Increase efficiency of sign_extend_inreg by using subregisters for truncation. As...

[oota-llvm.git] / lib / Target / X86 / README.txt

diff --git a/lib/Target/X86/README.txt b/lib/Target/X86/README.txt
index d70e90a3ca11fd3b128dfc851d7562d87f5b0398..073e2dacef183b26bab7ac32332d4a19f2702471 100644 (file)
--- a/lib/Target/X86/README.txt
+++ b/lib/Target/X86/README.txt
@@ -402,9 +402,7 @@ L4:
 There are 3 issues:
 
 1. Lack of post regalloc LICM.
-2. Poor sub-regclass support. That leads to inability to promote the 16-bit
-   arithmetic op to 32-bit and making use of leal.
-3. LSR unable to reused IV for a different type (i16 vs. i32) even though
+2. LSR unable to reused IV for a different type (i16 vs. i32) even though
    the cast would be free.
 
 //===---------------------------------------------------------------------===//
@@ -475,21 +473,6 @@ require a copy to be inserted (in X86InstrInfo::convertToThreeAddress).
 
 //===---------------------------------------------------------------------===//
 
-Bad codegen:
-
-char foo(int x) { return x; }
-
-_foo:
-       movl 4(%esp), %eax
-       shll $24, %eax
-       sarl $24, %eax
-       ret
-
-SIGN_EXTEND_INREG can be implemented as (sext (trunc)) to take advantage of 
-sub-registers.
-
-//===---------------------------------------------------------------------===//
-
 Consider this:
 
 typedef struct pair { float A, B; } pair;
@@ -1103,3 +1086,30 @@ These instructions should go away:
 movaps %xmm1, 192(%esp) 
 movaps %xmm1, 224(%esp) 
 movaps %xmm1, 176(%esp)
+
+//===---------------------------------------------------------------------===//
+
+This is a "commutable two-address" register coallescing deficiency:
+
+define <4 x float> @test1(<4 x float> %V) {
+entry:
+        %tmp8 = shufflevector <4 x float> %V, <4 x float> undef, <4 x i32> < i32 3, i32 2, i32 1, i32 0 >               ; <<4 x float>> [#uses=1]
+        %add = add <4 x float> %tmp8, %V                ; <<4 x float>> [#uses=1]
+        ret <4 x float> %add
+}
+
+this codegens to:
+
+_test1:
+        pshufd  $27, %xmm0, %xmm1
+        addps   %xmm0, %xmm1
+        movaps  %xmm1, %xmm0
+        ret
+
+instead of:
+
+_test1:
+        pshufd  $27, %xmm0, %xmm1
+        addps   %xmm1, %xmm0
+        ret
+