Index: lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
===================================================================
--- lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
+++ lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
@@ -737,9 +737,18 @@
 
   ArrayRef<Instruction *> NewChain = getVectorizablePrefix(Chain);
   if (NewChain.empty()) {
-    // No vectorization possible.
-    InstructionsProcessed->insert(Chain.begin(), Chain.end());
-    return false;
+    // No vectorization possible if the number of instructions
+    // is less than or equal to VF.
+    if (ChainSize <= VF) {
+      InstructionsProcessed->insert(Chain.begin(), Chain.end());
+      return false;
+    }
+    // Split the chain and try each slice seperately in order
+    // to increase the number of vector instructions generated.
+    ArrayRef<Instruction *> Left = Chain.slice(0, VF);
+    ArrayRef<Instruction *> Right = Chain.slice(VF);
+    return vectorizeStoreChain(Left, InstructionsProcessed) |
+           vectorizeStoreChain(Right, InstructionsProcessed);
   }
   if (NewChain.size() == 1) {
     // Failed after the first instruction. Discard it and try the smaller chain.
@@ -885,9 +894,18 @@
 
   ArrayRef<Instruction *> NewChain = getVectorizablePrefix(Chain);
   if (NewChain.empty()) {
-    // No vectorization possible.
-    InstructionsProcessed->insert(Chain.begin(), Chain.end());
-    return false;
+    // No vectorization possible if the number of instructions
+    // is less than or equal to VF.
+    if (ChainSize <= VF) {
+      InstructionsProcessed->insert(Chain.begin(), Chain.end());
+      return false;
+    }
+    // Split the chain and try each slice seperately in order
+    // to increase the number of vector instructions generated.
+    ArrayRef<Instruction *> Left = Chain.slice(0, VF);
+    ArrayRef<Instruction *> Right = Chain.slice(VF);
+    return vectorizeLoadChain(Left, InstructionsProcessed) |
+           vectorizeLoadChain(Right, InstructionsProcessed);
   }
   if (NewChain.size() == 1) {
     // Failed after the first instruction. Discard it and try the smaller chain.
Index: test/Transforms/LoadStoreVectorizer/AMDGPU/empty-prefix.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoadStoreVectorizer/AMDGPU/empty-prefix.ll
@@ -0,0 +1,330 @@
+; RUN: opt -mtriple=amdgcn-amd-amdhsa -load-store-vectorizer -S -o - %s | FileCheck %s
+
+; Split the chain and try again if the vectorizable
+; prefix is empty. This will vectorize 48 more scalars.
+
+; CHECK-LABEL: foo
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+; CHECK: store <4 x float>
+
+; Function Attrs: nounwind
+define void @foo(i8 addrspace(1)* %a, i8 addrspace(1)* %b) #0 {
+bb:
+  %tmp = bitcast i8 addrspace(1)* %b to float addrspace(1)*
+  %tmp1 = load float, float addrspace(1)* %tmp, align 4
+  %tmp2 = getelementptr i8, i8 addrspace(1)* %b, i64 4
+  %tmp3 = bitcast i8 addrspace(1)* %tmp2 to float addrspace(1)*
+  %tmp4 = load float, float addrspace(1)* %tmp3, align 4
+  %tmp5 = getelementptr i8, i8 addrspace(1)* %b, i64 8
+  %tmp6 = bitcast i8 addrspace(1)* %tmp5 to float addrspace(1)*
+  %tmp7 = load float, float addrspace(1)* %tmp6, align 4
+  %tmp8 = getelementptr i8, i8 addrspace(1)* %b, i64 12
+  %tmp9 = bitcast i8 addrspace(1)* %tmp8 to float addrspace(1)*
+  %tmp10 = load float, float addrspace(1)* %tmp9, align 4
+  %tmp11 = getelementptr i8, i8 addrspace(1)* %b, i64 16
+  %tmp12 = bitcast i8 addrspace(1)* %tmp11 to float addrspace(1)*
+  %tmp13 = load float, float addrspace(1)* %tmp12, align 4
+  %tmp14 = getelementptr i8, i8 addrspace(1)* %b, i64 20
+  %tmp15 = bitcast i8 addrspace(1)* %tmp14 to float addrspace(1)*
+  %tmp16 = load float, float addrspace(1)* %tmp15, align 4
+  %tmp17 = getelementptr i8, i8 addrspace(1)* %b, i64 24
+  %tmp18 = bitcast i8 addrspace(1)* %tmp17 to float addrspace(1)*
+  %tmp19 = load float, float addrspace(1)* %tmp18, align 4
+  %tmp20 = getelementptr i8, i8 addrspace(1)* %b, i64 28
+  %tmp21 = bitcast i8 addrspace(1)* %tmp20 to float addrspace(1)*
+  %tmp22 = load float, float addrspace(1)* %tmp21, align 4
+  %tmp23 = getelementptr i8, i8 addrspace(1)* %b, i64 32
+  %tmp24 = bitcast i8 addrspace(1)* %tmp23 to float addrspace(1)*
+  %tmp25 = load float, float addrspace(1)* %tmp24, align 4
+  %tmp26 = getelementptr i8, i8 addrspace(1)* %b, i64 36
+  %tmp27 = bitcast i8 addrspace(1)* %tmp26 to float addrspace(1)*
+  %tmp28 = load float, float addrspace(1)* %tmp27, align 4
+  %tmp29 = getelementptr i8, i8 addrspace(1)* %b, i64 40
+  %tmp30 = bitcast i8 addrspace(1)* %tmp29 to float addrspace(1)*
+  %tmp31 = load float, float addrspace(1)* %tmp30, align 4
+  %tmp32 = getelementptr i8, i8 addrspace(1)* %b, i64 44
+  %tmp33 = bitcast i8 addrspace(1)* %tmp32 to float addrspace(1)*
+  %tmp34 = load float, float addrspace(1)* %tmp33, align 4
+  %tmp35 = getelementptr i8, i8 addrspace(1)* %b, i64 48
+  %tmp36 = bitcast i8 addrspace(1)* %tmp35 to float addrspace(1)*
+  %tmp37 = load float, float addrspace(1)* %tmp36, align 4
+  %tmp38 = getelementptr i8, i8 addrspace(1)* %b, i64 52
+  %tmp39 = bitcast i8 addrspace(1)* %tmp38 to float addrspace(1)*
+  %tmp40 = load float, float addrspace(1)* %tmp39, align 4
+  %tmp41 = getelementptr i8, i8 addrspace(1)* %b, i64 56
+  %tmp42 = bitcast i8 addrspace(1)* %tmp41 to float addrspace(1)*
+  %tmp43 = load float, float addrspace(1)* %tmp42, align 4
+  %tmp44 = getelementptr i8, i8 addrspace(1)* %b, i64 60
+  %tmp45 = bitcast i8 addrspace(1)* %tmp44 to float addrspace(1)*
+  %tmp46 = load float, float addrspace(1)* %tmp45, align 4
+  %tmp47 = getelementptr i8, i8 addrspace(1)* %b, i64 64
+  %tmp48 = bitcast i8 addrspace(1)* %tmp47 to float addrspace(1)*
+  %tmp49 = load float, float addrspace(1)* %tmp48, align 4
+  %tmp50 = getelementptr i8, i8 addrspace(1)* %b, i64 68
+  %tmp51 = bitcast i8 addrspace(1)* %tmp50 to float addrspace(1)*
+  %tmp52 = load float, float addrspace(1)* %tmp51, align 4
+  %tmp53 = getelementptr i8, i8 addrspace(1)* %b, i64 72
+  %tmp54 = bitcast i8 addrspace(1)* %tmp53 to float addrspace(1)*
+  %tmp55 = load float, float addrspace(1)* %tmp54, align 4
+  %tmp56 = getelementptr i8, i8 addrspace(1)* %b, i64 76
+  %tmp57 = bitcast i8 addrspace(1)* %tmp56 to float addrspace(1)*
+  %tmp58 = load float, float addrspace(1)* %tmp57, align 4
+  %tmp59 = getelementptr i8, i8 addrspace(1)* %b, i64 80
+  %tmp60 = bitcast i8 addrspace(1)* %tmp59 to float addrspace(1)*
+  %tmp61 = load float, float addrspace(1)* %tmp60, align 4
+  %tmp62 = getelementptr i8, i8 addrspace(1)* %b, i64 84
+  %tmp63 = bitcast i8 addrspace(1)* %tmp62 to float addrspace(1)*
+  %tmp64 = load float, float addrspace(1)* %tmp63, align 4
+  %tmp65 = getelementptr i8, i8 addrspace(1)* %b, i64 88
+  %tmp66 = bitcast i8 addrspace(1)* %tmp65 to float addrspace(1)*
+  %tmp67 = load float, float addrspace(1)* %tmp66, align 4
+  %tmp68 = getelementptr i8, i8 addrspace(1)* %b, i64 92
+  %tmp69 = bitcast i8 addrspace(1)* %tmp68 to float addrspace(1)*
+  %tmp70 = load float, float addrspace(1)* %tmp69, align 4
+  %tmp71 = getelementptr i8, i8 addrspace(1)* %b, i64 96
+  %tmp72 = bitcast i8 addrspace(1)* %tmp71 to float addrspace(1)*
+  %tmp73 = load float, float addrspace(1)* %tmp72, align 4
+  %tmp74 = getelementptr i8, i8 addrspace(1)* %b, i64 100
+  %tmp75 = bitcast i8 addrspace(1)* %tmp74 to float addrspace(1)*
+  %tmp76 = load float, float addrspace(1)* %tmp75, align 4
+  %tmp77 = getelementptr i8, i8 addrspace(1)* %b, i64 104
+  %tmp78 = bitcast i8 addrspace(1)* %tmp77 to float addrspace(1)*
+  %tmp79 = load float, float addrspace(1)* %tmp78, align 4
+  %tmp80 = getelementptr i8, i8 addrspace(1)* %b, i64 108
+  %tmp81 = bitcast i8 addrspace(1)* %tmp80 to float addrspace(1)*
+  %tmp82 = load float, float addrspace(1)* %tmp81, align 4
+  %tmp83 = getelementptr i8, i8 addrspace(1)* %b, i64 112
+  %tmp84 = bitcast i8 addrspace(1)* %tmp83 to float addrspace(1)*
+  %tmp85 = load float, float addrspace(1)* %tmp84, align 4
+  %tmp86 = getelementptr i8, i8 addrspace(1)* %b, i64 116
+  %tmp87 = bitcast i8 addrspace(1)* %tmp86 to float addrspace(1)*
+  %tmp88 = load float, float addrspace(1)* %tmp87, align 4
+  %tmp89 = getelementptr i8, i8 addrspace(1)* %b, i64 120
+  %tmp90 = bitcast i8 addrspace(1)* %tmp89 to float addrspace(1)*
+  %tmp91 = load float, float addrspace(1)* %tmp90, align 4
+  %tmp92 = getelementptr i8, i8 addrspace(1)* %b, i64 124
+  %tmp93 = bitcast i8 addrspace(1)* %tmp92 to float addrspace(1)*
+  %tmp94 = load float, float addrspace(1)* %tmp93, align 4
+  %tmp95 = bitcast i8 addrspace(1)* %a to float addrspace(1)*
+  store float %tmp1, float addrspace(1)* %tmp95, align 4
+  %tmp96 = getelementptr i8, i8 addrspace(1)* %a, i64 4
+  %tmp97 = bitcast i8 addrspace(1)* %tmp96 to float addrspace(1)*
+  store float %tmp4, float addrspace(1)* %tmp97, align 4
+  %tmp98 = getelementptr i8, i8 addrspace(1)* %a, i64 8
+  %tmp99 = bitcast i8 addrspace(1)* %tmp98 to float addrspace(1)*
+  store float %tmp7, float addrspace(1)* %tmp99, align 4
+  %tmp100 = getelementptr i8, i8 addrspace(1)* %a, i64 12
+  %tmp101 = bitcast i8 addrspace(1)* %tmp100 to float addrspace(1)*
+  store float %tmp10, float addrspace(1)* %tmp101, align 4
+  %tmp102 = getelementptr i8, i8 addrspace(1)* %a, i64 16
+  %tmp103 = bitcast i8 addrspace(1)* %tmp102 to float addrspace(1)*
+  store float %tmp13, float addrspace(1)* %tmp103, align 4
+  %tmp104 = getelementptr i8, i8 addrspace(1)* %a, i64 20
+  %tmp105 = bitcast i8 addrspace(1)* %tmp104 to float addrspace(1)*
+  store float %tmp16, float addrspace(1)* %tmp105, align 4
+  %tmp106 = getelementptr i8, i8 addrspace(1)* %a, i64 24
+  %tmp107 = bitcast i8 addrspace(1)* %tmp106 to float addrspace(1)*
+  store float %tmp19, float addrspace(1)* %tmp107, align 4
+  %tmp108 = getelementptr i8, i8 addrspace(1)* %a, i64 28
+  %tmp109 = bitcast i8 addrspace(1)* %tmp108 to float addrspace(1)*
+  store float %tmp22, float addrspace(1)* %tmp109, align 4
+  %tmp110 = getelementptr i8, i8 addrspace(1)* %a, i64 32
+  %tmp111 = bitcast i8 addrspace(1)* %tmp110 to float addrspace(1)*
+  store float %tmp25, float addrspace(1)* %tmp111, align 4
+  %tmp112 = getelementptr i8, i8 addrspace(1)* %a, i64 36
+  %tmp113 = bitcast i8 addrspace(1)* %tmp112 to float addrspace(1)*
+  store float %tmp28, float addrspace(1)* %tmp113, align 4
+  %tmp114 = getelementptr i8, i8 addrspace(1)* %a, i64 40
+  %tmp115 = bitcast i8 addrspace(1)* %tmp114 to float addrspace(1)*
+  store float %tmp31, float addrspace(1)* %tmp115, align 4
+  %tmp116 = getelementptr i8, i8 addrspace(1)* %a, i64 44
+  %tmp117 = bitcast i8 addrspace(1)* %tmp116 to float addrspace(1)*
+  store float %tmp34, float addrspace(1)* %tmp117, align 4
+  %tmp118 = getelementptr i8, i8 addrspace(1)* %a, i64 48
+  %tmp119 = bitcast i8 addrspace(1)* %tmp118 to float addrspace(1)*
+  store float %tmp37, float addrspace(1)* %tmp119, align 4
+  %tmp120 = getelementptr i8, i8 addrspace(1)* %a, i64 52
+  %tmp121 = bitcast i8 addrspace(1)* %tmp120 to float addrspace(1)*
+  store float %tmp40, float addrspace(1)* %tmp121, align 4
+  %tmp122 = getelementptr i8, i8 addrspace(1)* %a, i64 56
+  %tmp123 = bitcast i8 addrspace(1)* %tmp122 to float addrspace(1)*
+  store float %tmp43, float addrspace(1)* %tmp123, align 4
+  %tmp124 = getelementptr i8, i8 addrspace(1)* %a, i64 60
+  %tmp125 = bitcast i8 addrspace(1)* %tmp124 to float addrspace(1)*
+  store float %tmp46, float addrspace(1)* %tmp125, align 4
+  %tmp126 = getelementptr i8, i8 addrspace(1)* %a, i64 64
+  %tmp127 = bitcast i8 addrspace(1)* %tmp126 to float addrspace(1)*
+  store float %tmp49, float addrspace(1)* %tmp127, align 4
+  %tmp128 = getelementptr i8, i8 addrspace(1)* %a, i64 68
+  %tmp129 = bitcast i8 addrspace(1)* %tmp128 to float addrspace(1)*
+  store float %tmp52, float addrspace(1)* %tmp129, align 4
+  %tmp130 = getelementptr i8, i8 addrspace(1)* %a, i64 72
+  %tmp131 = bitcast i8 addrspace(1)* %tmp130 to float addrspace(1)*
+  store float %tmp55, float addrspace(1)* %tmp131, align 4
+  %tmp132 = getelementptr i8, i8 addrspace(1)* %a, i64 76
+  %tmp133 = bitcast i8 addrspace(1)* %tmp132 to float addrspace(1)*
+  store float %tmp58, float addrspace(1)* %tmp133, align 4
+  %tmp134 = getelementptr i8, i8 addrspace(1)* %a, i64 80
+  %tmp135 = bitcast i8 addrspace(1)* %tmp134 to float addrspace(1)*
+  store float %tmp61, float addrspace(1)* %tmp135, align 4
+  %tmp136 = getelementptr i8, i8 addrspace(1)* %a, i64 84
+  %tmp137 = bitcast i8 addrspace(1)* %tmp136 to float addrspace(1)*
+  store float %tmp64, float addrspace(1)* %tmp137, align 4
+  %tmp138 = getelementptr i8, i8 addrspace(1)* %a, i64 88
+  %tmp139 = bitcast i8 addrspace(1)* %tmp138 to float addrspace(1)*
+  store float %tmp67, float addrspace(1)* %tmp139, align 4
+  %tmp140 = getelementptr i8, i8 addrspace(1)* %a, i64 92
+  %tmp141 = bitcast i8 addrspace(1)* %tmp140 to float addrspace(1)*
+  store float %tmp70, float addrspace(1)* %tmp141, align 4
+  %tmp142 = getelementptr i8, i8 addrspace(1)* %a, i64 96
+  %tmp143 = bitcast i8 addrspace(1)* %tmp142 to float addrspace(1)*
+  store float %tmp73, float addrspace(1)* %tmp143, align 4
+  %tmp144 = getelementptr i8, i8 addrspace(1)* %a, i64 100
+  %tmp145 = bitcast i8 addrspace(1)* %tmp144 to float addrspace(1)*
+  store float %tmp76, float addrspace(1)* %tmp145, align 4
+  %tmp146 = getelementptr i8, i8 addrspace(1)* %a, i64 104
+  %tmp147 = bitcast i8 addrspace(1)* %tmp146 to float addrspace(1)*
+  store float %tmp79, float addrspace(1)* %tmp147, align 4
+  %tmp148 = getelementptr i8, i8 addrspace(1)* %a, i64 108
+  %tmp149 = bitcast i8 addrspace(1)* %tmp148 to float addrspace(1)*
+  store float %tmp82, float addrspace(1)* %tmp149, align 4
+  %tmp150 = getelementptr i8, i8 addrspace(1)* %a, i64 112
+  %tmp151 = bitcast i8 addrspace(1)* %tmp150 to float addrspace(1)*
+  store float %tmp85, float addrspace(1)* %tmp151, align 4
+  %tmp152 = getelementptr i8, i8 addrspace(1)* %a, i64 116
+  %tmp153 = bitcast i8 addrspace(1)* %tmp152 to float addrspace(1)*
+  store float %tmp88, float addrspace(1)* %tmp153, align 4
+  %tmp154 = getelementptr i8, i8 addrspace(1)* %a, i64 120
+  %tmp155 = bitcast i8 addrspace(1)* %tmp154 to float addrspace(1)*
+  store float %tmp91, float addrspace(1)* %tmp155, align 4
+  %tmp156 = getelementptr i8, i8 addrspace(1)* %a, i64 124
+  %tmp157 = bitcast i8 addrspace(1)* %tmp156 to float addrspace(1)*
+  store float %tmp94, float addrspace(1)* %tmp157, align 4
+  %tmp158 = getelementptr i8, i8 addrspace(1)* %b, i64 128
+  %tmp159 = bitcast i8 addrspace(1)* %tmp158 to float addrspace(1)*
+  %tmp160 = load float, float addrspace(1)* %tmp159, align 4
+  %tmp161 = getelementptr i8, i8 addrspace(1)* %b, i64 132
+  %tmp162 = bitcast i8 addrspace(1)* %tmp161 to float addrspace(1)*
+  %tmp163 = load float, float addrspace(1)* %tmp162, align 4
+  %tmp164 = getelementptr i8, i8 addrspace(1)* %b, i64 136
+  %tmp165 = bitcast i8 addrspace(1)* %tmp164 to float addrspace(1)*
+  %tmp166 = load float, float addrspace(1)* %tmp165, align 4
+  %tmp167 = getelementptr i8, i8 addrspace(1)* %b, i64 140
+  %tmp168 = bitcast i8 addrspace(1)* %tmp167 to float addrspace(1)*
+  %tmp169 = load float, float addrspace(1)* %tmp168, align 4
+  %tmp170 = getelementptr i8, i8 addrspace(1)* %b, i64 144
+  %tmp171 = bitcast i8 addrspace(1)* %tmp170 to float addrspace(1)*
+  %tmp172 = load float, float addrspace(1)* %tmp171, align 4
+  %tmp173 = getelementptr i8, i8 addrspace(1)* %b, i64 148
+  %tmp174 = bitcast i8 addrspace(1)* %tmp173 to float addrspace(1)*
+  %tmp175 = load float, float addrspace(1)* %tmp174, align 4
+  %tmp176 = getelementptr i8, i8 addrspace(1)* %b, i64 152
+  %tmp177 = bitcast i8 addrspace(1)* %tmp176 to float addrspace(1)*
+  %tmp178 = load float, float addrspace(1)* %tmp177, align 4
+  %tmp179 = getelementptr i8, i8 addrspace(1)* %b, i64 156
+  %tmp180 = bitcast i8 addrspace(1)* %tmp179 to float addrspace(1)*
+  %tmp181 = load float, float addrspace(1)* %tmp180, align 4
+  %tmp182 = getelementptr i8, i8 addrspace(1)* %b, i64 160
+  %tmp183 = bitcast i8 addrspace(1)* %tmp182 to float addrspace(1)*
+  %tmp184 = load float, float addrspace(1)* %tmp183, align 4
+  %tmp185 = getelementptr i8, i8 addrspace(1)* %b, i64 164
+  %tmp186 = bitcast i8 addrspace(1)* %tmp185 to float addrspace(1)*
+  %tmp187 = load float, float addrspace(1)* %tmp186, align 4
+  %tmp188 = getelementptr i8, i8 addrspace(1)* %b, i64 168
+  %tmp189 = bitcast i8 addrspace(1)* %tmp188 to float addrspace(1)*
+  %tmp190 = load float, float addrspace(1)* %tmp189, align 4
+  %tmp191 = getelementptr i8, i8 addrspace(1)* %b, i64 172
+  %tmp192 = bitcast i8 addrspace(1)* %tmp191 to float addrspace(1)*
+  %tmp193 = load float, float addrspace(1)* %tmp192, align 4
+  %tmp194 = getelementptr i8, i8 addrspace(1)* %b, i64 176
+  %tmp195 = bitcast i8 addrspace(1)* %tmp194 to float addrspace(1)*
+  %tmp196 = load float, float addrspace(1)* %tmp195, align 4
+  %tmp197 = getelementptr i8, i8 addrspace(1)* %b, i64 180
+  %tmp198 = bitcast i8 addrspace(1)* %tmp197 to float addrspace(1)*
+  %tmp199 = load float, float addrspace(1)* %tmp198, align 4
+  %tmp200 = getelementptr i8, i8 addrspace(1)* %b, i64 184
+  %tmp201 = bitcast i8 addrspace(1)* %tmp200 to float addrspace(1)*
+  %tmp202 = load float, float addrspace(1)* %tmp201, align 4
+  %tmp203 = getelementptr i8, i8 addrspace(1)* %b, i64 188
+  %tmp204 = bitcast i8 addrspace(1)* %tmp203 to float addrspace(1)*
+  %tmp205 = load float, float addrspace(1)* %tmp204, align 4
+  %tmp206 = getelementptr i8, i8 addrspace(1)* %b, i64 192
+  %tmp207 = bitcast i8 addrspace(1)* %tmp206 to half addrspace(1)*
+  %tmp208 = load half, half addrspace(1)* %tmp207, align 2
+  %tmp209 = getelementptr i8, i8 addrspace(1)* %a, i64 128
+  %tmp210 = bitcast i8 addrspace(1)* %tmp209 to float addrspace(1)*
+  store float %tmp160, float addrspace(1)* %tmp210, align 4
+  %tmp211 = getelementptr i8, i8 addrspace(1)* %a, i64 132
+  %tmp212 = bitcast i8 addrspace(1)* %tmp211 to float addrspace(1)*
+  store float %tmp163, float addrspace(1)* %tmp212, align 4
+  %tmp213 = getelementptr i8, i8 addrspace(1)* %a, i64 136
+  %tmp214 = bitcast i8 addrspace(1)* %tmp213 to float addrspace(1)*
+  store float %tmp166, float addrspace(1)* %tmp214, align 4
+  %tmp215 = getelementptr i8, i8 addrspace(1)* %a, i64 140
+  %tmp216 = bitcast i8 addrspace(1)* %tmp215 to float addrspace(1)*
+  store float %tmp169, float addrspace(1)* %tmp216, align 4
+  %tmp217 = getelementptr i8, i8 addrspace(1)* %a, i64 144
+  %tmp218 = bitcast i8 addrspace(1)* %tmp217 to float addrspace(1)*
+  store float %tmp172, float addrspace(1)* %tmp218, align 4
+  %tmp219 = getelementptr i8, i8 addrspace(1)* %a, i64 148
+  %tmp220 = bitcast i8 addrspace(1)* %tmp219 to float addrspace(1)*
+  store float %tmp175, float addrspace(1)* %tmp220, align 4
+  %tmp221 = getelementptr i8, i8 addrspace(1)* %a, i64 152
+  %tmp222 = bitcast i8 addrspace(1)* %tmp221 to float addrspace(1)*
+  store float %tmp178, float addrspace(1)* %tmp222, align 4
+  %tmp223 = getelementptr i8, i8 addrspace(1)* %a, i64 156
+  %tmp224 = bitcast i8 addrspace(1)* %tmp223 to float addrspace(1)*
+  store float %tmp181, float addrspace(1)* %tmp224, align 4
+  %tmp225 = getelementptr i8, i8 addrspace(1)* %a, i64 160
+  %tmp226 = bitcast i8 addrspace(1)* %tmp225 to float addrspace(1)*
+  store float %tmp184, float addrspace(1)* %tmp226, align 4
+  %tmp227 = getelementptr i8, i8 addrspace(1)* %a, i64 164
+  %tmp228 = bitcast i8 addrspace(1)* %tmp227 to float addrspace(1)*
+  store float %tmp187, float addrspace(1)* %tmp228, align 4
+  %tmp229 = getelementptr i8, i8 addrspace(1)* %a, i64 168
+  %tmp230 = bitcast i8 addrspace(1)* %tmp229 to float addrspace(1)*
+  store float %tmp190, float addrspace(1)* %tmp230, align 4
+  %tmp231 = getelementptr i8, i8 addrspace(1)* %a, i64 172
+  %tmp232 = bitcast i8 addrspace(1)* %tmp231 to float addrspace(1)*
+  store float %tmp193, float addrspace(1)* %tmp232, align 4
+  %tmp233 = getelementptr i8, i8 addrspace(1)* %a, i64 176
+  %tmp234 = bitcast i8 addrspace(1)* %tmp233 to float addrspace(1)*
+  store float %tmp196, float addrspace(1)* %tmp234, align 4
+  %tmp235 = getelementptr i8, i8 addrspace(1)* %a, i64 180
+  %tmp236 = bitcast i8 addrspace(1)* %tmp235 to float addrspace(1)*
+  store float %tmp199, float addrspace(1)* %tmp236, align 4
+  %tmp237 = getelementptr i8, i8 addrspace(1)* %a, i64 184
+  %tmp238 = bitcast i8 addrspace(1)* %tmp237 to float addrspace(1)*
+  store float %tmp202, float addrspace(1)* %tmp238, align 4
+  %tmp239 = getelementptr i8, i8 addrspace(1)* %a, i64 188
+  %tmp240 = bitcast i8 addrspace(1)* %tmp239 to float addrspace(1)*
+  store float %tmp205, float addrspace(1)* %tmp240, align 4
+  %tmp241 = getelementptr i8, i8 addrspace(1)* %a, i64 192
+  %tmp242 = bitcast i8 addrspace(1)* %tmp241 to half addrspace(1)*
+  store half %tmp208, half addrspace(1)* %tmp242, align 2
+  ret void
+}
+
+attributes #0 = { argmemonly nounwind }