X86: Improve AVX512 fptoui lowering
Summary:
Add patterns for
fptoui <16 x float> to <16 x i8>
fptoui <16 x float> to <16 x i16>
Reviewers: igorb, delena, craig.topper
Reviewed By: craig.topper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D37505
llvm-svn: 312704
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index e9aa51f..151eba4 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -1171,6 +1171,8 @@
setOperationAction(ISD::FP_TO_SINT, MVT::v16i32, Legal);
setOperationAction(ISD::FP_TO_UINT, MVT::v16i32, Legal);
+ setOperationAction(ISD::FP_TO_UINT, MVT::v16i8, Legal);
+ setOperationAction(ISD::FP_TO_UINT, MVT::v16i16, Legal);
setOperationAction(ISD::FP_TO_UINT, MVT::v8i32, Legal);
setOperationAction(ISD::FP_TO_UINT, MVT::v4i32, Legal);
setOperationAction(ISD::FP_TO_UINT, MVT::v2i32, Custom);
diff --git a/llvm/lib/Target/X86/X86InstrAVX512.td b/llvm/lib/Target/X86/X86InstrAVX512.td
index 632fd3f..12709a4 100644
--- a/llvm/lib/Target/X86/X86InstrAVX512.td
+++ b/llvm/lib/Target/X86/X86InstrAVX512.td
@@ -8269,6 +8269,11 @@
defm VPMOVUSWB : avx512_trunc_wb<0x10, "vpmovuswb", X86vtruncus,
truncstore_us_vi8, masked_truncstore_us_vi8>;
+def : Pat<(v16i16 (fp_to_uint (v16f32 VR512:$src1))),
+ (VPMOVDWZrr (v16i32 (VCVTTPS2UDQZrr VR512:$src1)))>, Requires<[HasAVX512]>;
+def : Pat<(v16i8 (fp_to_uint (v16f32 VR512:$src1))),
+ (VPMOVDBZrr (v16i32 (VCVTTPS2UDQZrr VR512:$src1)))>, Requires<[HasAVX512]>;
+
let Predicates = [HasAVX512, NoVLX] in {
def: Pat<(v8i16 (X86vtrunc (v8i32 VR256X:$src))),
(v8i16 (EXTRACT_SUBREG
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index eeced40..871a38d 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1170,7 +1170,11 @@
{ ISD::FP_TO_UINT, MVT::v2i32, MVT::v2f32, 1 },
{ ISD::FP_TO_UINT, MVT::v4i32, MVT::v4f32, 1 },
{ ISD::FP_TO_UINT, MVT::v8i32, MVT::v8f32, 1 },
+ { ISD::FP_TO_UINT, MVT::v8i16, MVT::v8f64, 2 },
+ { ISD::FP_TO_UINT, MVT::v8i8, MVT::v8f64, 2 },
{ ISD::FP_TO_UINT, MVT::v16i32, MVT::v16f32, 1 },
+ { ISD::FP_TO_UINT, MVT::v16i16, MVT::v16f32, 2 },
+ { ISD::FP_TO_UINT, MVT::v16i8, MVT::v16f32, 2 },
};
static const TypeConversionCostTblEntry AVX2ConversionTbl[] = {