[X86] Disable f32->f64 extload when sse2 is enabled

Summary:
We can only use the memory form of cvtss2sd under optsize due to a partial register update. So previously we were emitting 2 instructions for extload when optimizing for speed. Also due to a late optimization in preprocessiseldag we had to handle (fpextend (loadf32)) under optsize.

This patch forces extload to expand so that it will always be in the (fpextend (loadf32)) form during isel. And when optimizing for speed we can just let each of those pieces select an instruction independently.

Reviewers: spatel, RKSimon

Reviewed By: RKSimon

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D62710

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@362919 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 2bed6c85bec5ac21c6046f5889af1ec7c856c5a5..c4db6932fa8643bb201678ab9b61fafbdf94ec45 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -534,6 +534,12 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
     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);

diff --git a/lib/Target/X86/X86InstrAVX512.td b/lib/Target/X86/X86InstrAVX512.td
index fbadd80b242687d91f5af627947e9c6bd2b3af63..f428b201adca8de837c3e2add806ee6f432a54d2 100644 (file)
--- a/lib/Target/X86/X86InstrAVX512.td
+++ b/lib/Target/X86/X86InstrAVX512.td
@@ -7521,14 +7521,6 @@ def : Pat<(f64 (fpextend (loadf32 addr:$src))),
           (VCVTSS2SDZrm (f64 (IMPLICIT_DEF)), addr:$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]>;

diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index ade5645d5bf1d4e19e916216cc3d57897d6bd67a..65849373e91e5b24f2ede802e51d52770948814f 100644 (file)
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -1251,13 +1251,6 @@ def : Pat<(f64 (fpextend FR32:$src)),
 def : Pat<(fpextend (loadf32 addr:$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, $src}",
@@ -1265,21 +1258,11 @@ def CVTSS2SDrr : I<0x5A, MRMSrcReg, (outs FR64:$dst), (ins FR32:$src),
                    XS, Requires<[UseSSE2]>, Sched<[WriteCvtSS2SD]>;
 def CVTSS2SDrm : I<0x5A, MRMSrcMem, (outs FR64:$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),