Pacify gcc-4.5 which wrongly thinks that RExcess (passed as the Excess parameter)

[oota-llvm.git] / lib / Target / README.txt

diff --git a/lib/Target/README.txt b/lib/Target/README.txt
index efb91a1b2839db35a5103c57fe2dcc064715a985..4d7ee08de1dee3dfc93d4d3e95acfa47bd434f1f 100644 (file)
--- a/lib/Target/README.txt
+++ b/lib/Target/README.txt
@@ -300,6 +300,14 @@ unsigned long reverse(unsigned v) {
     return v ^ (t >> 8);
 }
 
+Neither is this (very standard idiom):
+
+int f(int n)
+{
+  return (((n) << 24) | (((n) & 0xff00) << 8) 
+       | (((n) >> 8) & 0xff00) | ((n) >> 24));
+}
+
 //===---------------------------------------------------------------------===//
 
 [LOOP RECOGNITION]
@@ -898,17 +906,6 @@ The expression should optimize to something like
 
 //===---------------------------------------------------------------------===//
 
-From GCC Bug 3756:
-int
-pn (int n)
-{
- return (n >= 0 ? 1 : -1);
-}
-Should combine to (n >> 31) | 1.  Currently not optimized with "clang
--emit-llvm-bc | opt -std-compile-opts | llc".
-
-//===---------------------------------------------------------------------===//
-
 void a(int variable)
 {
  if (variable == 4 || variable == 6)
@@ -1880,3 +1877,47 @@ of the ADD, and replacing the ADD with the ADDE, should give the desired result.
 (That said, we are doing a lot better than gcc on this testcase. :) )
 
 //===---------------------------------------------------------------------===//
+
+Switch lowering generates less than ideal code for the following switch:
+define void @a(i32 %x) nounwind {
+entry:
+  switch i32 %x, label %if.end [
+    i32 0, label %if.then
+    i32 1, label %if.then
+    i32 2, label %if.then
+    i32 3, label %if.then
+    i32 5, label %if.then
+  ]
+if.then:
+  tail call void @foo() nounwind
+  ret void
+if.end:
+  ret void
+}
+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
+.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
+something like the following, which eliminates a branch:
+       xorl    $1, %edi
+       cmpl    $4, %edi
+       ja      .LBB0_2
+       ret
+.LBB0_2:
+       jmp     foo  # TAILCALL
+
+//===---------------------------------------------------------------------===//