summary | shortlog | log | commit | commitdiff | tree
raw | patch | inline | side by side (parent: 3e61ccd)
raw | patch | inline | side by side (parent: 3e61ccd)
author | Tim Northover <tnorthover@apple.com> | |
Thu, 17 Jul 2014 11:04:04 +0000 (11:04 +0000) | ||
committer | Tim Northover <tnorthover@apple.com> | |
Thu, 17 Jul 2014 11:04:04 +0000 (11:04 +0000) |
x86 has no native ability to extend an f16 to f64, but the same result
is obtained if we expand it into two separate extensions: f16 -> f32
-> f64.
Unfortunately the same is not true for truncate, so that still results
in a compilation failure.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213251 91177308-0d34-0410-b5e6-96231b3b80d8
is obtained if we expand it into two separate extensions: f16 -> f32
-> f64.
Unfortunately the same is not true for truncate, so that still results
in a compilation failure.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213251 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/X86ISelLowering.cpp | patch | blob | history | |
test/CodeGen/X86/cvt16.ll | patch | blob | history |
index 39186c54f9d48c8e4aacbdfaab50465141082f52..d3d2c76de215ae4385d532c64d35b40e272bc109 100644 (file)
setOperationAction(ISD::FP_TO_FP16, MVT::f32, Expand);
}
+ // There's never any support for extending beyond MVT::f32.
+ setOperationAction(ISD::FP16_TO_FP, MVT::f64, Expand);
+ setOperationAction(ISD::FP16_TO_FP, MVT::f80, Expand);
+
if (Subtarget->hasPOPCNT()) {
setOperationAction(ISD::CTPOP , MVT::i8 , Promote);
} else {
index f3d8049321007cdeba1043071206f5d944af60c2..501145ca7151000544aae48d0219f1d20cf325e7 100644 (file)
; F16C-NEXT: vcvtph2ps
; F16C: ret
+define double @test4(i16* nocapture %src) {
+ %1 = load i16* %src, align 2
+ %2 = tail call double @llvm.convert.from.fp16.f64(i16 %1)
+ ret double %2
+}
+; CHECK-LABEL: test4:
+; LIBCALL: callq __gnu_h2f_ieee
+; LIBCALL: cvtss2sd
+; SOFTFLOAT: callq __gnu_h2f_ieee
+; SOFTFLOAT: callq __extendsfdf2
+; F16C: vcvtph2ps
+; F16C: vcvtss2sd
+; F16C: ret
+
declare float @llvm.convert.from.fp16.f32(i16) nounwind readnone
declare i16 @llvm.convert.to.fp16.f32(float) nounwind readnone
-
+declare double @llvm.convert.from.fp16.f64(i16) nounwind readnone