[X86][SSE] Update the cost table for integer-integer conversions on SSE2/SSE4.1.

Previously in the conversion cost table there are no entries for integer-integer
conversions on SSE2. This will result in imprecise costs for certain vectorized
operations. This patch adds those entries for SSE2 and SSE4.1. The cost numbers
are counted from the result of running llc on the new test case in this patch.

Differential revision: http://reviews.llvm.org/D15132

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@255315 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86TargetTransformInfo.cpp b/lib/Target/X86/X86TargetTransformInfo.cpp
index cf7a826ea85d65bd52aa24b0b098cd9bbc398197..d33d57584128baf48f33c9ebda1195d42da28b38 100644 (file)
--- a/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -528,6 +528,9 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
   int ISD = TLI->InstructionOpcodeToISD(Opcode);
   assert(ISD && "Invalid opcode");
 
+  // FIXME: Need a better design of the cost table to handle non-simple types of
+  // potential massive combinations (elem_num x src_type x dst_type).
+
   static const TypeConversionCostTblEntry AVX512DQConversionTbl[] = {
     { ISD::UINT_TO_FP,  MVT::v2f64,  MVT::v2i64,  1 },
     { ISD::UINT_TO_FP,  MVT::v4f64,  MVT::v4i64,  1 },
@@ -705,7 +708,38 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
     { ISD::FP_TO_UINT,  MVT::v4i32, MVT::v4f64, 4*4 },
   };
 
-  static const TypeConversionCostTblEntry SSE2ConvTbl[] = {
+  static const TypeConversionCostTblEntry SSE41ConversionTbl[] = {
+    { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i16, 4 },
+    { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i16, 4 },
+    { ISD::ZERO_EXTEND, MVT::v8i32,  MVT::v8i16,  2 },
+    { ISD::SIGN_EXTEND, MVT::v8i32,  MVT::v8i16,  2 },
+    { ISD::ZERO_EXTEND, MVT::v4i32,  MVT::v4i16,  1 },
+    { ISD::SIGN_EXTEND, MVT::v4i32,  MVT::v4i16,  1 },
+    { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i8,  4 },
+    { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i8,  4 },
+    { ISD::ZERO_EXTEND, MVT::v8i32,  MVT::v8i8,   2 },
+    { ISD::SIGN_EXTEND, MVT::v8i32,  MVT::v8i8,   2 },
+    { ISD::ZERO_EXTEND, MVT::v4i32,  MVT::v4i8,   1 },
+    { ISD::SIGN_EXTEND, MVT::v4i32,  MVT::v4i8,   1 },
+    { ISD::ZERO_EXTEND, MVT::v16i16, MVT::v16i8,  2 },
+    { ISD::SIGN_EXTEND, MVT::v16i16, MVT::v16i8,  2 },
+    { ISD::ZERO_EXTEND, MVT::v8i16,  MVT::v8i8,   1 },
+    { ISD::SIGN_EXTEND, MVT::v8i16,  MVT::v8i8,   1 },
+    { ISD::ZERO_EXTEND, MVT::v4i16,  MVT::v4i8,   1 },
+    { ISD::SIGN_EXTEND, MVT::v4i16,  MVT::v4i8,   2 },
+
+    { ISD::TRUNCATE,    MVT::v16i16, MVT::v16i32, 6 },
+    { ISD::TRUNCATE,    MVT::v8i16,  MVT::v8i32,  3 },
+    { ISD::TRUNCATE,    MVT::v4i16,  MVT::v4i32,  1 },
+    { ISD::TRUNCATE,    MVT::v16i8,  MVT::v16i32, 30 },
+    { ISD::TRUNCATE,    MVT::v8i8,   MVT::v8i32,  3 },
+    { ISD::TRUNCATE,    MVT::v4i8,   MVT::v4i32,  1 },
+    { ISD::TRUNCATE,    MVT::v16i8,  MVT::v16i16, 3 },
+    { ISD::TRUNCATE,    MVT::v8i8,   MVT::v8i16,  1 },
+    { ISD::TRUNCATE,    MVT::v4i8,   MVT::v4i16,  2 },
+  };
+
+  static const TypeConversionCostTblEntry SSE2ConversionTbl[] = {
     // These are somewhat magic numbers justified by looking at the output of
     // Intel's IACA, running some kernels and making sure when we take
     // legalization into account the throughput will be overestimated.
@@ -726,13 +760,42 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
     { ISD::SINT_TO_FP, MVT::v4f32, MVT::v4i32, 15 },
     { ISD::SINT_TO_FP, MVT::v4f32, MVT::v8i16, 15 },
     { ISD::SINT_TO_FP, MVT::v4f32, MVT::v16i8, 8 },
+
+    { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i16, 6 },
+    { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i16, 8 },
+    { ISD::ZERO_EXTEND, MVT::v8i32,  MVT::v8i16,  3 },
+    { ISD::SIGN_EXTEND, MVT::v8i32,  MVT::v8i16,  4 },
+    { ISD::ZERO_EXTEND, MVT::v4i32,  MVT::v4i16,  1 },
+    { ISD::SIGN_EXTEND, MVT::v4i32,  MVT::v4i16,  2 },
+    { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i8,  9 },
+    { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i8,  12 },
+    { ISD::ZERO_EXTEND, MVT::v8i32,  MVT::v8i8,   6 },
+    { ISD::SIGN_EXTEND, MVT::v8i32,  MVT::v8i8,   6 },
+    { ISD::ZERO_EXTEND, MVT::v4i32,  MVT::v4i8,   2 },
+    { ISD::SIGN_EXTEND, MVT::v4i32,  MVT::v4i8,   3 },
+    { ISD::ZERO_EXTEND, MVT::v16i16, MVT::v16i8,  3 },
+    { ISD::SIGN_EXTEND, MVT::v16i16, MVT::v16i8,  4 },
+    { ISD::ZERO_EXTEND, MVT::v8i16,  MVT::v8i8,   1 },
+    { ISD::SIGN_EXTEND, MVT::v8i16,  MVT::v8i8,   2 },
+    { ISD::ZERO_EXTEND, MVT::v4i16,  MVT::v4i8,   1 },
+    { ISD::SIGN_EXTEND, MVT::v4i16,  MVT::v4i8,   6 },
+
+    { ISD::TRUNCATE,    MVT::v16i16, MVT::v16i32, 14 },
+    { ISD::TRUNCATE,    MVT::v8i16,  MVT::v8i32,  7 },
+    { ISD::TRUNCATE,    MVT::v4i16,  MVT::v4i32,  3 },
+    { ISD::TRUNCATE,    MVT::v16i8,  MVT::v16i32, 31 },
+    { ISD::TRUNCATE,    MVT::v8i8,   MVT::v8i32,  4 },
+    { ISD::TRUNCATE,    MVT::v4i8,   MVT::v4i32,  3 },
+    { ISD::TRUNCATE,    MVT::v16i8,  MVT::v16i16, 3 },
+    { ISD::TRUNCATE,    MVT::v8i8,   MVT::v8i16,  2 },
+    { ISD::TRUNCATE,    MVT::v4i8,   MVT::v4i16,  4 },
   };
 
   std::pair<int, MVT> LTSrc = TLI->getTypeLegalizationCost(DL, Src);
   std::pair<int, MVT> LTDest = TLI->getTypeLegalizationCost(DL, Dst);
 
   if (ST->hasSSE2() && !ST->hasAVX()) {
-    if (const auto *Entry = ConvertCostTableLookup(SSE2ConvTbl, ISD,
+    if (const auto *Entry = ConvertCostTableLookup(SSE2ConversionTbl, ISD,
                                                    LTDest.second, LTSrc.second))
       return LTSrc.first * Entry->Cost;
   }
@@ -770,6 +833,20 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
       return Entry->Cost;
   }
 
+  if (ST->hasSSE41()) {
+    if (const auto *Entry = ConvertCostTableLookup(SSE41ConversionTbl, ISD,
+                                                   DstTy.getSimpleVT(),
+                                                   SrcTy.getSimpleVT()))
+      return Entry->Cost;
+  }
+
+  if (ST->hasSSE2()) {
+    if (const auto *Entry = ConvertCostTableLookup(SSE2ConversionTbl, ISD,
+                                                   DstTy.getSimpleVT(),
+                                                   SrcTy.getSimpleVT()))
+      return Entry->Cost;
+  }
+
   return BaseT::getCastInstrCost(Opcode, Dst, Src);
 }
 

diff --git a/test/Analysis/CostModel/X86/sitofp.ll b/test/Analysis/CostModel/X86/sitofp.ll
index 9913a48969125f966ca00091825dea6e81b1ee35..9f0c4065c17880ee37288c042efae63addf4ac6e 100644 (file)
--- a/test/Analysis/CostModel/X86/sitofp.ll
+++ b/test/Analysis/CostModel/X86/sitofp.ll
@@ -248,13 +248,13 @@ define <2 x double> @sitofpv2i64v2double(<2 x i64> %a) {
   ; SSE2: cost of 20 {{.*}} sitofp
   ;
   ; AVX1-LABEL: sitofpv2i64v2double
-  ; AVX1: cost of 4 {{.*}} sitofp
+  ; AVX1: cost of 20 {{.*}} sitofp
   ;
   ; AVX2-LABEL: sitofpv2i64v2double
-  ; AVX2: cost of 4 {{.*}} sitofp
+  ; AVX2: cost of 20 {{.*}} sitofp
   ;
   ; AVX512F-LABEL: sitofpv2i64v2double
-  ; AVX512F: cost of 4 {{.*}} sitofp
+  ; AVX512F: cost of 20 {{.*}} sitofp
   %1 = sitofp <2 x i64> %a to <2 x double>
   ret <2 x double> %1
 }

diff --git a/test/Analysis/CostModel/X86/sse-itoi.ll b/test/Analysis/CostModel/X86/sse-itoi.ll
new file mode 100644 (file)
index 0000000..6429e4f
--- /dev/null
+++ b/test/Analysis/CostModel/X86/sse-itoi.ll
@@ -0,0 +1,353 @@
+; RUN: opt -mtriple=x86_64-apple-darwin -mattr=+sse2 -cost-model -analyze < %s | FileCheck --check-prefix=SSE2 %s
+; RUN: opt -mtriple=x86_64-apple-darwin -mattr=+sse4.1 -cost-model -analyze < %s | FileCheck --check-prefix=SSE41 %s
+
+define void @zext_v16i16_to_v16i32(<16 x i16>* %a) {
+; SSE2: zext_v16i16_to_v16i32
+; SSE2: cost of 6 {{.*}} zext
+;
+; SSE41: zext_v16i16_to_v16i32
+; SSE41: cost of 4 {{.*}} zext
+;
+  %1 = load <16 x i16>, <16 x i16>* %a
+  %2 = zext <16 x i16> %1 to <16 x i32>
+  store <16 x i32> %2, <16 x i32>* undef, align 4
+  ret void
+}
+
+define void @sext_v16i16_to_v16i32(<16 x i16>* %a) {
+; SSE2: sext_v16i16_to_v16i32
+; SSE2: cost of 8 {{.*}} sext
+;
+; SSE41: sext_v16i16_to_v16i32
+; SSE41: cost of 4 {{.*}} sext
+;
+  %1 = load <16 x i16>, <16 x i16>* %a
+  %2 = sext <16 x i16> %1 to <16 x i32>
+  store <16 x i32> %2, <16 x i32>* undef, align 4
+  ret void
+}
+
+define void @zext_v8i16_to_v8i32(<8 x i16>* %a) {
+; SSE2: zext_v8i16_to_v8i32
+; SSE2: cost of 3 {{.*}} zext
+;
+; SSE41: zext_v8i16_to_v8i32
+; SSE41: cost of 2 {{.*}} zext
+;
+  %1 = load <8 x i16>, <8 x i16>* %a
+  %2 = zext <8 x i16> %1 to <8 x i32>
+  store <8 x i32> %2, <8 x i32>* undef, align 4
+  ret void
+}
+
+define void @sext_v8i16_to_v8i32(<8 x i16>* %a) {
+; SSE2: sext_v8i16_to_v8i32
+; SSE2: cost of 4 {{.*}} sext
+;
+; SSE41: sext_v8i16_to_v8i32
+; SSE41: cost of 2 {{.*}} sext
+;
+  %1 = load <8 x i16>, <8 x i16>* %a
+  %2 = sext <8 x i16> %1 to <8 x i32>
+  store <8 x i32> %2, <8 x i32>* undef, align 4
+  ret void
+}
+
+define void @zext_v4i16_to_v4i32(<4 x i16>* %a) {
+; SSE2: zext_v4i16_to_v4i32
+; SSE2: cost of 1 {{.*}} zext
+;
+; SSE41: zext_v4i16_to_v4i32
+; SSE41: cost of 1 {{.*}} zext
+;
+  %1 = load <4 x i16>, <4 x i16>* %a
+  %2 = zext <4 x i16> %1 to <4 x i32>
+  store <4 x i32> %2, <4 x i32>* undef, align 4
+  ret void
+}
+
+define void @sext_v4i16_to_v4i32(<4 x i16>* %a) {
+; SSE2: sext_v4i16_to_v4i32
+; SSE2: cost of 2 {{.*}} sext
+;
+; SSE41: sext_v4i16_to_v4i32
+; SSE41: cost of 1 {{.*}} sext
+;
+  %1 = load <4 x i16>, <4 x i16>* %a
+  %2 = sext <4 x i16> %1 to <4 x i32>
+  store <4 x i32> %2, <4 x i32>* undef, align 4
+  ret void
+}
+
+define void @zext_v16i8_to_v16i32(<16 x i8>* %a) {
+; SSE2: zext_v16i8_to_v16i32
+; SSE2: cost of 9 {{.*}} zext
+;
+; SSE41: zext_v16i8_to_v16i32
+; SSE41: cost of 4 {{.*}} zext
+;
+  %1 = load <16 x i8>, <16 x i8>* %a
+  %2 = zext <16 x i8> %1 to <16 x i32>
+  store <16 x i32> %2, <16 x i32>* undef, align 4
+  ret void
+}
+
+define void @sext_v16i8_to_v16i32(<16 x i8>* %a) {
+; SSE2: sext_v16i8_to_v16i32
+; SSE2: cost of 12 {{.*}} sext
+;
+; SSE41: sext_v16i8_to_v16i32
+; SSE41: cost of 4 {{.*}} sext
+;
+  %1 = load <16 x i8>, <16 x i8>* %a
+  %2 = sext <16 x i8> %1 to <16 x i32>
+  store <16 x i32> %2, <16 x i32>* undef, align 4
+  ret void
+}
+
+define void @zext_v8i8_to_v8i32(<8 x i8>* %a) {
+; SSE2: zext_v8i8_to_v8i32
+; SSE2: cost of 6 {{.*}} zext
+;
+; SSE41: zext_v8i8_to_v8i32
+; SSE41: cost of 2 {{.*}} zext
+;
+  %1 = load <8 x i8>, <8 x i8>* %a
+  %2 = zext <8 x i8> %1 to <8 x i32>
+  store <8 x i32> %2, <8 x i32>* undef, align 4
+  ret void
+}
+
+define void @sext_v8i8_to_v8i32(<8 x i8>* %a) {
+; SSE2: sext_v8i8_to_v8i32
+; SSE2: cost of 6 {{.*}} sext
+;
+; SSE41: sext_v8i8_to_v8i32
+; SSE41: cost of 2 {{.*}} sext
+;
+  %1 = load <8 x i8>, <8 x i8>* %a
+  %2 = sext <8 x i8> %1 to <8 x i32>
+  store <8 x i32> %2, <8 x i32>* undef, align 4
+  ret void
+}
+
+define void @zext_v4i8_to_v4i32(<4 x i8>* %a) {
+; SSE2: zext_v4i8_to_v4i32
+; SSE2: cost of 2 {{.*}} zext
+;
+; SSE41: zext_v4i8_to_v4i32
+; SSE41: cost of 1 {{.*}} zext
+;
+  %1 = load <4 x i8>, <4 x i8>* %a
+  %2 = zext <4 x i8> %1 to <4 x i32>
+  store <4 x i32> %2, <4 x i32>* undef, align 4
+  ret void
+}
+
+define void @sext_v4i8_to_v4i32(<4 x i8>* %a) {
+; SSE2: sext_v4i8_to_v4i32
+; SSE2: cost of 3 {{.*}} sext
+;
+; SSE41: sext_v4i8_to_v4i32
+; SSE41: cost of 1 {{.*}} sext
+;
+  %1 = load <4 x i8>, <4 x i8>* %a
+  %2 = sext <4 x i8> %1 to <4 x i32>
+  store <4 x i32> %2, <4 x i32>* undef, align 4
+  ret void
+}
+
+define void @zext_v16i8_to_v16i16(<16 x i8>* %a) {
+; SSE2: zext_v16i8_to_v16i16
+; SSE2: cost of 3 {{.*}} zext
+;
+; SSE41: zext_v16i8_to_v16i16
+; SSE41: cost of 2 {{.*}} zext
+;
+  %1 = load <16 x i8>, <16 x i8>* %a
+  %2 = zext <16 x i8> %1 to <16 x i16>
+  store <16 x i16> %2, <16 x i16>* undef, align 4
+  ret void
+}
+
+define void @sext_v16i8_to_v16i16(<16 x i8>* %a) {
+; SSE2: sext_v16i8_to_v16i16
+; SSE2: cost of 4 {{.*}} sext
+;
+; SSE41: sext_v16i8_to_v16i16
+; SSE41: cost of 2 {{.*}} sext
+;
+  %1 = load <16 x i8>, <16 x i8>* %a
+  %2 = sext <16 x i8> %1 to <16 x i16>
+  store <16 x i16> %2, <16 x i16>* undef, align 4
+  ret void
+}
+
+define void @zext_v8i8_to_v8i16(<8 x i8>* %a) {
+; SSE2: zext_v8i8_to_v8i16
+; SSE2: cost of 1 {{.*}} zext
+;
+; SSE41: zext_v8i8_to_v8i16
+; SSE41: cost of 1 {{.*}} zext
+;
+  %1 = load <8 x i8>, <8 x i8>* %a
+  %2 = zext <8 x i8> %1 to <8 x i16>
+  store <8 x i16> %2, <8 x i16>* undef, align 4
+  ret void
+}
+
+define void @sext_v8i8_to_v8i16(<8 x i8>* %a) {
+; SSE2: sext_v8i8_to_v8i16
+; SSE2: cost of 2 {{.*}} sext
+;
+; SSE41: sext_v8i8_to_v8i16
+; SSE41: cost of 1 {{.*}} sext
+;
+  %1 = load <8 x i8>, <8 x i8>* %a
+  %2 = sext <8 x i8> %1 to <8 x i16>
+  store <8 x i16> %2, <8 x i16>* undef, align 4
+  ret void
+}
+
+define void @zext_v4i8_to_v4i16(<4 x i8>* %a) {
+; SSE2: zext_v4i8_to_v4i16
+; SSE2: cost of 1 {{.*}} zext
+;
+; SSE41: zext_v4i8_to_v4i16
+; SSE41: cost of 1 {{.*}} zext
+;
+  %1 = load <4 x i8>, <4 x i8>* %a
+  %2 = zext <4 x i8> %1 to <4 x i16>
+  store <4 x i16> %2, <4 x i16>* undef, align 4
+  ret void
+}
+
+define void @sext_v4i8_to_v4i16(<4 x i8>* %a) {
+; SSE2: sext_v4i8_to_v4i16
+; SSE2: cost of 6 {{.*}} sext
+;
+; SSE41: sext_v4i8_to_v4i16
+; SSE41: cost of 2 {{.*}} sext
+;
+  %1 = load <4 x i8>, <4 x i8>* %a
+  %2 = sext <4 x i8> %1 to <4 x i16>
+  store <4 x i16> %2, <4 x i16>* undef, align 4
+  ret void
+}
+
+define void @truncate_v16i32_to_v16i16(<16 x i32>* %a) {
+; SSE2: truncate_v16i32_to_v16i16
+; SSE2: cost of 14 {{.*}} trunc
+;
+; SSE41: truncate_v16i32_to_v16i16
+; SSE41: cost of 6 {{.*}} trunc
+;
+  %1 = load <16 x i32>, <16 x i32>* %a
+  %2 = trunc <16 x i32> %1 to <16 x i16>
+  store <16 x i16> %2, <16 x i16>* undef, align 4
+  ret void
+}
+
+define void @truncate_v8i32_to_v8i16(<8 x i32>* %a) {
+; SSE2: truncate_v8i32_to_v8i16
+; SSE2: cost of 7 {{.*}} trunc
+;
+; SSE41: truncate_v8i32_to_v8i16
+; SSE41: cost of 3 {{.*}} trunc
+;
+  %1 = load <8 x i32>, <8 x i32>* %a
+  %2 = trunc <8 x i32> %1 to <8 x i16>
+  store <8 x i16> %2, <8 x i16>* undef, align 4
+  ret void
+}
+
+define void @truncate_v4i32_to_v4i16(<4 x i32>* %a) {
+; SSE2: truncate_v4i32_to_v4i16
+; SSE2: cost of 3 {{.*}} trunc
+;
+; SSE41: truncate_v4i32_to_v4i16
+; SSE41: cost of 1 {{.*}} trunc
+;
+  %1 = load <4 x i32>, <4 x i32>* %a
+  %2 = trunc <4 x i32> %1 to <4 x i16>
+  store <4 x i16> %2, <4 x i16>* undef, align 4
+  ret void
+}
+
+define void @truncate_v16i32_to_v16i8(<16 x i32>* %a) {
+; SSE2: truncate_v16i32_to_v16i8
+; SSE2: cost of 31 {{.*}} trunc
+;
+; SSE41: truncate_v16i32_to_v16i8
+; SSE41: cost of 30 {{.*}} trunc
+;
+  %1 = load <16 x i32>, <16 x i32>* %a
+  %2 = trunc <16 x i32> %1 to <16 x i8>
+  store <16 x i8> %2, <16 x i8>* undef, align 4
+  ret void
+}
+
+define void @truncate_v8i32_to_v8i8(<8 x i32>* %a) {
+; SSE2: truncate_v8i32_to_v8i8
+; SSE2: cost of 4 {{.*}} trunc
+;
+; SSE41: truncate_v8i32_to_v8i8
+; SSE41: cost of 3 {{.*}} trunc
+;
+  %1 = load <8 x i32>, <8 x i32>* %a
+  %2 = trunc <8 x i32> %1 to <8 x i8>
+  store <8 x i8> %2, <8 x i8>* undef, align 4
+  ret void
+}
+
+define void @truncate_v4i32_to_v4i8(<4 x i32>* %a) {
+; SSE2: truncate_v4i32_to_v4i8
+; SSE2: cost of 3 {{.*}} trunc
+;
+; SSE41: truncate_v4i32_to_v4i8
+; SSE41: cost of 1 {{.*}} trunc
+;
+  %1 = load <4 x i32>, <4 x i32>* %a
+  %2 = trunc <4 x i32> %1 to <4 x i8>
+  store <4 x i8> %2, <4 x i8>* undef, align 4
+  ret void
+}
+
+define void @truncate_v16i16_to_v16i8(<16 x i16>* %a) {
+; SSE2: truncate_v16i16_to_v16i8
+; SSE2: cost of 3 {{.*}} trunc
+;
+; SSE41: truncate_v16i16_to_v16i8
+; SSE41: cost of 3 {{.*}} trunc
+;
+  %1 = load <16 x i16>, <16 x i16>* %a
+  %2 = trunc <16 x i16> %1 to <16 x i8>
+  store <16 x i8> %2, <16 x i8>* undef, align 4
+  ret void
+}
+
+define void @truncate_v8i16_to_v8i8(<8 x i16>* %a) {
+; SSE2: truncate_v8i16_to_v8i8
+; SSE2: cost of 2 {{.*}} trunc
+;
+; SSE41: truncate_v8i16_to_v8i8
+; SSE41: cost of 1 {{.*}} trunc
+;
+  %1 = load <8 x i16>, <8 x i16>* %a
+  %2 = trunc <8 x i16> %1 to <8 x i8>
+  store <8 x i8> %2, <8 x i8>* undef, align 4
+  ret void
+}
+
+define void @truncate_v4i16_to_v4i8(<4 x i16>* %a) {
+; SSE2: truncate_v4i16_to_v4i8
+; SSE2: cost of 4 {{.*}} trunc
+;
+; SSE41: truncate_v4i16_to_v4i8
+; SSE41: cost of 2 {{.*}} trunc
+;
+  %1 = load <4 x i16>, <4 x i16>* %a
+  %2 = trunc <4 x i16> %1 to <4 x i8>
+  store <4 x i8> %2, <4 x i8>* undef, align 4
+  ret void
+}