[Sparc] Leon errata fixes passes.

[lero_chris]

Summary

Errata fixes for various errata in different versions of the Leon variants of the Sparc 32 bit processor.

The nature of the errata are listed in the comments preceding the errata fix passes. Relevant unit tests are implemented for each of these.

Note: Running clang-format has changed a few other lines too, unrelated to the implemented errata fixes. These have been left in as this keeps the code formatting consistent.

[jacob_hansen]

Can't seem to find tests for the following passes:

FlushCacheLineSWAP
IgnoreZeroFlag
FixCALL

llvm/lib/Target/Sparc/LeonFeatures.td

18 ↗

(On Diff #62632)

Is this feature definition needed/used anywhere? I think the previously defined sofware floating point definition in Sparc.td is enough.

46 ↗

(On Diff #62632)

these requirement comments should probably be removed (here as well as in the descriptions).

llvm/lib/Target/Sparc/LeonPasses.cpp

654 ↗

(On Diff #62632)

Remove outcommented code.

714 ↗

(On Diff #62632)

would it make sense for the compiler to output a warning when this pass is successfully removing the call? The developer may want to know that the rounding mode change is not being executed correctly.

llvm/test/CodeGen/SPARC/LeonPreventRoundChangeUT.ll

3 ↗

(On Diff #62632)

is this check correct? Shouldn't it rather check that there is no call to fesetround ?

[lero_chris]

Update to address change recommended by comments. Small formatting changes. Missing unit tests added.

[dcederman]

lib/Target/Sparc/LeonFeatures.td

65–68 ↗

(On Diff #63195)

As jacob_hansen commented, this should only be a warning. It is not a good idea to remove valid function calls without notifying the user.

81–85 ↗

(On Diff #63195)

Flushing the cache is not a valid workaround for this errata, so this feature is not needed and will only decrease performance.

lib/Target/Sparc/LeonPasses.h

162 ↗

(On Diff #63195)

LBR35 is not the official name of the errata or errata fix, it should be removed to avoid confusion.

lib/Target/Sparc/Sparc.td

144 ↗

(On Diff #63195)

UMAC/SMAC is not available on ut699, gr712rc, or gr740.

lib/Target/Sparc/SparcISelLowering.cpp

1417–1419 ↗

(On Diff #63195)

This code has been commented out.

3100 ↗

(On Diff #63195)

This does not seem related to the errata fixes.

[lero_chris]

Further updates to address some review comments.

[jyknight]

I see you've already committed this in the time it took me to write down comments this morning. Please revert, and reopen the review. It seems to me that there are significant issues here. Some of those also present in code in LeonPasses.cpp that already was committed.

Also:

While it's not a big deal in this case, please don't do a file-wide clang-format in the same change as actual changes. You should be doing "git clang-format" or "clang-format-diff" to only format the lines you're modifying. (If the file is really egregiously ill-formatted, you can also run clang-format on the unmodified file, and commit that first).

lib/Target/Sparc/LeonFeatures.td

65–68 ↗

(On Diff #63195)

This doesn't appear to have been addressed.

81–85 ↗

(On Diff #63195)

This doesn't appear to have been addressed.

lib/Target/Sparc/LeonPasses.cpp

263 ↗

(On Diff #63215)

All of the isInlineAsm branches -- new and old -- seem wrong.

Testing instructions by looking at the prefix of the asm string can't possibly work properly. E.g., it's completely wrong if there are multiple instructions in an inline asm string.

One of two things makes sense. Either:
a) these fixes are only intended to be done on compiler-generated code. If so just remove the isInlineAsm clauses.

b) it's supposed to be done at translation of asm into object file. In which case, it should be done for an actual assembly input file too and these transforms are misplaced here.

I don't know myself how to introduce a transform at the asm level; there doesn't seem to be an obvious way to do it. Please ask for advice on the mailing list if that's what you need to do.

lib/Target/Sparc/SparcISelLowering.cpp

1642 ↗

(On Diff #63215)

This should actually have been 32. 64bit atomic instructions are not supported on leon. Also, unrelated to this change.

llvm/trunk/lib/Target/Sparc/SparcISelLowering.cpp

3380

Unrelated change.

3458

Unrelated change.

[lero_chris]

Re-opened to address latest comments.

[jyknight]

In D21960#478207, @lero_chris wrote:

Re-opened to address latest comments.

Please revert the change, too.

[lero_chris]

Addressing issues in previous review.

• Inline assembler removed.
• Non-working optimisation removed.
• Warning diagnostic generated on change of instruction behaviour for erratum fix.
• Changes to Unit tests to remove tests that work on inline assembler behaviour.
• Added (2) missing errata fixes.

[lero_chris]

Removed change to CMakeLists.txt that was relevant to a different change and inadvertently added to this review.

[dcederman]

I noticed that some of the files have been marked as executable. You should change that before committing anything.

lib/Target/Sparc/LeonPasses.cpp

757–762 ↗

(On Diff #67420)

How does this fill the data cache?

851–859 ↗

(On Diff #67420)

Erratas in trap handling should not be handled by the compiler, it should be done manually in each OS. Did you try to compile the trap handling code in, for example, Linux or RTEMS with this fix?

lib/Target/Sparc/LeonPasses.h

107–109 ↗

(On Diff #67420)

What is LBR29? Please add a description of the errata and the fix or a reference to an official document with the information.

What do you mean by application startup?

[lero_chris]

Modified some unit tests that were using inline assembler tests to work without this to reflect the non-use of inline assembler in the modified passes.

Removed "LBR" references to errata fixes as these were internal project references.

[lero_chris]

Addressing review comments.

lib/Target/Sparc/LeonFeatures.td

66–69 ↗

(On Diff #67733)

Warning now issued when this pass makes any changes.

82–86 ↗

(On Diff #67733)

Removed this pass if it does nothing.

lib/Target/Sparc/LeonPasses.cpp

231–232 ↗

(On Diff #67733)

All inline assembly code removed.

757–762 ↗

(On Diff #67733)

A cache stores recently-accessed data. To fill the cache, we need to access data big enough to fill the L1 cache of the LEON 2 FT CPU. To solve this problem, we use NOP instructions to fill a block of memory with NOP instructions. The LEON 2’s L1 data cache is 16 KB [6] and the size of the NOP instruction is 4 Bytes. Therefore, we need 4096 NOPs to entirely fill the cache. Note this will happen only once at the first call of the runOnMachineFunction() method.

851–859 ↗

(On Diff #67733)

Do you suggest that this pass should not be part of the compiler then? I can remove it if it fixes nothing.

lib/Target/Sparc/LeonPasses.h

108–110 ↗

(On Diff #67733)

Removed these internal project reference codes.

188 ↗

(On Diff #67733)

Removed these internal project reference codes.

lib/Target/Sparc/Sparc.td

145 ↗

(On Diff #67733)

Removed from feature set.

[dcederman]

Some more inline comments.

Could you please also revert the committed changes, like @jyknight asked you?

lib/Target/Sparc/LeonFeatures.td

88–90 ↗

(On Diff #67733)

A cache miss occurs when the data at the memory address accessed is not available in the cache. Filling the data cache with random data that will not be accessed again will not prevent cache misses, it will make them more likely.

Could you reference the document that describes the errata you are trying to provide a fix for? I looked in http://www.atmel.com/Images/doc4409.pdf but could not find a match.

lib/Target/Sparc/LeonPasses.cpp

757–762 ↗

(On Diff #67733)

But you are not accessing data? It is just a loop that does nothing. And if I understand the code correctly, you randomly add it to the first function you find?

851–859 ↗

(On Diff #67733)

You should remove it. Automatically changing assembly code in the trap handler is extremely risky.

[dcederman]

Why did you commit your changes mid-review? I'm reopening this review.

[lero_chris]

Hi Daniel. Nobody was commenting and I need to get this checked-in as I won't be around for three weeks now. You commented at *exactly* the same time as I did the check-in. Otherwise, I had addressed all the review comments.

I'll look at the comments and make any necessary changes when I am next at work.

[jyknight]

In D21960#513655, @lero_chris wrote:

Hi Daniel. Nobody was commenting and I need to get this checked-in as I won't be around for three weeks now. You commented at *exactly* the same time as I did the check-in. Otherwise, I had addressed all the review comments.

I'll look at the comments and make any necessary changes when I am next at work.

This is not OK. You have ignored two requests for a revert in a row now. I have reverted all of this in r278511.

[lero_chris]

Removed RestoreExecAddress and FillDataCache passes as these will have no effect.

[lero_chris]

In D21960#513813, @jyknight wrote:

In D21960#513655, @lero_chris wrote:

Hi Daniel. Nobody was commenting and I need to get this checked-in as I won't be around for three weeks now. You commented at *exactly* the same time as I did the check-in. Otherwise, I had addressed all the review comments.

I'll look at the comments and make any necessary changes when I am next at work.

This is not OK. You have ignored two requests for a revert in a row now. I have reverted all of this in r278511.

Sorry James. I had been addressing the comments. I hadn't realised that "revert" meant rolling back the repository changes too. SVN isn't something I use much and the language differs somewhat between source control systems.

I'll abandon this review and start a new review, albeit that this is all working and tested now.

[lero_chris]

Abandoned.

llvm/trunk/lib/Target/Sparc/LeonFeatures.td

 //===-- LeonFeatures.td - Describe the Leon Features -------*- tablegen -*-===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 //
 //===----------------------------------------------------------------------===//
 
-
 //===----------------------------------------------------------------------===//
-// UMAC and SMAC support for LEON3 and LEON4 processors.
+// CASA Support differs between LEON3-FT GR712RC and LEON3-FT UT699
+// We need to have the option to switch this on and off.
 //===----------------------------------------------------------------------===//
 
-//support to casa instruction; for leon3 subtarget only
-def UMACSMACSupport : SubtargetFeature<
-  "hasumacsmac", 
-  "HasUmacSmac", 
-  "true", 
-  "Enable UMAC and SMAC for LEON3 and LEON4 processors"
->;
-
+// support to casa instruction; for leon3 subtarget only
+def LeonCASA : SubtargetFeature<
+                   "hasleoncasa", "HasLeonCasa", "true",
+                   "Enable CASA instruction for LEON3 and LEON4 processors">;
 
 //===----------------------------------------------------------------------===//
-// CASA Support differs between LEON3-FT GR712RC and LEON3-FT UT699
-// We need to have the option to switch this on and off.
+// UMAC and SMAC support for LEON3 and LEON4 processors.
 //===----------------------------------------------------------------------===//
 
-//support to casa instruction; for leon3 subtarget only
-def LeonCASA : SubtargetFeature<
-  "hasleoncasa", 
-  "HasLeonCasa", 
-  "true", 
-  "Enable CASA instruction for LEON3 and LEON4 processors"
->;
-
-def InsertNOPLoad: SubtargetFeature<
-  "insertnopload",
-  "InsertNOPLoad",
-  "true",
-  "LEON3 erratum fix: Insert a NOP instruction after every single-cycle load instruction when the next instruction is another load/store instruction" 
->;
-
-def FixFSMULD : SubtargetFeature<
-  "fixfsmuld",
-  "FixFSMULD",
-  "true",
-  "LEON erratum fix: Do not use FSMULD" 
->;
-
-def ReplaceFMULS : SubtargetFeature<
-  "replacefmuls",
-  "ReplaceFMULS",
-  "true",
-  "LEON erratum fix: Replace FMULS instruction with FMULD and relevant conversion instructions" 
->;
-
-def FixAllFDIVSQRT : SubtargetFeature<
-  "fixallfdivsqrt",
-  "FixAllFDIVSQRT",
-  "true",
-  "LEON erratum fix: Fix FDIVS/FDIVD/FSQRTS/FSQRTD instructions with NOPs and floating-point store" 
->;
+// support to casa instruction; for leon3 subtarget only
+def UMACSMACSupport
+    : SubtargetFeature<"hasumacsmac", "HasUmacSmac", "true",
+                       "Enable UMAC and SMAC for LEON3 and LEON4 processors">;
+
+//===----------------------------------------------------------------------===//
+// LEON Erratum fixes
+//===----------------------------------------------------------------------===//
+
+def ReplaceSDIV
+    : SubtargetFeature<
+          "replacesdiv", "PerformSDIVReplace", "true",
+          "AT697E erratum fix: Do not emit SDIV, emit SDIVCC instead">;
+
+def FixCALL
+    : SubtargetFeature<"fixcall", "FixCallImmediates", "true",
+                       "AT697E erratum fix: Restrict the size of the immediate "
+                       "operand of the CALL instruction to 20 bits">;
+
+def IgnoreZeroFlag
+    : SubtargetFeature<"ignrzeroflag", "IgnoreZeroFlag", "true",
+                       "AT697E erratum fix: Do not rely on the zero bit flag "
+                       "on a divide overflow for SDIVCC and UDIVCC">;
+
+def InsertNOPDoublePrecision
+    : SubtargetFeature<"insrtnopdblprcsn", "InsertNOPDoublePrecision", "true",
+                       "LEON2 erratum fix: Insert a NOP before the double "
+                       "precision floating point instruction">;
+
+def FixFSMULD : SubtargetFeature<"fixfsmuld", "FixFSMULD", "true",
+                                 "LEON3 erratum fix: Do not select FSMULD">;
+
+def ReplaceFMULS
+    : SubtargetFeature<"replacefmuls", "ReplaceFMULS", "true",
+                       "LEON3 erratum fix: Replace FMULS instruction with a "
+                       "routine using conversions/double precision operations "
+                       "to replace FMULS">;
+
+def PreventRoundChange
+    : SubtargetFeature<"prvntroundchange", "PreventRoundChange", "true",
+                       "LEON3 erratum fix: Prevent any rounding mode change "
+                       "request: use only the round-to-nearest rounding mode">;
+
+def FixAllFDIVSQRT
+    : SubtargetFeature<"fixallfdivsqrt", "FixAllFDIVSQRT", "true",
+                       "LEON3 erratum fix: Fix FDIVS/FDIVD/FSQRTS/FSQRTD "
+                       "instructions with NOPs and floating-point store">;
+
+def InsertNOPLoad
+    : SubtargetFeature<"insertnopload", "InsertNOPLoad", "true",
+                       "LEON3 erratum fix: Insert a NOP instruction after "
+                       "every single-cycle load instruction when the next "
+                       "instruction is another load/store instruction">;
+
+def FlushCacheLineSWAP
+    : SubtargetFeature<"flshcachelineswap", "FlushCacheLineSWAP", "true",
+                       "LEON3 erratum fix: Flush cache line containing the "
+                       "lock before performing any of the atomic instructions "
+                       "SWAP and LDSTUB">;
+
+def InsertNOPsLoadStore
+    : SubtargetFeature<"insertnopsloadstore", "InsertNOPsLoadStore", "true",
+                       "LEON3 erratum fix: Insert NOPs between "
+                       "single-precision loads and the store, so the number of "
+                       "instructions between is 4">;

llvm/trunk/lib/Target/Sparc/LeonPasses.h

protected:
   void clearUsedRegisterList() { UsedRegisters.clear(); }
 
   void markRegisterUsed(int registerIndex) {
     UsedRegisters.push_back(registerIndex);
   }
   int getUnusedFPRegister(MachineRegisterInfo &MRI);
 };
 
-class LLVM_LIBRARY_VISIBILITY InsertNOPLoad : public LEONMachineFunctionPass {
+class LLVM_LIBRARY_VISIBILITY ReplaceSDIV : public LEONMachineFunctionPass {
 public:
   static char ID;
 
-  InsertNOPLoad(TargetMachine &tm);
+  ReplaceSDIV();
+  ReplaceSDIV(TargetMachine &tm);
   bool runOnMachineFunction(MachineFunction &MF) override;
 
   const char *getPassName() const override {
-    return "InsertNOPLoad: Erratum Fix LBR35: insert a NOP instruction after "
-           "every single-cycle load instruction when the next instruction is "
-           "another load/store instruction";
+    return "ReplaceSDIV: Erratum Fix LBR25:  do not emit SDIV, but emit SDIVCC "
+           "instead";
+  }
+};
+
+class LLVM_LIBRARY_VISIBILITY FixCALL : public LEONMachineFunctionPass {
+public:
+  static char ID;
+
+  FixCALL(TargetMachine &tm);
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  const char *getPassName() const override {
+    return "FixCALL: Erratum Fix LBR26: restrict the size of the immediate "
+           "operand of the CALL instruction to 20 bits";
+  }
+};
+
+class LLVM_LIBRARY_VISIBILITY IgnoreZeroFlag : public LEONMachineFunctionPass {
+public:
+  static char ID;
+
+  IgnoreZeroFlag(TargetMachine &tm);
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  const char *getPassName() const override {
+    return "IgnoreZeroFlag: Erratum Fix LBR28: do not rely on the zero bit "
+           "flag on a divide overflow for SDIVCC and UDIVCC";
+  }
+};
+
+class LLVM_LIBRARY_VISIBILITY InsertNOPDoublePrecision
+    : public LEONMachineFunctionPass {
+public:
+  static char ID;
+
+  InsertNOPDoublePrecision(TargetMachine &tm);
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  const char *getPassName() const override {
+    return "InsertNOPDoublePrecision: Erratum Fix LBR30: insert a NOP before "
+           "the double precision floating point instruction";
   }
 };
 
 class LLVM_LIBRARY_VISIBILITY FixFSMULD : public LEONMachineFunctionPass {
 public:
   static char ID;
 
   FixFSMULD(TargetMachine &tm);
public:
 
   const char *getPassName() const override {
     return "ReplaceFMULS: Erratum Fix LBR32: replace FMULS instruction with a "
            "routine using conversions/double precision operations to replace "
            "FMULS";
   }
 };
 
+class LLVM_LIBRARY_VISIBILITY PreventRoundChange
+    : public LEONMachineFunctionPass {
+public:
+  static char ID;
+
+  PreventRoundChange(TargetMachine &tm);
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  const char *getPassName() const override {
+    return "PreventRoundChange: Erratum Fix LBR33: prevent any rounding mode "
+           "change request: use only the round-to-nearest rounding mode";
+  }
+};
+
 class LLVM_LIBRARY_VISIBILITY FixAllFDIVSQRT : public LEONMachineFunctionPass {
 public:
   static char ID;
 
   FixAllFDIVSQRT(TargetMachine &tm);
   bool runOnMachineFunction(MachineFunction &MF) override;
 
   const char *getPassName() const override {
     return "FixAllFDIVSQRT: Erratum Fix LBR34: fix FDIVS/FDIVD/FSQRTS/FSQRTD "
            "instructions with NOPs and floating-point store";
   }
 };
-} // namespace llvm
+
+class LLVM_LIBRARY_VISIBILITY InsertNOPLoad : public LEONMachineFunctionPass {
+public:
+  static char ID;
+
+  InsertNOPLoad(TargetMachine &tm);
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  const char *getPassName() const override {
+    return "InsertNOPLoad: insert a NOP instruction after "
+           "every single-cycle load instruction when the next instruction is "
+           "another load/store instruction";
+  }
+};
+
+class LLVM_LIBRARY_VISIBILITY FlushCacheLineSWAP
+    : public LEONMachineFunctionPass {
+public:
+  static char ID;
+
+  FlushCacheLineSWAP(TargetMachine &tm);
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  const char *getPassName() const override {
+    return "FlushCacheLineSWAP: Erratum Fix LBR36: flush cache line containing "
+           "the lock before performing any of the atomic instructions SWAP and "
+           "LDSTUB";
+  }
+};
+
+class LLVM_LIBRARY_VISIBILITY InsertNOPsLoadStore
+    : public LEONMachineFunctionPass {
+public:
+  static char ID;
+
+  InsertNOPsLoadStore(TargetMachine &tm);
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  const char *getPassName() const override {
+    return "InsertNOPsLoadStore: Erratum Fix LBR37: insert NOPs between "
+           "single-precision loads and the store, so the number of "
+           "instructions between is 4";
+  }
+};
+} // namespace lllvm
 
 #endif // LLVM_LIB_TARGET_SPARC_LEON_PASSES_H

llvm/trunk/lib/Target/Sparc/LeonPasses.cpp

for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
       int Reg3Index = UNASSIGNED_INDEX;
 
       if (Opcode == SP::FSMULD && MI.getNumOperands() == 3) {
         // take the registers from fsmuld %f20,%f21,%f8
         Reg1Index = MI.getOperand(0).getReg();
         Reg2Index = MI.getOperand(1).getReg();
         Reg3Index = MI.getOperand(2).getReg();
       } else if (MI.isInlineAsm()) {
-        std::string AsmString(
-            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName());
-        std::string FMULSOpCoode("fsmuld");
-        std::transform(AsmString.begin(), AsmString.end(), AsmString.begin(),
-                       ::tolower);
-        if (AsmString.find(FMULSOpCoode) ==
-            0) { // this is an inline FSMULD instruction
+        StringRef AsmString =
+            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName();
+        if (AsmString.startswith_lower("fsmuld")) {
+          // this is an inline FSMULD instruction
 
           unsigned StartOp = InlineAsm::MIOp_FirstOperand;
 
           // extracts the registers from the inline assembly instruction
           for (unsigned i = StartOp, e = MI.getNumOperands(); i != e; ++i) {
             const MachineOperand &MO = MI.getOperand(i);
             if (MO.isReg()) {
               if (Reg1Index == UNASSIGNED_INDEX)
for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
       int Reg3Index = UNASSIGNED_INDEX;
 
       if (Opcode == SP::FMULS && MI.getNumOperands() == 3) {
         // take the registers from fmuls %f20,%f21,%f8
         Reg1Index = MI.getOperand(0).getReg();
         Reg2Index = MI.getOperand(1).getReg();
         Reg3Index = MI.getOperand(2).getReg();
       } else if (MI.isInlineAsm()) {
-        std::string AsmString(
-            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName());
-        std::string FMULSOpCoode("fmuls");
-        std::transform(AsmString.begin(), AsmString.end(), AsmString.begin(),
-                       ::tolower);
-        if (AsmString.find(FMULSOpCoode) ==
-            0) { // this is an inline FMULS instruction
+        StringRef AsmString =
+            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName();
+        if (AsmString.startswith_lower("fmuls")) {
+          // this is an inline FMULS instruction
           unsigned StartOp = InlineAsm::MIOp_FirstOperand;
 
           // extracts the registers from the inline assembly instruction
           for (unsigned i = StartOp, e = MI.getNumOperands(); i != e; ++i) {
             const MachineOperand &MO = MI.getOperand(i);
             if (MO.isReg()) {
               if (Reg1Index == UNASSIGNED_INDEX)
                 Reg1Index = MO.getReg();
bool FixAllFDIVSQRT::runOnMachineFunction(MachineFunction &MF) {
   bool Modified = false;
   for (auto MFI = MF.begin(), E = MF.end(); MFI != E; ++MFI) {
     MachineBasicBlock &MBB = *MFI;
     for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
       MachineInstr &MI = *MBBI;
       unsigned Opcode = MI.getOpcode();
 
       if (MI.isInlineAsm()) {
-        std::string AsmString(
-            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName());
-        std::string FSQRTDOpCode("fsqrtd");
-        std::string FDIVDOpCode("fdivd");
-        std::transform(AsmString.begin(), AsmString.end(), AsmString.begin(),
-                       ::tolower);
-        if (AsmString.find(FSQRTDOpCode) ==
-            0) { // this is an inline fsqrts instruction
+        StringRef AsmString =
+            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName();
+        if (AsmString.startswith_lower("fsqrtd")) {
+          // this is an inline fsqrts instruction
           Opcode = SP::FSQRTD;
-        } else if (AsmString.find(FDIVDOpCode) ==
-                   0) { // this is an inline fsqrts instruction
+        } else if (AsmString.startswith_lower("fdivd")) {
+          // this is an inline fsqrts instruction
           Opcode = SP::FDIVD;
         }
       }
 
       // Note: FDIVS and FSQRTS cannot be generated when this erratum fix is
       // switched on so we don't need to check for them here. They will
       // already have been converted to FSQRTD or FDIVD earlier in the
       // pipeline.
       if (Opcode == SP::FSQRTD || Opcode == SP::FDIVD) {
+        // Insert 5 NOPs before FSQRTD,FDIVD.
         for (int InsertedCount = 0; InsertedCount < 5; InsertedCount++)
           BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
 
         MachineBasicBlock::iterator NMBBI = std::next(MBBI);
+        // ... and inserting 28 NOPs after FSQRTD,FDIVD.
         for (int InsertedCount = 0; InsertedCount < 28; InsertedCount++)
           BuildMI(MBB, NMBBI, DL, TII.get(SP::NOP));
 
         Modified = true;
       }
     }
   }
 
   return Modified;
 }
+
+//*****************************************************************************
+//**** ReplaceSDIV pass
+//*****************************************************************************
+// This pass fixes the incorrectly working SDIV instruction that
+// exist for some earlier versions of the LEON processor line. The instruction
+// is replaced with an SDIVcc instruction instead, which is working.
+//
+char ReplaceSDIV::ID = 0;
+
+ReplaceSDIV::ReplaceSDIV() : LEONMachineFunctionPass(ID) {}
+
+ReplaceSDIV::ReplaceSDIV(TargetMachine &tm) : LEONMachineFunctionPass(tm, ID) {}
+
+bool ReplaceSDIV::runOnMachineFunction(MachineFunction &MF) {
+  Subtarget = &MF.getSubtarget<SparcSubtarget>();
+  const TargetInstrInfo &TII = *Subtarget->getInstrInfo();
+
+  bool Modified = false;
+  for (auto MFI = MF.begin(), E = MF.end(); MFI != E; ++MFI) {
+    MachineBasicBlock &MBB = *MFI;
+    for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
+      MachineInstr &MI = *MBBI;
+      unsigned Opcode = MI.getOpcode();
+      if (Opcode == SP::SDIVrr) {
+        MI.setDesc(TII.get(SP::SDIVCCrr));
+        Modified = true;
+      } else if (Opcode == SP::SDIVri) {
+        MI.setDesc(TII.get(SP::SDIVCCri));
+        Modified = true;
+      }
+    }
+  }
+
+  return Modified;
+}
+
+static RegisterPass<ReplaceSDIV> X("replace-sdiv", "Replase SDIV Pass", false,
+                                   false);
+
+//*****************************************************************************
+//**** FixCALL pass
+//*****************************************************************************
+// This pass restricts the size of the immediate operand of the CALL
+// instruction, which can cause problems on some earlier versions of the LEON
+// processor, which can interpret some of the call address bits incorrectly.
+//
+char FixCALL::ID = 0;
+
+FixCALL::FixCALL(TargetMachine &tm) : LEONMachineFunctionPass(tm, ID) {}
+
+bool FixCALL::runOnMachineFunction(MachineFunction &MF) {
+  bool Modified = false;
+
+  for (auto MFI = MF.begin(), E = MF.end(); MFI != E; ++MFI) {
+    MachineBasicBlock &MBB = *MFI;
+    for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
+      MachineInstr &MI = *MBBI;
+      MI.print(errs());
+      errs() << "\n";
+
+      unsigned Opcode = MI.getOpcode();
+      if (Opcode == SP::CALL || Opcode == SP::CALLrr) {
+        unsigned NumOperands = MI.getNumOperands();
+        for (unsigned OperandIndex = 0; OperandIndex < NumOperands;
+             OperandIndex++) {
+          MachineOperand &MO = MI.getOperand(OperandIndex);
+          if (MO.isImm()) {
+            int64_t Value = MO.getImm();
+            MO.setImm(Value & 0x000fffffL);
+            Modified = true;
+            break;
+          }
+        }
+      } else if (MI.isInlineAsm()) // inline assembly immediate call
+      {
+        StringRef AsmString =
+            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName();
+        if (AsmString.startswith_lower("call")) {
+          // this is an inline call instruction
+          unsigned StartOp = InlineAsm::MIOp_FirstOperand;
+
+          // extracts the registers from the inline assembly instruction
+          for (unsigned i = StartOp, e = MI.getNumOperands(); i != e; ++i) {
+            MachineOperand &MO = MI.getOperand(i);
+            if (MO.isImm()) {
+              int64_t Value = MO.getImm();
+              MO.setImm(Value & 0x000fffffL);
+              Modified = true;
+            }
+          }
+        }
+      }
+    }
+  }
+
+  return Modified;
+}
+
+//*****************************************************************************
+//**** IgnoreZeroFlag pass
+//*****************************************************************************
+// This erratum fix fixes the overflow behavior of SDIVCC and UDIVCC
+// instructions that exists on some earlier LEON processors. Where these
+// instructions are detected, they are replaced by a sequence that will
+// explicitly write the overflow bit flag if this is required.
+//
+char IgnoreZeroFlag::ID = 0;
+
+IgnoreZeroFlag::IgnoreZeroFlag(TargetMachine &tm)
+    : LEONMachineFunctionPass(tm, ID) {}
+
+bool IgnoreZeroFlag::runOnMachineFunction(MachineFunction &MF) {
+  Subtarget = &MF.getSubtarget<SparcSubtarget>();
+  const TargetInstrInfo &TII = *Subtarget->getInstrInfo();
+  DebugLoc DL = DebugLoc();
+
+  bool Modified = false;
+  for (auto MFI = MF.begin(), E = MF.end(); MFI != E; ++MFI) {
+    MachineBasicBlock &MBB = *MFI;
+    for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
+      MachineInstr &MI = *MBBI;
+      unsigned Opcode = MI.getOpcode();
+      if (Opcode == SP::SDIVCCrr || Opcode == SP::SDIVCCri ||
+          Opcode == SP::UDIVCCrr || Opcode == SP::UDIVCCri) {
+
+        // split the current machine basic block - just after the sdivcc/udivcc
+        // instruction
+        // create a label that help us skip the zero flag update (of PSR -
+        // Processor Status Register)
+        // if conditions are not met
+        const BasicBlock *LLVM_BB = MBB.getBasicBlock();
+        MachineFunction::iterator It =
+            std::next(MachineFunction::iterator(MBB));
+
+        MachineBasicBlock *dneBB = MF.CreateMachineBasicBlock(LLVM_BB);
+        MF.insert(It, dneBB);
+
+        // Transfer the remainder of MBB and its successor edges to dneBB.
+        dneBB->splice(dneBB->begin(), &MBB,
+                      std::next(MachineBasicBlock::iterator(MI)), MBB.end());
+        dneBB->transferSuccessorsAndUpdatePHIs(&MBB);
+
+        MBB.addSuccessor(dneBB);
+
+        MachineBasicBlock::iterator NextMBBI = std::next(MBBI);
+
+        // bvc - branch if overflow flag not set
+        BuildMI(MBB, NextMBBI, DL, TII.get(SP::BCOND))
+            .addMBB(dneBB)
+            .addImm(SPCC::ICC_VS);
+
+        // bnz - branch if not zero
+        BuildMI(MBB, NextMBBI, DL, TII.get(SP::BCOND))
+            .addMBB(dneBB)
+            .addImm(SPCC::ICC_NE);
+
+        // use the WRPSR (Write Processor State Register) instruction to set the
+        // zeo flag to 1
+        // create wr %g0, 1, %psr
+        BuildMI(MBB, NextMBBI, DL, TII.get(SP::WRPSRri))
+            .addReg(SP::G0)
+            .addImm(1);
+
+        BuildMI(MBB, NextMBBI, DL, TII.get(SP::NOP));
+
+        Modified = true;
+      } else if (MI.isInlineAsm()) {
+        StringRef AsmString =
+            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName();
+        if (AsmString.startswith_lower("sdivcc") ||
+            AsmString.startswith_lower("udivcc")) {
+          // this is an inline SDIVCC or UDIVCC instruction
+
+          // split the current machine basic block - just after the
+          // sdivcc/udivcc instruction
+          // create a label that help us skip the zero flag update (of PSR -
+          // Processor Status Register)
+          // if conditions are not met
+          const BasicBlock *LLVM_BB = MBB.getBasicBlock();
+          MachineFunction::iterator It =
+              std::next(MachineFunction::iterator(MBB));
+
+          MachineBasicBlock *dneBB = MF.CreateMachineBasicBlock(LLVM_BB);
+          MF.insert(It, dneBB);
+
+          // Transfer the remainder of MBB and its successor edges to dneBB.
+          dneBB->splice(dneBB->begin(), &MBB,
+                        std::next(MachineBasicBlock::iterator(MI)), MBB.end());
+          dneBB->transferSuccessorsAndUpdatePHIs(&MBB);
+
+          MBB.addSuccessor(dneBB);
+
+          MachineBasicBlock::iterator NextMBBI = std::next(MBBI);
+
+          // bvc - branch if overflow flag not set
+          BuildMI(MBB, NextMBBI, DL, TII.get(SP::BCOND))
+              .addMBB(dneBB)
+              .addImm(SPCC::ICC_VS);
+
+          // bnz - branch if not zero
+          BuildMI(MBB, NextMBBI, DL, TII.get(SP::BCOND))
+              .addMBB(dneBB)
+              .addImm(SPCC::ICC_NE);
+
+          // use the WRPSR (Write Processor State Register) instruction to set
+          // the zeo flag to 1
+          // create wr %g0, 1, %psr
+          BuildMI(MBB, NextMBBI, DL, TII.get(SP::WRPSRri))
+              .addReg(SP::G0)
+              .addImm(1);
+
+          BuildMI(MBB, NextMBBI, DL, TII.get(SP::NOP));
+
+          Modified = true;
+        }
+      }
+    }
+  }
+
+  return Modified;
+}
+
+//*****************************************************************************
+//**** InsertNOPDoublePrecision pass
+//*****************************************************************************
+// This erratum fix for some earlier LEON processors fixes a problem where a
+// double precision load will not yield the correct result if used in FMUL,
+// FDIV, FADD, FSUB or FSQRT instructions later. If this sequence is detected,
+// inserting a NOP between the two instructions will fix the erratum.
+// 1.scans the code after register allocation;
+// 2.checks for the problem conditions as described in the AT697E erratum
+// “Odd-Numbered FPU Register Dependency not Properly Checked in some
+// Double-Precision FPU Operations”;
+// 3.inserts NOPs if the problem exists.
+//
+char InsertNOPDoublePrecision::ID = 0;
+
+InsertNOPDoublePrecision::InsertNOPDoublePrecision(TargetMachine &tm)
+    : LEONMachineFunctionPass(tm, ID) {}
+
+bool InsertNOPDoublePrecision::runOnMachineFunction(MachineFunction &MF) {
+  Subtarget = &MF.getSubtarget<SparcSubtarget>();
+  const TargetInstrInfo &TII = *Subtarget->getInstrInfo();
+  DebugLoc DL = DebugLoc();
+
+  bool Modified = false;
+  for (auto MFI = MF.begin(), E = MF.end(); MFI != E; ++MFI) {
+    MachineBasicBlock &MBB = *MFI;
+    for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
+      MachineInstr &MI = *MBBI;
+      unsigned Opcode = MI.getOpcode();
+      if (Opcode == SP::LDDFri || Opcode == SP::LDDFrr) {
+        MachineBasicBlock::iterator NMBBI = std::next(MBBI);
+        MachineInstr &NMI = *NMBBI;
+
+        unsigned NextOpcode = NMI.getOpcode();
+        // NMI.print(errs());
+        if (NextOpcode == SP::FADDD || NextOpcode == SP::FSUBD ||
+            NextOpcode == SP::FMULD || NextOpcode == SP::FDIVD) {
+          int RegAIndex = GetRegIndexForOperand(MI, 0);
+          int RegBIndex = GetRegIndexForOperand(NMI, 0);
+          int RegCIndex =
+              GetRegIndexForOperand(NMI, 2); // Second source operand is index 2
+          int RegDIndex =
+              GetRegIndexForOperand(NMI, 1); // Destination operand is index 1
+
+          if ((RegAIndex == RegBIndex + 1 && RegBIndex == RegDIndex) ||
+              (RegAIndex == RegCIndex + 1 && RegCIndex == RegDIndex) ||
+              (RegAIndex == RegBIndex + 1 && RegCIndex == RegDIndex) ||
+              (RegAIndex == RegCIndex + 1 && RegBIndex == RegDIndex)) {
+            // Insert NOP between the two instructions.
+            BuildMI(MBB, NMBBI, DL, TII.get(SP::NOP));
+            Modified = true;
+          }
+
+          // Check the errata patterns that only happen for FADDD and FMULD
+          if (Modified == false &&
+              (NextOpcode == SP::FADDD || NextOpcode == SP::FMULD)) {
+            RegAIndex = GetRegIndexForOperand(MI, 1);
+            if (RegAIndex == RegBIndex + 1 && RegBIndex == RegCIndex &&
+                RegBIndex == RegDIndex) {
+              // Insert NOP between the two instructions.
+              BuildMI(MBB, NMBBI, DL, TII.get(SP::NOP));
+              Modified = true;
+            }
+          }
+        } else if (NextOpcode == SP::FSQRTD) {
+          int RegAIndex = GetRegIndexForOperand(MI, 1);
+          int RegBIndex = GetRegIndexForOperand(NMI, 0);
+          int RegCIndex = GetRegIndexForOperand(NMI, 1);
+
+          if (RegAIndex == RegBIndex + 1 && RegBIndex == RegCIndex) {
+            // Insert NOP between the two instructions.
+            BuildMI(MBB, NMBBI, DL, TII.get(SP::NOP));
+            Modified = true;
+          }
+        }
+      }
+    }
+  }
+
+  return Modified;
+}
+
+//*****************************************************************************
+//**** PreventRoundChange pass
+//*****************************************************************************
+// To prevent any explicit change of the default rounding mode, this pass
+// detects any call of the fesetround function and removes this call from the
+// list of generated operations.
+//
+char PreventRoundChange::ID = 0;
+
+PreventRoundChange::PreventRoundChange(TargetMachine &tm)
+    : LEONMachineFunctionPass(tm, ID) {}
+
+bool PreventRoundChange::runOnMachineFunction(MachineFunction &MF) {
+  Subtarget = &MF.getSubtarget<SparcSubtarget>();
+
+  bool Modified = false;
+  for (auto MFI = MF.begin(), E = MF.end(); MFI != E; ++MFI) {
+    MachineBasicBlock &MBB = *MFI;
+    for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
+      MachineInstr &MI = *MBBI;
+      unsigned Opcode = MI.getOpcode();
+      if (Opcode == SP::CALL && MI.getNumOperands() > 0) {
+        MachineOperand &MO = MI.getOperand(0);
+
+        if (MO.isGlobal()) {
+          StringRef FuncName = MO.getGlobal()->getName();
+          if (FuncName.compare_lower("fesetround") == 0) {
+            MachineBasicBlock::iterator NMBBI = std::next(MBBI);
+            MI.eraseFromParent();
+            MBBI = NMBBI;
+            Modified = true;
+          }
+        }
+      }
+    }
+  }
+
+  return Modified;
+}
+//*****************************************************************************
+//**** FlushCacheLineSWAP pass
+//*****************************************************************************
+// This pass inserts FLUSHW just before any SWAP atomic instruction.
+//
+char FlushCacheLineSWAP::ID = 0;
+
+FlushCacheLineSWAP::FlushCacheLineSWAP(TargetMachine &tm)
+    : LEONMachineFunctionPass(tm, ID) {}
+
+bool FlushCacheLineSWAP::runOnMachineFunction(MachineFunction &MF) {
+  Subtarget = &MF.getSubtarget<SparcSubtarget>();
+  const TargetInstrInfo &TII = *Subtarget->getInstrInfo();
+  DebugLoc DL = DebugLoc();
+
+  bool Modified = false;
+  for (auto MFI = MF.begin(), E = MF.end(); MFI != E; ++MFI) {
+    MachineBasicBlock &MBB = *MFI;
+    for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
+      MachineInstr &MI = *MBBI;
+      unsigned Opcode = MI.getOpcode();
+      if (Opcode == SP::SWAPrr || Opcode == SP::SWAPri ||
+          Opcode == SP::LDSTUBrr || Opcode == SP::LDSTUBri) {
+        // insert flush and 5 NOPs before the swap/ldstub instruction
+        BuildMI(MBB, MBBI, DL, TII.get(SP::FLUSH));
+        BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+        BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+        BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+        BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+        BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+
+        Modified = true;
+      } else if (MI.isInlineAsm()) {
+        StringRef AsmString =
+            MI.getOperand(InlineAsm::MIOp_AsmString).getSymbolName();
+        if (AsmString.startswith_lower("swap") ||
+            AsmString.startswith_lower("ldstub")) {
+          // this is an inline swap or ldstub instruction
+
+          // insert flush and 5 NOPs before the swap/ldstub instruction
+          BuildMI(MBB, MBBI, DL, TII.get(SP::FLUSH));
+          BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+          BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+          BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+          BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+          BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+
+          Modified = true;
+        }
+      }
+    }
+  }
+
+  return Modified;
+}
+
+//*****************************************************************************
+//**** InsertNOPsLoadStore pass
+//*****************************************************************************
+// This pass shall insert NOPs between floating point loads and stores when the
+// following circumstances are present [5]:
+// Pattern 1:
+// 1. single-precision load or single-precision FPOP to register %fX, where X is
+// the same register as the store being checked;
+// 2. single-precision load or single-precision FPOP to register %fY , where Y
+// is the opposite register in the same double-precision pair;
+// 3. 0-3 instructions of any kind, except stores from %fX or %fY or operations
+// with %fX as destination;
+// 4. the store (from register %fX) being considered.
+// Pattern 2:
+// 1. double-precision FPOP;
+// 2. any number of operations on any kind, except no double-precision FPOP and
+// at most one (less than two) single-precision or single-to-double FPOPs;
+// 3. the store (from register %fX) being considered.
+//
+char InsertNOPsLoadStore::ID = 0;
+
+InsertNOPsLoadStore::InsertNOPsLoadStore(TargetMachine &tm)
+    : LEONMachineFunctionPass(tm, ID) {}
+
+bool InsertNOPsLoadStore::runOnMachineFunction(MachineFunction &MF) {
+  Subtarget = &MF.getSubtarget<SparcSubtarget>();
+  const TargetInstrInfo &TII = *Subtarget->getInstrInfo();
+  DebugLoc DL = DebugLoc();
+
+  MachineInstr *Pattern1FirstInstruction = NULL;
+  MachineInstr *Pattern2FirstInstruction = NULL;
+  unsigned int StoreInstructionsToCheck = 0;
+  int FxRegIndex, FyRegIndex;
+
+  bool Modified = false;
+  for (auto MFI = MF.begin(), E = MF.end(); MFI != E; ++MFI) {
+    MachineBasicBlock &MBB = *MFI;
+    for (auto MBBI = MBB.begin(), E = MBB.end(); MBBI != E; ++MBBI) {
+      MachineInstr &MI = *MBBI;
+
+      if (StoreInstructionsToCheck > 0) {
+        if (((MI.getOpcode() == SP::STFrr || MI.getOpcode() == SP::STFri) &&
+             (GetRegIndexForOperand(MI, LAST_OPERAND) == FxRegIndex ||
+              GetRegIndexForOperand(MI, LAST_OPERAND) == FyRegIndex)) ||
+            GetRegIndexForOperand(MI, 0) == FxRegIndex) {
+          // Insert four NOPs
+          for (unsigned InsertedCount = 0; InsertedCount < 4; InsertedCount++) {
+            BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+          }
+          Modified = true;
+        }
+        StoreInstructionsToCheck--;
+      }
+
+      switch (MI.getOpcode()) {
+      // Watch for Pattern 1 FPop instructions
+      case SP::LDrr:
+      case SP::LDri:
+      case SP::LDFrr:
+      case SP::LDFri:
+      case SP::FADDS:
+      case SP::FSUBS:
+      case SP::FMULS:
+      case SP::FDIVS:
+      case SP::FSQRTS:
+      case SP::FCMPS:
+      case SP::FMOVS:
+      case SP::FNEGS:
+      case SP::FABSS:
+      case SP::FITOS:
+      case SP::FSTOI:
+      case SP::FITOD:
+      case SP::FDTOI:
+      case SP::FDTOS:
+        if (Pattern1FirstInstruction != NULL) {
+          FxRegIndex = GetRegIndexForOperand(*Pattern1FirstInstruction, 0);
+          FyRegIndex = GetRegIndexForOperand(MI, 0);
+
+          // Check to see if these registers are part of the same double
+          // precision
+          // register pair.
+          int DoublePrecRegIndexForX = (FxRegIndex - SP::F0) / 2;
+          int DoublePrecRegIndexForY = (FyRegIndex - SP::F0) / 2;
+
+          if (DoublePrecRegIndexForX == DoublePrecRegIndexForY)
+            StoreInstructionsToCheck = 4;
+        }
+
+        Pattern1FirstInstruction = &MI;
+        break;
+      // End of Pattern 1
+
+      // Search for Pattern 2
+      case SP::FADDD:
+      case SP::FSUBD:
+      case SP::FMULD:
+      case SP::FDIVD:
+      case SP::FSQRTD:
+      case SP::FCMPD:
+        Pattern2FirstInstruction = &MI;
+        Pattern1FirstInstruction = NULL;
+        break;
+
+      case SP::STFrr:
+      case SP::STFri:
+      case SP::STDFrr:
+      case SP::STDFri:
+        if (Pattern2FirstInstruction != NULL) {
+          if (GetRegIndexForOperand(MI, LAST_OPERAND) ==
+              GetRegIndexForOperand(*Pattern2FirstInstruction, 0)) {
+            // Insert four NOPs
+            for (unsigned InsertedCount = 0; InsertedCount < 4;
+                 InsertedCount++) {
+              BuildMI(MBB, MBBI, DL, TII.get(SP::NOP));
+            }
+
+            Pattern2FirstInstruction = NULL;
+          }
+        }
+        Pattern1FirstInstruction = NULL;
+        break;
+      // End of Pattern 2
+
+      default:
+        // Ensure we don't count debug-only values while we're testing for the
+        // patterns.
+        if (!MI.isDebugValue())
+          Pattern1FirstInstruction = NULL;
+        break;
+      }
+    }
+  }
+
+  return Modified;
+}

llvm/trunk/lib/Target/Sparc/Sparc.td

 
 include "llvm/Target/Target.td"
 
 //===----------------------------------------------------------------------===//
 // SPARC Subtarget features.
 //
 
 def FeatureV9
-  : SubtargetFeature<"v9", "IsV9", "true",
-                     "Enable SPARC-V9 instructions">;
+    : SubtargetFeature<"v9", "IsV9", "true", "Enable SPARC-V9 instructions">;
 def FeatureV8Deprecated
     : SubtargetFeature<"deprecated-v8", "V8DeprecatedInsts", "true",
                        "Enable deprecated V8 instructions in V9 mode">;
 def FeatureVIS
     : SubtargetFeature<"vis", "IsVIS", "true",
                        "Enable UltraSPARC Visual Instruction Set extensions">;
 def FeatureVIS2
     : SubtargetFeature<"vis2", "IsVIS2", "true",
                        "Enable Visual Instruction Set extensions II">;
 def FeatureVIS3
     : SubtargetFeature<"vis3", "IsVIS3", "true",
                        "Enable Visual Instruction Set extensions III">;
 def FeatureLeon
-  : SubtargetFeature<"leon", "IsLeon", "true",
-                     "Enable LEON extensions">;
+    : SubtargetFeature<"leon", "IsLeon", "true", "Enable LEON extensions">;
 
 def FeatureHardQuad
     : SubtargetFeature<"hard-quad-float", "HasHardQuad", "true",
                        "Enable quad-word floating point instructions">;
 
 def UsePopc : SubtargetFeature<"popc", "UsePopc", "true",
                                "Use the popc (population count) instruction">;
 
-def FeatureSoftFloat : SubtargetFeature<"soft-float", "UseSoftFloat", "true",
-                              "Use software emulation for floating point">;  
+def FeatureSoftFloat
+    : SubtargetFeature<"soft-float", "UseSoftFloat", "true",
+                       "Use software emulation for floating point">;
 
-//==== Features added predmoninantly for LEON subtarget support                               
+//==== Features added predmoninantly for LEON subtarget support
 include "LeonFeatures.td"
 
 //===----------------------------------------------------------------------===//
 // Register File, Calling Conv, Instruction Descriptions
 //===----------------------------------------------------------------------===//
 
 include "SparcRegisterInfo.td"
 include "SparcCallingConv.td"
 include "SparcSchedule.td"
 include "SparcInstrInfo.td"
 
 def SparcInstrInfo : InstrInfo;
 
-def SparcAsmParser : AsmParser {
-  bit ShouldEmitMatchRegisterName = 0;
-}
+def SparcAsmParser : AsmParser { bit ShouldEmitMatchRegisterName = 0; }
 
 //===----------------------------------------------------------------------===//
 // SPARC processors supported.
 //===----------------------------------------------------------------------===//
 
 class Proc<string Name, list<SubtargetFeature> Features>
     : Processor<Name, NoItineraries, Features>;
 
-def : Proc<"generic",         []>;
-def : Proc<"v7",              []>;
-def : Proc<"v8",              []>;
-def : Proc<"supersparc",      []>;
-def : Proc<"sparclite",       []>;
-def : Proc<"f934",            []>;
-def : Proc<"hypersparc",      []>;
-def : Proc<"sparclite86x",    []>;
-def : Proc<"sparclet",        []>;
-def : Proc<"tsc701",          []>;
-def : Proc<"myriad2",         []>;
-def : Proc<"myriad2.1",       []>;
-def : Proc<"myriad2.2",       []>;
-def : Proc<"v9",              [FeatureV9]>;
-def : Proc<"ultrasparc",      [FeatureV9, FeatureV8Deprecated, FeatureVIS]>;
-def : Proc<"ultrasparc3",     [FeatureV9, FeatureV8Deprecated, FeatureVIS,
-                               FeatureVIS2]>;
-def : Proc<"niagara",         [FeatureV9, FeatureV8Deprecated, FeatureVIS,
-                               FeatureVIS2]>;
-def : Proc<"niagara2",        [FeatureV9, FeatureV8Deprecated, UsePopc,
-                               FeatureVIS, FeatureVIS2]>;
-def : Proc<"niagara3",        [FeatureV9, FeatureV8Deprecated, UsePopc,
-                               FeatureVIS, FeatureVIS2]>;
-def : Proc<"niagara4",        [FeatureV9, FeatureV8Deprecated, UsePopc,
-                               FeatureVIS, FeatureVIS2, FeatureVIS3]>;
+def : Proc<"generic", []>;
+def : Proc<"v7", []>;
+def : Proc<"v8", []>;
+def : Proc<"supersparc", []>;
+def : Proc<"sparclite", []>;
+def : Proc<"f934", []>;
+def : Proc<"hypersparc", []>;
+def : Proc<"sparclite86x", []>;
+def : Proc<"sparclet", []>;
+def : Proc<"tsc701", []>;
+def : Proc<"myriad2", []>;
+def : Proc<"myriad2.1", []>;
+def : Proc<"myriad2.2", []>;
+def : Proc<"v9", [ FeatureV9 ]>;
+def : Proc<"ultrasparc", [ FeatureV9, FeatureV8Deprecated, FeatureVIS ]>;
+def : Proc<"ultrasparc3",
+           [ FeatureV9, FeatureV8Deprecated, FeatureVIS, FeatureVIS2 ]>;
+def : Proc<"niagara",
+           [ FeatureV9, FeatureV8Deprecated, FeatureVIS, FeatureVIS2 ]>;
+def : Proc<"niagara2", [
+  FeatureV9, FeatureV8Deprecated, UsePopc, FeatureVIS, FeatureVIS2
+]>;
+def : Proc<"niagara3", [
+  FeatureV9, FeatureV8Deprecated, UsePopc, FeatureVIS, FeatureVIS2
+]>;
+def : Proc<"niagara4", [
+  FeatureV9, FeatureV8Deprecated, UsePopc, FeatureVIS, FeatureVIS2, FeatureVIS3
+]>;
 
 // LEON 2 FT generic
-def : Processor<"leon2", LEON2Itineraries,
-                [FeatureLeon]>;
+def : Processor<"leon2", LEON2Itineraries, [ FeatureLeon ]>;
 
 // LEON 2 FT (AT697E)
-// TO DO: Place-holder: Processor specific features will be added *very* soon here.
-def : Processor<"at697e", LEON2Itineraries,
-                [FeatureLeon, InsertNOPLoad]>;
+// AT697E: Provides full coverage of AT697E - covers all the erratum fixes for
+// LEON2 AT697E
+def : Processor<"at697e", LEON2Itineraries, [
+  FeatureLeon, ReplaceSDIV, FixCALL, IgnoreZeroFlag, InsertNOPDoublePrecision
+]>;
 
 // LEON 2 FT (AT697F)
-// TO DO: Place-holder: Processor specific features will be added *very* soon here.
+// AT697F: Provides full coverage of AT697F - covers all the erratum fixes for
+// LEON2 AT697F
 def : Processor<"at697f", LEON2Itineraries,
-                [FeatureLeon, InsertNOPLoad]>;
-
+                [ FeatureLeon, InsertNOPDoublePrecision ]>;
 
 // LEON 3 FT generic
-def : Processor<"leon3", LEON3Itineraries,
-                [FeatureLeon, UMACSMACSupport]>;
+def : Processor<"leon3", LEON3Itineraries, [ FeatureLeon, UMACSMACSupport ]>;
 
 // LEON 3 FT (UT699). Provides features for the UT699 processor
-// - covers all the erratum fixes for LEON3, but does not support the CASA instruction.
-def : Processor<"ut699", LEON3Itineraries, 
-                [FeatureLeon, InsertNOPLoad, FixFSMULD, ReplaceFMULS, FixAllFDIVSQRT]>;
+// - covers all the erratum fixes for LEON3, but does not support the CASA
+// instruction.
+def : Processor<"ut699", LEON3Itineraries, [
+  FeatureLeon, FixFSMULD, ReplaceFMULS, PreventRoundChange,
+  FixAllFDIVSQRT, InsertNOPLoad, FlushCacheLineSWAP, InsertNOPsLoadStore
+]>;
 
 // LEON3 FT (GR712RC). Provides features for the GR712RC processor.
-// - covers all the erratum fixed for LEON3 and support for the CASA instruction. 
+// - covers all the erratum fixed for LEON3 and support for the CASA
+// instruction.
 def : Processor<"gr712rc", LEON3Itineraries,
-                [FeatureLeon, LeonCASA]>;
+                [ FeatureLeon, LeonCASA ]>;
 
 // LEON 4 FT generic
 def : Processor<"leon4", LEON4Itineraries,
-                [FeatureLeon, UMACSMACSupport, LeonCASA]>;
+                [ FeatureLeon, LeonCASA ]>;
 
-// LEON 4 FT (GR740) 
-// TO DO: Place-holder: Processor specific features will be added *very* soon here.
-def : Processor<"gr740", LEON4Itineraries, 
-                [FeatureLeon, UMACSMACSupport, LeonCASA]>;
+// GR740: Provides full coverage of GR740 - covers all the erratum fixes for
+// LEON3 + support to CASA + LEON 4 instruction timings
+def : Processor<"gr740", LEON4Itineraries,
+                [ FeatureLeon, LeonCASA ]> {}
 
 //===----------------------------------------------------------------------===//
 // Declare the target which we are implementing
 //===----------------------------------------------------------------------===//
 
 def SparcAsmWriter : AsmWriter {
-  string AsmWriterClassName  = "InstPrinter";
+  string AsmWriterClassName = "InstPrinter";
   int PassSubtarget = 1;
   int Variant = 0;
 }
 
 def Sparc : Target {
   // Pull in Instruction Info:
   let InstructionSet = SparcInstrInfo;
-  let AssemblyParsers  = [SparcAsmParser];
-  let AssemblyWriters = [SparcAsmWriter];
+  let AssemblyParsers = [ SparcAsmParser ];
+  let AssemblyWriters = [ SparcAsmWriter ];
 }

llvm/trunk/lib/Target/Sparc/SparcISelLowering.cpp

 #include "llvm/CodeGen/SelectionDAG.h"
 #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/ErrorHandling.h"
 using namespace llvm;
 
-
 //===----------------------------------------------------------------------===//
 // Calling Convention Implementation
 //===----------------------------------------------------------------------===//
 
 static bool CC_Sparc_Assign_SRet(unsigned &ValNo, MVT &ValVT,
                                  MVT &LocVT, CCValAssign::LocInfo &LocInfo,
                                  ISD::ArgFlagsTy &ArgFlags, CCState &State)
 {
if (Subtarget->is64Bit()) {
     setOperationAction(ISD::ROTR , MVT::i64, Expand);
     setOperationAction(ISD::DYNAMIC_STACKALLOC, MVT::i64, Custom);
   }
 
   // ATOMICs.
   // Atomics are supported on SparcV9. 32-bit atomics are also
   // supported by some Leon SparcV8 variants. Otherwise, atomics
   // are unsupported.
-  if (Subtarget->isV9())
-    setMaxAtomicSizeInBitsSupported(64);
-  else if (Subtarget->hasLeonCasa())
+  if (Subtarget->isV9() || Subtarget->hasLeonCasa())
     setMaxAtomicSizeInBitsSupported(64);
   else
     setMaxAtomicSizeInBitsSupported(0);
 
   setMinCmpXchgSizeInBits(32);
 
   setOperationAction(ISD::ATOMIC_SWAP, MVT::i32, Legal);
 

 
 
 static SDValue LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG,
                               const SparcSubtarget *Subtarget) {
 
   uint64_t depth = Op.getConstantOperandVal(0);
 
   return getFRAMEADDR(depth, Op, DAG, Subtarget);
-
 }
 
 static SDValue LowerRETURNADDR(SDValue Op, SelectionDAG &DAG,
                                const SparcTargetLowering &TLI,
                                const SparcSubtarget *Subtarget) {
   MachineFunction &MF = DAG.getMachineFunction();
   MachineFrameInfo *MFI = MF.getFrameInfo();
   MFI->setReturnAddressIsTaken(true);
LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::INTRINSIC_WO_CHAIN: return LowerINTRINSIC_WO_CHAIN(Op, DAG);
   }
 }
 
 MachineBasicBlock *
 SparcTargetLowering::EmitInstrWithCustomInserter(MachineInstr &MI,
                                                  MachineBasicBlock *BB) const {
   switch (MI.getOpcode()) {
-  default: llvm_unreachable("Unknown SELECT_CC!");
+  default: llvm_unreachable("Unknown Custom Instruction!");
   case SP::SELECT_CC_Int_ICC:
   case SP::SELECT_CC_FP_ICC:
   case SP::SELECT_CC_DFP_ICC:
   case SP::SELECT_CC_QFP_ICC:
     return expandSelectCC(MI, BB, SP::BCOND);
   case SP::SELECT_CC_Int_FCC:
   case SP::SELECT_CC_FP_FCC:
   case SP::SELECT_CC_DFP_FCC:
   case SP::SELECT_CC_QFP_FCC:
     return expandSelectCC(MI, BB, SP::FBCOND);
   case SP::EH_SJLJ_SETJMP32ri:
   case SP::EH_SJLJ_SETJMP32rr:
     return emitEHSjLjSetJmp(MI, BB);
   case SP::EH_SJLJ_LONGJMP32rr:
   case SP::EH_SJLJ_LONGJMP32ri:
     return emitEHSjLjLongJmp(MI, BB);
-
   }
 }
 
 MachineBasicBlock *
 SparcTargetLowering::expandSelectCC(MachineInstr &MI, MachineBasicBlock *BB,
                                     unsigned BROpcode) const {
   const TargetInstrInfo &TII = *Subtarget->getInstrInfo();
   DebugLoc dl = MI.getDebugLoc();

 //===----------------------------------------------------------------------===//
 
 /// getConstraintType - Given a constraint letter, return the type of
 /// constraint it is for this target.
 SparcTargetLowering::ConstraintType
 SparcTargetLowering::getConstraintType(StringRef Constraint) const {
   if (Constraint.size() == 1) {
     switch (Constraint[0]) {
-    default:  break;
-    case 'r': return C_RegisterClass;
+    default:
+      break;
+    case 'f':
+    case 'r':
+      return C_RegisterClass;
     case 'I': // SIMM13
       return C_Other;
     }
   }
 
   return TargetLowering::getConstraintType(Constraint);
 }
 

 }
 
 std::pair<unsigned, const TargetRegisterClass *>
 SparcTargetLowering::getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
                                                   StringRef Constraint,
                                                   MVT VT) const {
   if (Constraint.size() == 1) {
     switch (Constraint[0]) {
+    case 'f':
+      return std::make_pair(0U, &SP::FPRegsRegClass);
+
     case 'r':
       if (VT == MVT::v2i32)
         return std::make_pair(0U, &SP::IntPairRegClass);
       else
         return std::make_pair(0U, &SP::IntRegsRegClass);
     }
   } else if (!Constraint.empty() && Constraint.size() <= 5
               && Constraint[0] == '{' && *(Constraint.end()-1) == '}') {

llvm/trunk/lib/Target/Sparc/SparcSubtarget.h

class SparcSubtarget : public SparcGenSubtargetInfo {
 
   // LEON features
   bool HasUmacSmac;
   bool HasLeonCasa;
   bool InsertNOPLoad;
   bool FixFSMULD;
   bool ReplaceFMULS;
   bool FixAllFDIVSQRT;
+  bool UseSoftFpu;
+  bool PerformSDIVReplace;
+  bool FixCallImmediates;
+  bool IgnoreZeroFlag;
+  bool InsertNOPDoublePrecision;
+  bool PreventRoundChange;
+  bool FlushCacheLineSWAP;
+  bool InsertNOPsLoadStore;
 
   SparcInstrInfo InstrInfo;
   SparcTargetLowering TLInfo;
   SelectionDAGTargetInfo TSInfo;
   SparcFrameLowering FrameLowering;
 
 public:
   SparcSubtarget(const Triple &TT, const std::string &CPU,
public:
   bool isVIS2() const { return IsVIS2; }
   bool isVIS3() const { return IsVIS3; }
   bool useDeprecatedV8Instructions() const { return V8DeprecatedInsts; }
   bool hasHardQuad() const { return HasHardQuad; }
   bool usePopc() const { return UsePopc; }
   bool useSoftFloat() const { return UseSoftFloat; }
 
   // Leon options
-  bool hasUmacSmac() const { return HasUmacSmac; }
+  bool useSoftFpu() const { return UseSoftFpu; }
   bool hasLeonCasa() const { return HasLeonCasa; }
-  bool insertNOPLoad() const { return InsertNOPLoad; }
+  bool hasUmacSmac() const { return HasUmacSmac; }
+  bool performSDIVReplace() const { return PerformSDIVReplace; }
+  bool fixCallImmediates() const { return FixCallImmediates; }
+  bool ignoreZeroFlag() const { return IgnoreZeroFlag; }
+  bool insertNOPDoublePrecision() const { return InsertNOPDoublePrecision; }
   bool fixFSMULD() const { return FixFSMULD; }
   bool replaceFMULS() const { return ReplaceFMULS; }
+  bool preventRoundChange() const { return PreventRoundChange; }
   bool fixAllFDIVSQRT() const { return FixAllFDIVSQRT; }
+  bool flushCacheLineSWAP() const { return FlushCacheLineSWAP; }
+  bool insertNOPsLoadStore() const { return InsertNOPsLoadStore; }
+  bool insertNOPLoad() const { return InsertNOPLoad; }
 
   /// ParseSubtargetFeatures - Parses features string setting specified
   /// subtarget options.  Definition of function is auto generated by tblgen.
   void ParseSubtargetFeatures(StringRef CPU, StringRef FS);
   SparcSubtarget &initializeSubtargetDependencies(StringRef CPU, StringRef FS);
 
   bool is64Bit() const { return Is64Bit; }
 

llvm/trunk/lib/Target/Sparc/SparcSubtarget.cpp

SparcSubtarget &SparcSubtarget::initializeSubtargetDependencies(StringRef CPU,
   IsVIS = false;
   HasHardQuad = false;
   UsePopc = false;
   UseSoftFloat = false;
 
   // Leon features
   HasLeonCasa = false;
   HasUmacSmac = false;
-  InsertNOPLoad = false;
+  PerformSDIVReplace = false;
+  FixCallImmediates = false;
+  IgnoreZeroFlag = false;
+  InsertNOPDoublePrecision = false;
   FixFSMULD = false;
   ReplaceFMULS = false;
+  PreventRoundChange = false;
   FixAllFDIVSQRT = false;
+  InsertNOPLoad = false;
+  FlushCacheLineSWAP = false;
+  InsertNOPsLoadStore = false;
 
   // Determine default and user specified characteristics
   std::string CPUName = CPU;
   if (CPUName.empty())
     CPUName = (Is64Bit) ? "v9" : "v8";
 
   // Parse features string.
   ParseSubtargetFeatures(CPUName, FS);

llvm/trunk/lib/Target/Sparc/SparcTargetMachine.cpp

: LLVMTargetMachine(T, computeDataLayout(TT, is64bit), TT, CPU, FS, Options,
                         getEffectiveRelocModel(RM), CM, OL),
       TLOF(make_unique<SparcELFTargetObjectFile>()),
       Subtarget(TT, CPU, FS, *this, is64bit), is64Bit(is64bit) {
   initAsmInfo();
 }
 
 SparcTargetMachine::~SparcTargetMachine() {}
 
-const SparcSubtarget * 
+const SparcSubtarget *
 SparcTargetMachine::getSubtargetImpl(const Function &F) const {
   Attribute CPUAttr = F.getFnAttribute("target-cpu");
   Attribute FSAttr = F.getFnAttribute("target-features");
 
   std::string CPU = !CPUAttr.hasAttribute(Attribute::None)
                         ? CPUAttr.getValueAsString().str()
                         : TargetCPU;
   std::string FS = !FSAttr.hasAttribute(Attribute::None)
                        ? FSAttr.getValueAsString().str()
                        : TargetFS;
 
   // FIXME: This is related to the code below to reset the target options,
   // we need to know whether or not the soft float flag is set on the
   // function, so we can enable it as a subtarget feature.
   bool softFloat =
       F.hasFnAttribute("use-soft-float") &&
       F.getFnAttribute("use-soft-float").getValueAsString() == "true";
 
-  if (softFloat)         
+  if (softFloat)
     FS += FS.empty() ? "+soft-float" : ",+soft-float";
 
   auto &I = SubtargetMap[CPU + FS];
   if (!I) {
     // This needs to be done before we create a new subtarget since any
     // creation will depend on the TM and the code generation flags on the
     // function that reside in TargetOptions.
     resetTargetOptions(F);
     I = llvm::make_unique<SparcSubtarget>(TargetTriple, CPU, FS, *this,
                                           this->is64Bit);
   }
   return I.get();
 }
 
 namespace {
 /// Sparc Code Generator Pass Configuration Options.
 class SparcPassConfig : public TargetPassConfig {
 public:
   SparcPassConfig(SparcTargetMachine *TM, PassManagerBase &PM)
       : TargetPassConfig(TM, PM) {}
 
   SparcTargetMachine &getSparcTargetMachine() const {
     return getTM<SparcTargetMachine>();
   }
 
   void addIRPasses() override;
   bool addInstSelector() override;
   void addPreEmitPass() override;
void SparcPassConfig::addIRPasses() {
   TargetPassConfig::addIRPasses();
 }
 
 bool SparcPassConfig::addInstSelector() {
   addPass(createSparcISelDag(getSparcTargetMachine()));
   return false;
 }
 
-void SparcPassConfig::addPreEmitPass(){
+void SparcPassConfig::addPreEmitPass() {
   addPass(createSparcDelaySlotFillerPass(getSparcTargetMachine()));
-
-  if (this->getSparcTargetMachine().getSubtargetImpl()->insertNOPLoad())
-  {
-    addPass(new InsertNOPLoad(getSparcTargetMachine()));
+  if (this->getSparcTargetMachine().getSubtargetImpl()->ignoreZeroFlag()) {
+    addPass(new IgnoreZeroFlag(getSparcTargetMachine()));
+  }
+  if (this->getSparcTargetMachine().getSubtargetImpl()->performSDIVReplace()) {
+    addPass(new ReplaceSDIV(getSparcTargetMachine()));
   }
-  if (this->getSparcTargetMachine().getSubtargetImpl()->fixFSMULD())
-  {
+  if (this->getSparcTargetMachine().getSubtargetImpl()->fixCallImmediates()) {
+    addPass(new FixCALL(getSparcTargetMachine()));
+  }
+  if (this->getSparcTargetMachine().getSubtargetImpl()->fixFSMULD()) {
     addPass(new FixFSMULD(getSparcTargetMachine()));
   }
-  if (this->getSparcTargetMachine().getSubtargetImpl()->replaceFMULS())
-  {
+  if (this->getSparcTargetMachine().getSubtargetImpl()->replaceFMULS()) {
     addPass(new ReplaceFMULS(getSparcTargetMachine()));
   }
-  if (this->getSparcTargetMachine().getSubtargetImpl()->fixAllFDIVSQRT())
-  {
+  if (this->getSparcTargetMachine().getSubtargetImpl()->preventRoundChange()) {
+    addPass(new PreventRoundChange(getSparcTargetMachine()));
+  }
+  if (this->getSparcTargetMachine().getSubtargetImpl()->fixAllFDIVSQRT()) {
     addPass(new FixAllFDIVSQRT(getSparcTargetMachine()));
   }
+  if (this->getSparcTargetMachine().getSubtargetImpl()->insertNOPsLoadStore()) {
+    addPass(new InsertNOPsLoadStore(getSparcTargetMachine()));
+  }
+  if (this->getSparcTargetMachine().getSubtargetImpl()->insertNOPLoad()) {
+    addPass(new InsertNOPLoad(getSparcTargetMachine()));
+  }
+  if (this->getSparcTargetMachine().getSubtargetImpl()->flushCacheLineSWAP()) {
+    addPass(new FlushCacheLineSWAP(getSparcTargetMachine()));
+  }
+  if (this->getSparcTargetMachine()
+          .getSubtargetImpl()
+          ->insertNOPDoublePrecision()) {
+    addPass(new InsertNOPDoublePrecision(getSparcTargetMachine()));
+  }
 }
 
-void SparcV8TargetMachine::anchor() { }
+void SparcV8TargetMachine::anchor() {}
 
 SparcV8TargetMachine::SparcV8TargetMachine(const Target &T, const Triple &TT,
                                            StringRef CPU, StringRef FS,
                                            const TargetOptions &Options,
                                            Optional<Reloc::Model> RM,
                                            CodeModel::Model CM,
                                            CodeGenOpt::Level OL)
     : SparcTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, false) {}
 
-void SparcV9TargetMachine::anchor() { }
+void SparcV9TargetMachine::anchor() {}
 
 SparcV9TargetMachine::SparcV9TargetMachine(const Target &T, const Triple &TT,
                                            StringRef CPU, StringRef FS,
                                            const TargetOptions &Options,
                                            Optional<Reloc::Model> RM,
                                            CodeModel::Model CM,
                                            CodeGenOpt::Level OL)
     : SparcTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, true) {}

llvm/trunk/test/CodeGen/SPARC/LeonFixCALLPassUT.ll

+; RUN: llc %s -O0 -march=sparc -mcpu=at697e -o - | FileCheck %s -check-prefix=FIXCALL
+; RUN: llc %s -O0 -march=sparc -mcpu=leon2 -mattr=+fixcall -o - | FileCheck %s -check-prefix=FIXCALL
+
+; RUN: llc %s -O0 -march=sparc -mcpu=at697e -mattr=-fixcall -o - | FileCheck %s -check-prefix=NO_FIXCALL
+; RUN: llc %s -O0 -march=sparc -mcpu=leon2  -o - | FileCheck %s -check-prefix=NO_FIXCALL
+
+
+; FIXCALL-LABEL:        immediate_call_test
+; FIXCALL:        call 763288
+
+; NO_FIXCALL-LABEL:     immediate_call_test
+; NO_FIXCALL:         call 2047583640
+define void @immediate_call_test() nounwind {
+entry:
+        call void asm sideeffect "call $0", "i"(i32 2047583640) nounwind
+        ret void
+}
+
+
+

llvm/trunk/test/CodeGen/SPARC/LeonInsertNOPLoad.ll

+; RUN: llc %s -O0 -march=sparc -mcpu=ut699 -o - | FileCheck %s
+
+; CHECK:        ld [%o0+%lo(.LCPI0_0)], %f0
+; CHECK-NEXT:   nop
+
+
+define float @X() #0 {
+entry:
+  %f = alloca float, align 4
+  store float 0x3FF3C08320000000, float* %f, align 4
+  %0 = load float, float* %f, align 4
+  ret float %0
+}

llvm/trunk/test/CodeGen/SPARC/LeonInsertNOPsDoublePrecision.ll

+; RUN: llc %s -O0 -march=sparc -mcpu=at697f -o - | FileCheck %s
+
+; CHECK:        ldd
+; CHECK:        ldd
+; CHECK-NEXT:   nop
+
+define double @mult() #0 {
+entry:
+  %x = alloca double, align 8
+  %y = alloca double, align 8
+  store double 3.141590e+00, double* %x, align 8
+  store double 1.234560e+00, double* %y, align 8
+  %0 = load double, double* %x, align 8
+  %1 = load double, double* %y, align 8
+  %mul = fmul double %0, %1
+  ret double %mul
+}

llvm/trunk/test/CodeGen/SPARC/LeonPreventRoundChangePassUT.ll

+; RUN: llc %s -O0 -march=sparc -mcpu=ut699 -o - | FileCheck %s -check-prefix=NO_ROUND_FUNC
+; RUN: llc %s -O0 -march=sparc -mcpu=leon3 -mattr=+prvntroundchange -o - | FileCheck %s -check-prefix=NO_ROUND_FUNC
+
+; RUN: llc %s -O0 -march=sparc -mcpu=ut699 -mattr=-prvntroundchange -o - | FileCheck %s -check-prefix=ROUND_FUNC
+; RUN: llc %s -O0 -march=sparc -mcpu=leon3  -o - | FileCheck %s -check-prefix=ROUND_FUNC
+
+
+; NO_ROUND_FUNC-LABEL: test_round_change
+; NO_ROUND_FUNC-NOT: fesetround
+
+; ROUND_FUNC-LABEL: test_round_change
+; ROUND_FUNC: fesetround
+
+; ModuleID = '<stdin>'
+target datalayout = "E-m:e-p:32:32-i64:64-f128:64-n32-S64"
+target triple = "sparc-unknown--eabi"
+
+@.str = private unnamed_addr constant [17 x i8] c"-((-a)*b) != a*b\00", align 1
+@.str.1 = private unnamed_addr constant [7 x i8] c"test.c\00", align 1
+@__PRETTY_FUNCTION__.mult = private unnamed_addr constant [12 x i8] c"void mult()\00", align 1
+
+; Function Attrs: nounwind
+define void @test_round_change() #0 {
+entry:
+  %a = alloca double, align 8
+  %b = alloca double, align 8
+  %x = alloca float, align 4
+  store double 1.100000e+00, double* %a, align 8
+  store double 1.010000e+01, double* %b, align 8
+  store float 0x400921FA00000000, float* %x, align 4
+  %call = call i32 @fesetround(i32 2048) #2
+  %0 = load double, double* %a, align 8
+  %sub = fsub double -0.000000e+00, %0
+  %1 = load double, double* %b, align 8
+  %mul = fmul double %sub, %1
+  %sub1 = fsub double -0.000000e+00, %mul
+  %2 = load double, double* %a, align 8
+  %3 = load double, double* %b, align 8
+  %mul2 = fmul double %2, %3
+  %cmp = fcmp une double %sub1, %mul2
+  br i1 %cmp, label %cond.true, label %cond.false
+
+cond.true:                                        ; preds = %entry
+  br label %cond.end
+
+cond.false:                                       ; preds = %entry
+  call void @__assert_fail(i8* getelementptr inbounds ([17 x i8], [17 x i8]* @.str, i32 0, i32 0), i8* getelementptr inbounds ([7 x i8], [7 x i8]* @.str.1, i32 0, i32 0), i32 10, i8* getelementptr inbounds ([12 x i8], [12 x i8]* @__PRETTY_FUNCTION__.mult, i32 0, i32 0)) #3
+  unreachable
+                                                  ; No predecessors!
+  br label %cond.end
+
+cond.end:                                         ; preds = %4, %cond.true
+  ret void
+}
+
+; Function Attrs: nounwind
+declare i32 @fesetround(i32) #0
+
+; Function Attrs: noreturn nounwind
+declare void @__assert_fail(i8*, i8*, i32, i8*) #1
+
+attributes #0 = { nounwind "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { noreturn nounwind "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #2 = { nounwind }
+attributes #3 = { noreturn nounwind }
 No newline at end of file

llvm/trunk/test/CodeGen/SPARC/LeonReplaceSDIVPassUT.ll

+; RUN: llc %s -O0 -march=sparc -mcpu=at697e -o - | FileCheck %s
+
+; CHECK: sdivcc %o0, %o1, %o0
+
+define i32 @lbr59(i32 %a, i32 %b)
+{
+  %r = sdiv i32 %a, %b
+  ret i32 %r 
+}