Implement a readme entry, compiling

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

diff --git a/lib/Target/X86/README-SSE.txt b/lib/Target/X86/README-SSE.txt
index 1f29e0a1bebbb858b49f694a407a7c3bcc0e8481..4ec5a5ac4b90ea3a7f4eb937e38a0d3be94c9fa4 100644 (file)
--- a/lib/Target/X86/README-SSE.txt
+++ b/lib/Target/X86/README-SSE.txt
@@ -782,23 +782,3 @@ just a matter of matching (scalar_to_vector (load x)) to movd.
 
 //===---------------------------------------------------------------------===//
 
-Take the following code:
-#include <xmmintrin.h>
-__m128i doload64(short x) {return _mm_set_epi16(0,0,0,0,0,0,0,1);}
-
-On x86, LLVM generates the following:
-doload64:
-        subl    $28, %esp
-        movl    $0, 4(%esp)
-        movl    $1, (%esp)
-        movq    (%esp), %xmm0
-        addl    $28, %esp
-        ret
-
-LLVM should instead generate something more like the following:
-doload64:
-        movl    $1, %eax
-        movd    %eax, %xmm0
-        ret
-
-//===---------------------------------------------------------------------===//