diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 62577162f1d4..e7fe40379b41 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -937,14 +937,6 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
     setOperationAction(ISD::FP_TO_UINT,         MVT::v2i16, Custom);
     setOperationAction(ISD::FP_TO_UINT,         MVT::v4i16, Custom);
 
-    // By marking FP_TO_SINT v8i16 as Custom, will trick type legalization into
-    // promoting v8i8 FP_TO_UINT into FP_TO_SINT. When the v8i16 FP_TO_SINT is
-    // split again based on the input type, this will cause an AssertSExt i16 to
-    // be emitted instead of an AssertZExt. This will allow packssdw followed by
-    // packuswb to be used to truncate to v8i8. This is necessary since packusdw
-    // isn't available until sse4.1.
-    setOperationAction(ISD::FP_TO_SINT,         MVT::v8i16, Custom);
-
     setOperationAction(ISD::SINT_TO_FP,         MVT::v4i32, Legal);
     setOperationAction(ISD::SINT_TO_FP,         MVT::v2i32, Custom);
 
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index b4db1cc9bc17..0b3a5319baac 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1576,6 +1576,9 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
     { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, 6 },
     { ISD::UINT_TO_FP, MVT::v4f32, MVT::v2i64, 15 },
 
+    { ISD::FP_TO_SINT,  MVT::v4i16,  MVT::v4f32,  2 },
+    { ISD::FP_TO_SINT,  MVT::v2i16,  MVT::v2f64,  2 },
+
     { ISD::FP_TO_SINT,  MVT::v2i32,  MVT::v2f64,  3 },
 
     { ISD::UINT_TO_FP,  MVT::f64,    MVT::i64,    6 },
diff --git a/llvm/test/Analysis/CostModel/X86/fptosi.ll b/llvm/test/Analysis/CostModel/X86/fptosi.ll
index 2f8ea1352aff..7583d6e60c80 100644
--- a/llvm/test/Analysis/CostModel/X86/fptosi.ll
+++ b/llvm/test/Analysis/CostModel/X86/fptosi.ll
@@ -92,28 +92,28 @@ define i32 @fptosi_double_i32(i32 %arg) {
 define i32 @fptosi_double_i16(i32 %arg) {
 ; SSE-LABEL: 'fptosi_double_i16'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
-; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'fptosi_double_i16'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'fptosi_double_i16'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; BTVER2-LABEL: 'fptosi_double_i16'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -235,28 +235,28 @@ define i32 @fptosi_float_i32(i32 %arg) {
 define i32 @fptosi_float_i16(i32 %arg) {
 ; SSE-LABEL: 'fptosi_float_i16'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
-; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'fptosi_float_i16'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'fptosi_float_i16'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; BTVER2-LABEL: 'fptosi_float_i16'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef