cmp;
   case X86::ADD16ri:
   case X86::ADD16ri8:
   case X86::ADD16ri8_DB:
@@ -141,8 +112,10 @@ static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
   case X86::ADD64rr:
   case X86::ADD64rr_DB:
   case X86::ADD8ri:
+  case X86::ADD8ri_DB:
   case X86::ADD8rm:
   case X86::ADD8rr:
+  case X86::ADD8rr_DB:
   case X86::SUB16ri:
   case X86::SUB16ri8:
   case X86::SUB16rm:
@@ -158,7 +131,7 @@ static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
   case X86::SUB8ri:
   case X86::SUB8rm:
   case X86::SUB8rr:
-    return FuseKind == FuseCmp || FuseKind == FuseInc;
+    return FirstInstrKind::ALU;
   case X86::INC16r:
   case X86::INC32r:
   case X86::INC64r:
@@ -167,10 +140,87 @@ static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
   case X86::DEC32r:
   case X86::DEC64r:
   case X86::DEC8r:
-    return FuseKind == FuseInc;
-  case X86::INSTRUCTION_LIST_END:
-    return true;
+    return FirstInstrKind::IncDec;
+  }
+}
+
+static JumpKind classifySecond(const MachineInstr &MI) {
+  X86::CondCode CC = X86::getCondFromBranch(MI);
+  if (CC == X86::COND_INVALID)
+    return JumpKind::Invalid;
+
+  switch (CC) {
+  default:
+    return JumpKind::Invalid;
+  case X86::COND_E:
+  case X86::COND_NE:
+  case X86::COND_L:
+  case X86::COND_LE:
+  case X86::COND_G:
+  case X86::COND_GE:
+    return JumpKind::ELG;
+  case X86::COND_B:
+  case X86::COND_BE:
+  case X86::COND_A:
+  case X86::COND_AE:
+    return JumpKind::AB;
+  case X86::COND_S:
+  case X86::COND_NS:
+  case X86::COND_P:
+  case X86::COND_NP:
+  case X86::COND_O:
+  case X86::COND_NO:
+    return JumpKind::SPO;
+  }
+}
+
+/// Check if the instr pair, FirstMI and SecondMI, should be fused
+/// together. Given SecondMI, when FirstMI is unspecified, then check if
+/// SecondMI may be part of a fused pair at all.
+static bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
+                                   const TargetSubtargetInfo &TSI,
+                                   const MachineInstr *FirstMI,
+                                   const MachineInstr &SecondMI) {
+  const X86Subtarget &ST = static_cast<const X86Subtarget &>(TSI);
+
+  // Check if this processor supports any kind of fusion.
+  if (!(ST.hasBranchFusion() || ST.hasMacroFusion()))
+    return false;
+
+  const JumpKind BranchKind = classifySecond(SecondMI);
+
+  if (BranchKind == JumpKind::Invalid)
+    return false; // Second cannot be fused with anything.
+
+  if (FirstMI == nullptr)
+    return true; // We're only checking whether Second can be fused at all.
+
+  const FirstInstrKind TestKind = classifyFirst(*FirstMI);
+
+  if (ST.hasBranchFusion()) {
+    // Branch fusion can merge CMP and TEST with all conditional jumps.
+    return (TestKind == FirstInstrKind::Cmp ||
+            TestKind == FirstInstrKind::Test);
+  }
+
+  if (ST.hasMacroFusion()) {
+    // Macro Fusion rules are a bit more complex. See Agner Fog's
+    // Microarchitecture table 9.2 "Instruction Fusion".
+    switch (TestKind) {
+    case FirstInstrKind::Test:
+    case FirstInstrKind::And:
+      return true;
+    case FirstInstrKind::Cmp:
+    case FirstInstrKind::ALU:
+      return BranchKind == JumpKind::ELG || BranchKind == JumpKind::AB;
+    case FirstInstrKind::IncDec:
+      return BranchKind == JumpKind::ELG;
+    case FirstInstrKind::Invalid:
+      return false;
+    }
   }
+
+  llvm_unreachable("unknown branch fusion type");
 }
 
 namespace llvm {