Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
@@ -534,6 +534,12 @@
     addRegisterClass(MVT::f64, Subtarget.hasAVX512() ? &X86::FR64XRegClass
                                                      : &X86::FR64RegClass);
 
+    // Disable f32->f64 extload as we can only generate this in one instruction
+    // under optsize. So its easier to pattern match (fpext (load)) for that
+    // case instead of needing to emit 2 instructions for extload in the
+    // non-optsize case.
+    setLoadExtAction(ISD::EXTLOAD, MVT::f64, MVT::f32, Expand);
+
     for (auto VT : { MVT::f32, MVT::f64 }) {
       // Use ANDPD to simulate FABS.
       setOperationAction(ISD::FABS, VT, Custom);
Index: llvm/trunk/lib/Target/X86/X86InstrAVX512.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86InstrAVX512.td
+++ llvm/trunk/lib/Target/X86/X86InstrAVX512.td
@@ -7521,14 +7521,6 @@
           (VCVTSS2SDZrm (f64 (IMPLICIT_DEF)), addr:$src)>,
           Requires<[HasAVX512, OptForSize]>;
 
-def : Pat<(f64 (extloadf32 addr:$src)),
-          (VCVTSS2SDZrm (f64 (IMPLICIT_DEF)), addr:$src)>,
-      Requires<[HasAVX512, OptForSize]>;
-
-def : Pat<(f64 (extloadf32 addr:$src)),
-          (VCVTSS2SDZrr (f64 (IMPLICIT_DEF)), (VMOVSSZrm addr:$src))>,
-          Requires<[HasAVX512, OptForSpeed]>;
-
 def : Pat<(f32 (fpround FR64X:$src)),
           (VCVTSD2SSZrr (f32 (IMPLICIT_DEF)), FR64X:$src)>,
            Requires<[HasAVX512]>;
Index: llvm/trunk/lib/Target/X86/X86InstrSSE.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86InstrSSE.td
+++ llvm/trunk/lib/Target/X86/X86InstrSSE.td
@@ -1251,13 +1251,6 @@
 def : Pat<(fpextend (loadf32 addr:$src)),
     (VCVTSS2SDrm (f64 (IMPLICIT_DEF)), addr:$src)>, Requires<[UseAVX, OptForSize]>;
 
-def : Pat<(extloadf32 addr:$src),
-    (VCVTSS2SDrm (f64 (IMPLICIT_DEF)), addr:$src)>,
-    Requires<[UseAVX, OptForSize]>;
-def : Pat<(extloadf32 addr:$src),
-    (VCVTSS2SDrr (f64 (IMPLICIT_DEF)), (VMOVSSrm addr:$src))>,
-    Requires<[UseAVX, OptForSpeed]>;
-
 let isCodeGenOnly = 1 in {
 def CVTSS2SDrr : I<0x5A, MRMSrcReg, (outs FR64:$dst), (ins FR32:$src),
                    "cvtss2sd\t{$src, $dst|$dst, $src}",
@@ -1265,21 +1258,11 @@
                    XS, Requires<[UseSSE2]>, Sched<[WriteCvtSS2SD]>;
 def CVTSS2SDrm : I<0x5A, MRMSrcMem, (outs FR64:$dst), (ins f32mem:$src),
                    "cvtss2sd\t{$src, $dst|$dst, $src}",
-                   [(set FR64:$dst, (extloadf32 addr:$src))]>,
+                   [(set FR64:$dst, (fpextend (loadf32 addr:$src)))]>,
                    XS, Requires<[UseSSE2, OptForSize]>,
                    Sched<[WriteCvtSS2SD.Folded]>;
 } // isCodeGenOnly = 1
 
-// extload f32 -> f64.  This matches load+fpextend because we have a hack in
-// the isel (PreprocessForFPConvert) that can introduce loads after dag
-// combine.
-// Since these loads aren't folded into the fpextend, we have to match it
-// explicitly here.
-def : Pat<(fpextend (loadf32 addr:$src)),
-          (CVTSS2SDrm addr:$src)>, Requires<[UseSSE2, OptForSize]>;
-def : Pat<(extloadf32 addr:$src),
-          (CVTSS2SDrr (MOVSSrm addr:$src))>, Requires<[UseSSE2, OptForSpeed]>;
-
 let hasSideEffects = 0 in {
 def VCVTSS2SDrr_Int: I<0x5A, MRMSrcReg,
                       (outs VR128:$dst), (ins VR128:$src1, VR128:$src2),