One more for 3.2. :)<div class="gmail_extra"><br><br><div class="gmail_quote">On Fri, Nov 16, 2012 at 4:03 PM, Justin Holewinski <span dir="ltr"><<a href="mailto:jholewinski@nvidia.com" target="_blank">jholewinski@nvidia.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Author: jholewinski<br>
Date: Fri Nov 16 15:03:51 2012<br>
New Revision: 168198<br>
<br>
URL: <a href="http://llvm.org/viewvc/llvm-project?rev=168198&view=rev" target="_blank">http://llvm.org/viewvc/llvm-project?rev=168198&view=rev</a><br>
Log:<br>
[NVPTX] Order global variables in def-use order before emiting them in the final assembly<br>
<br>
Added:<br>
llvm/trunk/test/CodeGen/NVPTX/global-ordering.ll<br>
Modified:<br>
llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp<br>
<br>
Modified: llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp<br>
URL: <a href="http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp?rev=168198&r1=168197&r2=168198&view=diff" target="_blank">http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp?rev=168198&r1=168197&r2=168198&view=diff</a><br>
==============================================================================<br>
--- llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp (original)<br>
+++ llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp Fri Nov 16 15:03:51 2012<br>
@@ -68,7 +68,54 @@<br>
cl::location(llvm::InterleaveSrcInPtx));<br>
<br>
<br>
+namespace {<br>
+/// DiscoverDependentGlobals - Return a set of GlobalVariables on which \p V<br>
+/// depends.<br>
+void DiscoverDependentGlobals(Value *V,<br>
+ DenseSet<GlobalVariable*> &Globals) {<br>
+ if (GlobalVariable *GV = dyn_cast<GlobalVariable>(V))<br>
+ Globals.insert(GV);<br>
+ else {<br>
+ if (User *U = dyn_cast<User>(V)) {<br>
+ for (unsigned i = 0, e = U->getNumOperands(); i != e; ++i) {<br>
+ DiscoverDependentGlobals(U->getOperand(i), Globals);<br>
+ }<br>
+ }<br>
+ }<br>
+}<br>
<br>
+/// VisitGlobalVariableForEmission - Add \p GV to the list of GlobalVariable<br>
+/// instances to be emitted, but only after any dependents have been added<br>
+/// first.<br>
+void VisitGlobalVariableForEmission(GlobalVariable *GV,<br>
+ SmallVectorImpl<GlobalVariable*> &Order,<br>
+ DenseSet<GlobalVariable*> &Visited,<br>
+ DenseSet<GlobalVariable*> &Visiting) {<br>
+ // Have we already visited this one?<br>
+ if (Visited.count(GV)) return;<br>
+<br>
+ // Do we have a circular dependency?<br>
+ if (Visiting.count(GV))<br>
+ report_fatal_error("Circular dependency found in global variable set");<br>
+<br>
+ // Start visiting this global<br>
+ Visiting.insert(GV);<br>
+<br>
+ // Make sure we visit all dependents first<br>
+ DenseSet<GlobalVariable*> Others;<br>
+ for (unsigned i = 0, e = GV->getNumOperands(); i != e; ++i)<br>
+ DiscoverDependentGlobals(GV->getOperand(i), Others);<br>
+<br>
+ for (DenseSet<GlobalVariable*>::iterator I = Others.begin(),<br>
+ E = Others.end(); I != E; ++I)<br>
+ VisitGlobalVariableForEmission(*I, Order, Visited, Visiting);<br>
+<br>
+ // Now we can visit ourself<br>
+ Order.push_back(GV);<br>
+ Visited.insert(GV);<br>
+ Visiting.erase(GV);<br>
+}<br>
+}<br>
<br>
// @TODO: This is a copy from AsmPrinter.cpp. The function is static, so we<br>
// cannot just link to the existing version.<br>
@@ -893,10 +940,27 @@<br>
<br>
emitDeclarations(M, OS2);<br>
<br>
- // Print out module-level global variables here.<br>
+ // As ptxas does not support forward references of globals, we need to first<br>
+ // sort the list of module-level globals in def-use order. We visit each<br>
+ // global variable in order, and ensure that we emit it *after* its dependent<br>
+ // globals. We use a little extra memory maintaining both a set and a list to<br>
+ // have fast searches while maintaining a strict ordering.<br>
+ SmallVector<GlobalVariable*,8> Globals;<br>
+ DenseSet<GlobalVariable*> GVVisited;<br>
+ DenseSet<GlobalVariable*> GVVisiting;<br>
+<br>
+ // Visit each global variable, in order<br>
for (Module::global_iterator I = M.global_begin(), E = M.global_end();<br>
- I != E; ++I)<br>
- printModuleLevelGV(I, OS2);<br>
+ I != E; ++I)<br>
+ VisitGlobalVariableForEmission(I, Globals, GVVisited, GVVisiting);<br>
+<br>
+ assert(GVVisited.size() == M.getGlobalList().size() &&<br>
+ "Missed a global variable");<br>
+ assert(GVVisiting.size() == 0 && "Did not fully process a global variable");<br>
+<br>
+ // Print out module-level global variables in proper order<br>
+ for (unsigned i = 0, e = Globals.size(); i != e; ++i)<br>
+ printModuleLevelGV(Globals[i], OS2);<br>
<br>
OS2 << '\n';<br>
<br>
<br>
Added: llvm/trunk/test/CodeGen/NVPTX/global-ordering.ll<br>
URL: <a href="http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/NVPTX/global-ordering.ll?rev=168198&view=auto" target="_blank">http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/NVPTX/global-ordering.ll?rev=168198&view=auto</a><br>
==============================================================================<br>
--- llvm/trunk/test/CodeGen/NVPTX/global-ordering.ll (added)<br>
+++ llvm/trunk/test/CodeGen/NVPTX/global-ordering.ll Fri Nov 16 15:03:51 2012<br>
@@ -0,0 +1,20 @@<br>
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=PTX32<br>
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s --check-prefix=PTX64<br>
+<br>
+; Make sure we emit these globals in def-use order<br>
+<br>
+<br>
+; PTX32: .visible .global .align 1 .u8 a = 2;<br>
+; PTX32-NEXT: .visible .global .align 4 .u32 a2 = a;<br>
+; PTX64: .visible .global .align 1 .u8 a = 2;<br>
+; PTX64-NEXT: .visible .global .align 8 .u64 a2 = a;<br>
+@a2 = addrspace(1) global i8 addrspace(1)* @a<br>
+@a = addrspace(1) global i8 2<br>
+<br>
+<br>
+; PTX32: .visible .global .align 1 .u8 b = 1;<br>
+; PTX32-NEXT: .visible .global .align 4 .u32 b2[2] = {b, b};<br>
+; PTX64: .visible .global .align 1 .u8 b = 1;<br>
+; PTX64-NEXT: .visible .global .align 8 .u64 b2[2] = {b, b};<br>
+@b2 = addrspace(1) global [2 x i8 addrspace(1)*] [i8 addrspace(1)* @b, i8 addrspace(1)* @b]<br>
+@b = addrspace(1) global i8 1<br>
<br>
<br>
_______________________________________________<br>
llvm-commits mailing list<br>
<a href="mailto:llvm-commits@cs.uiuc.edu">llvm-commits@cs.uiuc.edu</a><br>
<a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits" target="_blank">http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits</a><br>
</blockquote></div><br><br clear="all"><div><br></div>-- <br><br><div>Thanks,</div><div><br></div><div>Justin Holewinski</div><br>
</div>