From efec1396accbff7e6e652ffb0e77c56e6c0b7a42 Mon Sep 17 00:00:00 2001
From: Scott Linder <scott@scottlinder.com>
Date: Tue, 5 Mar 2019 03:02:00 +0000
Subject: [PATCH] [AMDGPU] Implement AMDGPUMCInstrAnalysis

Implement MCInstrAnalysis for AMDGPU, with default implementations save
for `evaluateBranch`.

Differential Revision: https://reviews.llvm.org/D58400

llvm-svn: 355373
---
 .../AMDGPU/Disassembler/AMDGPUDisassembler.cpp     |  2 ++
 .../AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp     | 31 ++++++++++++++++
 llvm/test/MC/AMDGPU/branch-comment.s               | 42 ++++++++++++++++++++++
 3 files changed, 75 insertions(+)
 create mode 100644 llvm/test/MC/AMDGPU/branch-comment.s

diff --git a/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp b/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
index 0acd30f..58c9c93 100644
--- a/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
+++ b/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
@@ -76,6 +76,8 @@ static DecodeStatus decodeSoppBrTarget(MCInst &Inst, unsigned Imm,
                                        uint64_t Addr, const void *Decoder) {
   auto DAsm = static_cast<const AMDGPUDisassembler*>(Decoder);
 
+  // Our branches take a simm16, but we need two extra bits to account for the
+  // factor of 4.
   APInt SignedOffset(18, Imm * 4, true);
   int64_t Offset = (SignedOffset.sext(64) + 4 + Addr).getSExtValue();
 
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp
index 9cb7705..ee75cca 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp
@@ -20,6 +20,7 @@
 #include "llvm/MC/MCAsmBackend.h"
 #include "llvm/MC/MCCodeEmitter.h"
 #include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCInstrAnalysis.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/MC/MCObjectWriter.h"
 #include "llvm/MC/MCRegisterInfo.h"
@@ -103,6 +104,35 @@ static MCStreamer *createMCStreamer(const Triple &T, MCContext &Context,
                                  std::move(Emitter), RelaxAll);
 }
 
+namespace {
+
+class AMDGPUMCInstrAnalysis : public MCInstrAnalysis {
+public:
+  explicit AMDGPUMCInstrAnalysis(const MCInstrInfo *Info)
+      : MCInstrAnalysis(Info) {}
+
+  bool evaluateBranch(const MCInst &Inst, uint64_t Addr, uint64_t Size,
+                      uint64_t &Target) const override {
+    if (Inst.getNumOperands() == 0 || !Inst.getOperand(0).isImm() ||
+        Info->get(Inst.getOpcode()).OpInfo[0].OperandType !=
+            MCOI::OPERAND_PCREL)
+      return false;
+
+    int64_t Imm = Inst.getOperand(0).getImm();
+    // Our branches take a simm16, but we need two extra bits to account for
+    // the factor of 4.
+    APInt SignedOffset(18, Imm * 4, true);
+    Target = (SignedOffset.sext(64) + Addr + Size).getZExtValue();
+    return true;
+  }
+};
+
+} // end anonymous namespace
+
+static MCInstrAnalysis *createAMDGPUMCInstrAnalysis(const MCInstrInfo *Info) {
+  return new AMDGPUMCInstrAnalysis(Info);
+}
+
 extern "C" void LLVMInitializeAMDGPUTargetMC() {
 
   TargetRegistry::RegisterMCInstrInfo(getTheGCNTarget(), createAMDGPUMCInstrInfo);
@@ -113,6 +143,7 @@ extern "C" void LLVMInitializeAMDGPUTargetMC() {
     TargetRegistry::RegisterMCRegInfo(*T, createAMDGPUMCRegisterInfo);
     TargetRegistry::RegisterMCSubtargetInfo(*T, createAMDGPUMCSubtargetInfo);
     TargetRegistry::RegisterMCInstPrinter(*T, createAMDGPUMCInstPrinter);
+    TargetRegistry::RegisterMCInstrAnalysis(*T, createAMDGPUMCInstrAnalysis);
     TargetRegistry::RegisterMCAsmBackend(*T, createAMDGPUAsmBackend);
     TargetRegistry::RegisterELFStreamer(*T, createMCStreamer);
   }
diff --git a/llvm/test/MC/AMDGPU/branch-comment.s b/llvm/test/MC/AMDGPU/branch-comment.s
new file mode 100644
index 0000000..e9cada6
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/branch-comment.s
@@ -0,0 +1,42 @@
+// RUN: llvm-mc -arch=amdgcn -mcpu=fiji -filetype=obj %s | llvm-objcopy -S -K keep_symbol - | llvm-objdump -disassemble -mcpu=fiji - | FileCheck %s --check-prefix=BIN
+
+// FIXME: Immediate operands to sopp_br instructions are currently scaled by a
+// factor of 4, are unsigned, are always PC relative, don't accept most
+// expressions, and are not range checked.
+
+loop_start_nosym:
+s_branch loop_start_nosym
+// BIN-NOT: loop_start_nosym:
+// BIN: s_branch 65535 // 000000000000: BF82FFFF <.text>
+
+s_branch loop_end_nosym
+// BIN: s_branch 0 // 000000000004: BF820000 <.text+0x8>
+// BIN-NOT: loop_end_nosym:
+loop_end_nosym:
+  s_nop 0
+
+keep_symbol:
+  s_nop 0
+
+loop_start_sym:
+s_branch loop_start_sym
+// BIN-NOT: loop_start_sym:
+// BIN: s_branch 65535 // 000000000010: BF82FFFF <keep_symbol+0x4>
+
+s_branch loop_end_sym
+// BIN: s_branch 0 // 000000000014: BF820000 <keep_symbol+0xc>
+// BIN-NOT: loop_end_sym:
+loop_end_sym:
+  s_nop 0
+
+s_branch 65535
+// BIN: s_branch 65535 // 00000000001C: BF82FFFF <keep_symbol+0x10>
+
+s_branch 32768
+// BIN: s_branch 32768 // 000000000020: BF828000 <keep_symbol+0xfffffffffffe0018>
+
+s_branch 32767
+// BIN: s_branch 32767 // 000000000024: BF827FFF <keep_symbol+0x20018>
+
+s_branch 0x80000000ffff
+// BIN: s_branch 65535 // 000000000028: BF82FFFF <keep_symbol+0x1c>
-- 
2.7.4