implement rdar://6653118 - fastisel should fold loads where possible.

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

diff --git a/lib/Target/README.txt b/lib/Target/README.txt
index b1080b594ff1cd100e1219f23c44f490208cd4d9..4faf8bcfd419982b438c73c5758e88e8f6840cce 100644 (file)
--- a/lib/Target/README.txt
+++ b/lib/Target/README.txt
@@ -906,17 +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)
@@ -1888,3 +1877,63 @@ 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
+//===---------------------------------------------------------------------===//
+Given a branch where the two target blocks are identical ("ret i32 %b" in
+both), simplifycfg will simplify them away. But not so for a switch statement:
+
+define i32 @f(i32 %a, i32 %b) nounwind readnone {
+entry:
+        switch i32 %a, label %bb3 [
+                i32 4, label %bb
+                i32 6, label %bb
+        ]
+
+bb:             ; preds = %entry, %entry
+        ret i32 %b
+
+bb3:            ; preds = %entry
+        ret i32 %b
+}
+//===---------------------------------------------------------------------===//