These are done.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@31649 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/README-SSE.txt b/lib/Target/X86/README-SSE.txt
index 2de68edad003f462366be53b601027918c33c173..5c7722da535245efd9a5da073478408143d7e8c1 100644 (file)
--- a/lib/Target/X86/README-SSE.txt
+++ b/lib/Target/X86/README-SSE.txt
@@ -4,30 +4,6 @@
 
 //===---------------------------------------------------------------------===//
 
-There are serious issues folding loads into "scalar sse" intrinsics.  For
-example, this:
-
-float minss4( float x, float *y ) { 
-  return _mm_cvtss_f32(_mm_min_ss(_mm_set_ss(x),_mm_set_ss(*y)));
-}
-
-compiles to:
-
-_minss4:
-        subl $4, %esp
-        movl 12(%esp), %eax
-***     movss 8(%esp), %xmm0
-***     movss (%eax), %xmm1
-***     minss %xmm1, %xmm0
-        movss %xmm0, (%esp)
-        flds (%esp)
-        addl $4, %esp
-        ret
-
-Each operand of the minss is a load.  At least one should be folded!
-
-//===---------------------------------------------------------------------===//
-
 Expand libm rounding functions inline:  Significant speedups possible.
 http://gcc.gnu.org/ml/gcc-patches/2006-10/msg00909.html
 
@@ -165,17 +141,6 @@ This will be solved when we go to a dynamic programming based isel.
 
 //===---------------------------------------------------------------------===//
 
-Should generate min/max for stuff like:
-
-void minf(float a, float b, float *X) {
-  *X = a <= b ? a : b;
-}
-
-Make use of floating point min / max instructions. Perhaps introduce ISD::FMIN
-and ISD::FMAX node types?
-
-//===---------------------------------------------------------------------===//
-
 Lower memcpy / memset to a series of SSE 128 bit move instructions when it's
 feasible.
 
@@ -225,29 +190,6 @@ Perhaps use pxor / xorp* to clear a XMM register first?
 
 //===---------------------------------------------------------------------===//
 
-Better codegen for:
-
-void f(float a, float b, vector float * out) { *out = (vector float){ a, 0.0, 0.0, b}; }
-void f(float a, float b, vector float * out) { *out = (vector float){ a, b, 0.0, 0}; }
-
-For the later we generate:
-
-_f:
-        pxor %xmm0, %xmm0
-        movss 8(%esp), %xmm1
-        movaps %xmm0, %xmm2
-        unpcklps %xmm1, %xmm2
-        movss 4(%esp), %xmm1
-        unpcklps %xmm0, %xmm1
-        unpcklps %xmm2, %xmm1
-        movl 12(%esp), %eax
-        movaps %xmm1, (%eax)
-        ret
-
-This seems like it should use shufps, one for each of a & b.
-
-//===---------------------------------------------------------------------===//
-
 How to decide when to use the "floating point version" of logical ops? Here are
 some code fragments:
 

diff --git a/lib/Target/X86/README.txt b/lib/Target/X86/README.txt
index 956caff0c4e05a4b679e2dacfbb5e6e877972dec..834a47c51b9d350fb79013836234d80b3e092bcb 100644 (file)
--- a/lib/Target/X86/README.txt
+++ b/lib/Target/X86/README.txt
@@ -232,17 +232,6 @@ which is probably slower, but it's interesting at least :)
 
 //===---------------------------------------------------------------------===//
 
-Should generate min/max for stuff like:
-
-void minf(float a, float b, float *X) {
-  *X = a <= b ? a : b;
-}
-
-Make use of floating point min / max instructions. Perhaps introduce ISD::FMIN
-and ISD::FMAX node types?
-
-//===---------------------------------------------------------------------===//
-
 The first BB of this code:
 
 declare bool %foo()