[llvm-commits] [llvm] r107613 - /llvm/trunk/lib/Target/X86/README-SSE.txt

[Chris Lattner]

Author: lattner
Date: Mon Jul  5 00:48:41 2010
New Revision: 107613

URL: http://llvm.org/viewvc/llvm-project?rev=107613&view=rev
Log:
some notes about suboptimal insertps's

Modified:
    llvm/trunk/lib/Target/X86/README-SSE.txt

Modified: llvm/trunk/lib/Target/X86/README-SSE.txt
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/README-SSE.txt?rev=107613&r1=107612&r2=107613&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/README-SSE.txt (original)
+++ llvm/trunk/lib/Target/X86/README-SSE.txt Mon Jul  5 00:48:41 2010
@@ -846,3 +846,34 @@
 doing a shuffle from v[1] to v[0] then a float store.
 
 //===---------------------------------------------------------------------===//
+
+On SSE4 machines, we compile this code:
+
+define <2 x float> @test2(<2 x float> %Q, <2 x float> %R,
+       <2 x float> *%P) nounwind {
+  %Z = fadd <2 x float> %Q, %R
+
+  store <2 x float> %Z, <2 x float> *%P
+  ret <2 x float> %Z
+}
+
+into:
+
+_test2:                                 ## @test2
+## BB#0:
+	insertps	$0, %xmm2, %xmm2
+	insertps	$16, %xmm3, %xmm2
+	insertps	$0, %xmm0, %xmm3
+	insertps	$16, %xmm1, %xmm3
+	addps	%xmm2, %xmm3
+	movq	%xmm3, (%rdi)
+	movaps	%xmm3, %xmm0
+	pshufd	$1, %xmm3, %xmm1
+                                        ## kill: XMM1<def> XMM1<kill>
+	ret
+
+The insertps's of $0 are pointless complex copies.
+
+//===---------------------------------------------------------------------===//
+
+