[asan] Skip promotable allocas to improve performance at -O0
Currently, the ASan executables built with -O0 are unnecessarily slow.
The main reason is that ASan instrumentation pass inserts redundant
checks around promotable allocas. These allocas do not get instrumented
under -O1 because they get converted to virtual registered by mem2reg.
With this patch, ASan instrumentation pass will only instrument non
promotable allocas, giving us a speedup of 39% on a collection of
benchmarks with -O0. (There is no measurable speedup at -O1.)
llvm-svn: 230724
diff --git a/llvm/test/Instrumentation/AddressSanitizer/stack_layout.ll b/llvm/test/Instrumentation/AddressSanitizer/stack_layout.ll
index 97e3bbb..6575dd6 100644
--- a/llvm/test/Instrumentation/AddressSanitizer/stack_layout.ll
+++ b/llvm/test/Instrumentation/AddressSanitizer/stack_layout.ll
@@ -26,6 +26,12 @@
%XXX = alloca [10 x i8], align 1
%YYY = alloca [20 x i8], align 1
%ZZZ = alloca [30 x i8], align 1
+ %arr1.ptr = bitcast [10 x i8]* %XXX to i8*
+ store volatile i8 0, i8* %arr1.ptr
+ %arr2.ptr = bitcast [20 x i8]* %YYY to i8*
+ store volatile i8 0, i8* %arr2.ptr
+ %arr3.ptr = bitcast [30 x i8]* %ZZZ to i8*
+ store volatile i8 0, i8* %arr3.ptr
ret void
}
@@ -41,6 +47,12 @@
%AAA = alloca [5 x i8], align 1
%BBB = alloca [55 x i8], align 1
%CCC = alloca [555 x i8], align 1
+ %arr1.ptr = bitcast [5 x i8]* %AAA to i8*
+ store volatile i8 0, i8* %arr1.ptr
+ %arr2.ptr = bitcast [55 x i8]* %BBB to i8*
+ store volatile i8 0, i8* %arr2.ptr
+ %arr3.ptr = bitcast [555 x i8]* %CCC to i8*
+ store volatile i8 0, i8* %arr3.ptr
ret void
}
@@ -57,5 +69,11 @@
%AAA = alloca [128 x i8], align 16
%BBB = alloca [128 x i8], align 64
%CCC = alloca [128 x i8], align 256
+ %arr1.ptr = bitcast [128 x i8]* %AAA to i8*
+ store volatile i8 0, i8* %arr1.ptr
+ %arr2.ptr = bitcast [128 x i8]* %BBB to i8*
+ store volatile i8 0, i8* %arr2.ptr
+ %arr3.ptr = bitcast [128 x i8]* %CCC to i8*
+ store volatile i8 0, i8* %arr3.ptr
ret void
}