[llvm-commits] [llvm] r123414 - in /llvm/trunk: lib/Target/X86/X86FastISel.cpp test/CodeGen/X86/fast-isel-gep.ll
Chris Lattner
sabre at nondot.org
Thu Jan 13 16:01:01 PST 2011
Author: lattner
Date: Thu Jan 13 18:01:01 2011
New Revision: 123414
URL: http://llvm.org/viewvc/llvm-project?rev=123414&view=rev
Log:
fix PR8961 - a fast isel miscompilation where we'd insert a new instruction
after sext's generated for addressing that got folded. Previously we compiled
test5 into:
_test5: ## @test5
## BB#0:
movq -8(%rsp), %rax ## 8-byte Reload
movq (%rdi,%rax), %rdi
addq %rdx, %rdi
movslq %esi, %rax
movq %rax, -8(%rsp) ## 8-byte Spill
movq %rdi, %rax
ret
which is insane and wrong. Now we produce:
_test5: ## @test5
## BB#0:
movslq %esi, %rax
movq (%rdi,%rax), %rax
addq %rdx, %rax
ret
Modified:
llvm/trunk/lib/Target/X86/X86FastISel.cpp
llvm/trunk/test/CodeGen/X86/fast-isel-gep.ll
Modified: llvm/trunk/lib/Target/X86/X86FastISel.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86FastISel.cpp?rev=123414&r1=123413&r2=123414&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86FastISel.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86FastISel.cpp Thu Jan 13 18:01:01 2011
@@ -1933,7 +1933,7 @@
XII.foldMemoryOperandImpl(*FuncInfo.MF, MI, OpNo, AddrOps, Size, Alignment);
if (Result == 0) return false;
- MI->getParent()->insert(MI, Result);
+ FuncInfo.MBB->insert(FuncInfo.InsertPt, Result);
MI->eraseFromParent();
return true;
}
Modified: llvm/trunk/test/CodeGen/X86/fast-isel-gep.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/fast-isel-gep.ll?rev=123414&r1=123413&r2=123414&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/fast-isel-gep.ll (original)
+++ llvm/trunk/test/CodeGen/X86/fast-isel-gep.ll Thu Jan 13 18:01:01 2011
@@ -70,3 +70,20 @@
; X64: test4:
; X64: 128(%r{{.*}},%r{{.*}},8)
}
+
+; PR8961 - Make sure the sext for the GEP addressing comes before the load that
+; is folded.
+define i64 @test5(i8* %A, i32 %I, i64 %B) nounwind {
+ %v8 = getelementptr i8* %A, i32 %I
+ %v9 = bitcast i8* %v8 to i64*
+ %v10 = load i64* %v9
+ %v11 = add i64 %B, %v10
+ ret i64 %v11
+; X64: test5:
+; X64: movslq %esi, %rax
+; X64-NEXT: movq (%rdi,%rax), %rax
+; X64-NEXT: addq %rdx, %rax
+; X64-NEXT: ret
+}
+
+
More information about the llvm-commits
mailing list