X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTarget%2FREADME.txt;h=1f69ffb09c0a4a04298f9e84b91acd2b3c06b1ec;hb=689b86ed2e1f1daf9201f0ef83ff3bc1d5167232;hp=0105ae4562a988851d267582c11a459fc17b6aa7;hpb=b6fcf4cfbc075fd20f496d992180d177f4f4d721;p=oota-llvm.git

diff --git a/lib/Target/README.txt b/lib/Target/README.txt
index 0105ae4562a..1f69ffb09c0 100644
--- a/lib/Target/README.txt
+++ b/lib/Target/README.txt
@@ -870,11 +870,6 @@ rshift_gt (unsigned int a)
    bar ();
 }
 
-void neg_eq_cst(unsigned int a) {
-if (-a == 123)
-bar();
-}
-
 All should simplify to a single comparison.  All of these are
 currently not optimized with "clang -emit-llvm-bc | opt
 -std-compile-opts".
@@ -1767,7 +1762,6 @@ case it choses instead to keep the max operation obvious.
 
 //===---------------------------------------------------------------------===//
 
-Switch lowering generates less than ideal code for the following switch:
 define void @a(i32 %x) nounwind {
 entry:
   switch i32 %x, label %if.end [
@@ -1788,19 +1782,15 @@ declare void @foo()
 Generated code on x86-64 (other platforms give similar results):
 a:
 	cmpl	$5, %edi
-	ja	.LBB0_2
-	movl	%edi, %eax
-	movl	$47, %ecx
-	btq	%rax, %rcx
-	jb	.LBB0_3
+	ja	LBB2_2
+	cmpl	$4, %edi
+	jne	LBB2_3
 .LBB0_2:
 	ret
 .LBB0_3:
 	jmp	foo  # TAILCALL
 
-The movl+movl+btq+jb could be simplified to a cmpl+jne.
-
-Or, if we wanted to be really clever, we could simplify the whole thing to
+If we wanted to be really clever, we could simplify the whole thing to
 something like the following, which eliminates a branch:
 	xorl    $1, %edi
 	cmpl	$4, %edi
@@ -2346,3 +2336,25 @@ Note that bb1 and bb2 are the same.  This doesn't happen at the IR level
 because one call is passing an i32 and the other is passing an i64.
 
 //===---------------------------------------------------------------------===//
+
+I see this sort of pattern in 176.gcc in a few places (e.g. the start of
+store_bit_field).  The rem should be replaced with a multiply and subtract:
+
+  %3 = sdiv i32 %A, %B
+  %4 = srem i32 %A, %B
+
+Similarly for udiv/urem.  Note that this shouldn't be done on X86 or ARM,
+which can do this in a single operation (instruction or libcall).  It is
+probably best to do this in the code generator.
+
+//===---------------------------------------------------------------------===//
+
+unsigned foo(unsigned x, unsigned y) { return (x & y) == 0 || x == 0; }
+should fold to (x & y) == 0.
+
+//===---------------------------------------------------------------------===//
+
+unsigned foo(unsigned x, unsigned y) { return x > y && x != 0; }
+should fold to x > y.
+
+//===---------------------------------------------------------------------===//