[LV] Enable considering higher VFs when data extend ops are present in the loop

LV currently limits the VF based on the widest type in the loop.  This
might not be beneficial for loops with data extend ops in them. In some
cases, this strategy has been found to inhibit considering higher VFs
even though a higher VF might be profitable.

This patch aims to relax this constraint to enable higher VFs and lets
the cost model take the decision of considering whether a  particular VF
is beneficial or not.

Author: sushgokh

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -4123,6 +4123,15 @@ ElementCount LoopVectorizationCostModel::getMaximizedVFForTarget(
   auto MaxVectorElementCount = ElementCount::get(
       llvm::bit_floor(WidestRegister.getKnownMinValue() / WidestType),
       ComputeScalableMaxVF);
+
+  // For loops with extend operations e.g. zext, sext etc., limiting the max VF
+  // based on widest type inhibits considering higher VFs even though
+  // vectorizing with higher VF might be profitable. In such cases, we should
+  // limit the max VF based on smallest type and the decision whether a
+  // particular VF is beneficial or not be left to cost model.
+  if (WidestType != SmallestType)
+    MaximizeBandwidth = true;
+
   MaxVectorElementCount = MinVF(MaxVectorElementCount, MaxSafeVF);
   LLVM_DEBUG(dbgs() << "LV: The Widest register safe to use is: "
                     << (MaxVectorElementCount * WidestType) << " bits.\n");

llvm/test/CodeGen/WebAssembly/int-mac-reduction-loops.ll

@@ -1,27 +1,20 @@
 ; RUN: opt -mattr=+simd128 -passes=loop-vectorize %s | llc -mtriple=wasm32 -mattr=+simd128 -verify-machineinstrs -o - | FileCheck %s
-; RUN: opt -mattr=+simd128 -passes=loop-vectorize -vectorizer-maximize-bandwidth %s | llc -mtriple=wasm32 -mattr=+simd128 -verify-machineinstrs -o - | FileCheck %s --check-prefix=MAX-BANDWIDTH
+; RUN: opt -mattr=+simd128 -passes=loop-vectorize -vectorizer-maximize-bandwidth %s | llc -mtriple=wasm32 -mattr=+simd128 -verify-machineinstrs -o - | FileCheck %s
 
 target triple = "wasm32"
 
 define hidden i32 @i32_mac_s8(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i32_mac_s8:
-; CHECK:    v128.load32_zero 0:p2align=0
-; CHECK:    i16x8.extend_low_i8x16_s
-; CHECK:    v128.load32_zero 0:p2align=0
-; CHECK:    i16x8.extend_low_i8x16_s
-; CHECK:    i32x4.extmul_low_i16x8_s
-; CHECK:    i32x4.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i16x8.extend_low_i8x16_s
-; MAX-BANDWIDTH: i32x4.dot_i16x8_s
-; MAX-BANDWIDTH: i16x8.extend_high_i8x16_s
-; MAX-BANDWIDTH: i16x8.extend_high_i8x16_s
-; MAX-BANDWIDTH: i32x4.dot_i16x8_s
-; MAX-BANDWIDTH: i32x4.add
-; MAX-BANDWIDTH: i32x4.add
+; CHECK: v128.load
+; CHECK: i16x8.extend_low_i8x16_s
+; CHECK: v128.load
+; CHECK: i16x8.extend_low_i8x16_s
+; CHECK: i32x4.dot_i16x8_s
+; CHECK: i16x8.extend_high_i8x16_s
+; CHECK: i16x8.extend_high_i8x16_s
+; CHECK: i32x4.dot_i16x8_s
+; CHECK: i32x4.add
+; CHECK: i32x4.add
 
 entry:
   %cmp7.not = icmp eq i32 %N, 0
@@ -49,14 +42,9 @@ for.body:                                         ; preds = %entry, %for.body
 
 define hidden i32 @i32_mac_s16(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i32_mac_s16:
-; CHECK:    i32x4.load16x4_s 0:p2align=1
-; CHECK:    i32x4.load16x4_s 0:p2align=1
-; CHECK:    i32x4.mul
-; CHECK:    i32x4.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i32x4.dot_i16x8_s
+; CHECK: v128.load
+; CHECK: v128.load
+; CHECK: i32x4.dot_i16x8_s
 
 entry:
   %cmp7.not = icmp eq i32 %N, 0
@@ -84,37 +72,30 @@ for.body:                                         ; preds = %entry, %for.body
 
 define hidden i64 @i64_mac_s16(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i64_mac_s16:
-; CHECK:    v128.load32_zero 0:p2align=1
-; CHECK:    i32x4.extend_low_i16x8_s
-; CHECK:    v128.load32_zero 0:p2align=1
-; CHECK:    i32x4.extend_low_i16x8_s
-; CHECK:    i64x2.extmul_low_i32x4_s
-; CHECK:    i64x2.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i8x16.shuffle	12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i8x16.shuffle	12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
-; MAX-BANDWIDTH: i64x2.add
-; MAX-BANDWIDTH: i8x16.shuffle	8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: i8x16.shuffle	8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
-; MAX-BANDWIDTH: i64x2.add
-; MAX-BANDWIDTH: i8x16.shuffle	4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: i8x16.shuffle	4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
-; MAX-BANDWIDTH: i64x2.add
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_s
-; MAX-BANDWIDTH: i64x2.add
+; CHECK: v128.load
+; CHECK: i8x16.shuffle	12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: v128.load
+; CHECK: i8x16.shuffle	12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i64x2.extmul_low_i32x4_s
+; CHECK: i64x2.add
+; CHECK: i8x16.shuffle	8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i8x16.shuffle	8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i64x2.extmul_low_i32x4_s
+; CHECK: i64x2.add
+; CHECK: i8x16.shuffle	4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i8x16.shuffle	4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i64x2.extmul_low_i32x4_s
+; CHECK: i64x2.add
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i64x2.extmul_low_i32x4_s
+; CHECK: i64x2.add
 
 entry:
   %cmp7.not = icmp eq i32 %N, 0
@@ -142,19 +123,13 @@ for.body:                                         ; preds = %entry, %for.body
 
 define hidden i64 @i64_mac_s32(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i64_mac_s32:
-; CHECK:    v128.load64_zero 0:p2align=2
-; CHECK:    v128.load64_zero 0:p2align=2
-; CHECK:    i32x4.mul
-; CHECK:    i64x2.extend_low_i32x4_s
-; CHECK:    i64x2.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i32x4.mul
-; MAX-BANDWIDTH: i64x2.extend_high_i32x4_s
-; MAX-BANDWIDTH: i64x2.add
-; MAX-BANDWIDTH: i64x2.extend_low_i32x4_s
-; MAX-BANDWIDTH: i64x2.add
+; CHECK: v128.load
+; CHECK: v128.load
+; CHECK: i32x4.mul
+; CHECK: i64x2.extend_high_i32x4_s
+; CHECK: i64x2.add
+; CHECK: i64x2.extend_low_i32x4_s
+; CHECK: i64x2.add
 
 entry:
   %cmp6.not = icmp eq i32 %N, 0
@@ -181,25 +156,18 @@ for.body:                                         ; preds = %entry, %for.body
 
 define hidden i32 @i32_mac_u8(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i32_mac_u8:
-; CHECK:    v128.load32_zero 0:p2align=0
-; CHECK:    i16x8.extend_low_i8x16_u
-; CHECK:    v128.load32_zero 0:p2align=0
-; CHECK:    i16x8.extend_low_i8x16_u
-; CHECK:    i32x4.extmul_low_i16x8_u
-; CHECK:    i32x4.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i16x8.extmul_low_i8x16_u
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i32x4.extend_high_i16x8_u
-; MAX-BANDWIDTH: i32x4.add
-; MAX-BANDWIDTH: i16x8.extmul_high_i8x16_u
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i32x4.extend_high_i16x8_u
-; MAX-BANDWIDTH: i32x4.add
-; MAX-BANDWIDTH: i32x4.add
-; MAX-BANDWIDTH: i32x4.add
+; CHECK: v128.load
+; CHECK: v128.load
+; CHECK: i16x8.extmul_low_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.extend_high_i16x8_u
+; CHECK: i32x4.add
+; CHECK: i16x8.extmul_high_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.extend_high_i16x8_u
+; CHECK: i32x4.add
+; CHECK: i32x4.add
+; CHECK: i32x4.add
 
 entry:
   %cmp7.not = icmp eq i32 %N, 0
@@ -227,17 +195,12 @@ for.body:                                         ; preds = %entry, %for.body
 
 define hidden i32 @i32_mac_u16(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i32_mac_u16:
-; CHECK:    i32x4.load16x4_u 0:p2align=1
-; CHECK:    i32x4.load16x4_u 0:p2align=1
-; CHECK:    i32x4.mul
-; CHECK:    i32x4.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i32x4.extmul_low_i16x8_u
-; MAX-BANDWIDTH: i32x4.extmul_high_i16x8_u
-; MAX-BANDWIDTH: i32x4.add
-; MAX-BANDWIDTH: i32x4.add
+; CHECK: v128.load
+; CHECK: v128.load
+; CHECK: i32x4.extmul_low_i16x8_u
+; CHECK: i32x4.extmul_high_i16x8_u
+; CHECK: i32x4.add
+; CHECK: i32x4.add
 
 entry:
   %cmp7.not = icmp eq i32 %N, 0
@@ -265,21 +228,16 @@ for.body:                                         ; preds = %entry, %for.body
 
 define hidden i32 @i32_mac_u16_s16(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i32_mac_u16_s16:
-; CHECK:    i32x4.load16x4_s 0:p2align=1
-; CHECK:    i32x4.load16x4_u 0:p2align=1
-; CHECK:    i32x4.mul
-; CHECK:    i32x4.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i32x4.extend_high_i16x8_s
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i32x4.extend_high_i16x8_u
-; MAX-BANDWIDTH: i32x4.mul
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_s
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i32x4.mul
-; MAX-BANDWIDTH: i32x4.add
-; MAX-BANDWIDTH: i32x4.add
+; CHECK: v128.load
+; CHECK: i32x4.extend_high_i16x8_s
+; CHECK: v128.load
+; CHECK: i32x4.extend_high_i16x8_u
+; CHECK: i32x4.mul
+; CHECK: i32x4.extend_low_i16x8_s
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.mul
+; CHECK: i32x4.add
+; CHECK: i32x4.add
 
 entry:
   %cmp7.not = icmp eq i32 %N, 0
@@ -307,37 +265,30 @@ for.body:                                         ; preds = %entry, %for.body
 
 define hidden i64 @i64_mac_u16(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i64_mac_u16:
-; CHECK:    v128.load32_zero 0:p2align=1
-; CHECK:    i32x4.extend_low_i16x8_u
-; CHECK:    v128.load32_zero 0:p2align=1
-; CHECK:    i32x4.extend_low_i16x8_u
-; CHECK:    i64x2.extmul_low_i32x4_u
-; CHECK:    i64x2.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i8x16.shuffle	12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i8x16.shuffle	12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
-; MAX-BANDWIDTH: i64x2.add
-; MAX-BANDWIDTH: i8x16.shuffle	8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i8x16.shuffle	8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
-; MAX-BANDWIDTH: i64x2.add
-; MAX-BANDWIDTH: i8x16.shuffle	4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i8x16.shuffle	4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
-; MAX-BANDWIDTH: i64x2.add
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i32x4.extend_low_i16x8_u
-; MAX-BANDWIDTH: i64x2.extmul_low_i32x4_u
-; MAX-BANDWIDTH: i64x2.add
+; CHECK: v128.load
+; CHECK: i8x16.shuffle	12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: v128.load
+; CHECK: i8x16.shuffle	12, 13, 14, 15, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i64x2.extmul_low_i32x4_u
+; CHECK: i64x2.add
+; CHECK: i8x16.shuffle	8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i8x16.shuffle	8, 9, 10, 11, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i64x2.extmul_low_i32x4_u
+; CHECK: i64x2.add
+; CHECK: i8x16.shuffle	4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i8x16.shuffle	4, 5, 6, 7, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i64x2.extmul_low_i32x4_u
+; CHECK: i64x2.add
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i64x2.extmul_low_i32x4_u
+; CHECK: i64x2.add
 
 entry:
   %cmp8.not = icmp eq i32 %N, 0
@@ -365,19 +316,13 @@ for.body:                                         ; preds = %entry, %for.body
 
 define hidden i64 @i64_mac_u32(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %N) {
 ; CHECK-LABEL: i64_mac_u32:
-; CHECK:    v128.load64_zero 0:p2align=2
-; CHECK:    v128.load64_zero 0:p2align=2
-; CHECK:    i32x4.mul
-; CHECK:    i64x2.extend_low_i32x4_u
-; CHECK:    i64x2.add
-
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: v128.load
-; MAX-BANDWIDTH: i32x4.mul
-; MAX-BANDWIDTH: i64x2.extend_high_i32x4_u
-; MAX-BANDWIDTH: i64x2.add
-; MAX-BANDWIDTH: i64x2.extend_low_i32x4_u
-; MAX-BANDWIDTH: i64x2.add
+; CHECK: v128.load
+; CHECK: v128.load
+; CHECK: i32x4.mul
+; CHECK: i64x2.extend_high_i32x4_u
+; CHECK: i64x2.add
+; CHECK: i64x2.extend_low_i32x4_u
+; CHECK: i64x2.add
 
 entry:
   %cmp6.not = icmp eq i32 %N, 0

llvm/test/CodeGen/WebAssembly/interleave.ll

@@ -15,13 +15,37 @@ target datalayout = "e-m:e-p:32:32-p10:8:8-p20:8:8-i64:64-i128:128-n32:64-S128-n
 ; Function Attrs: nofree norecurse nosync nounwind memory(argmem: readwrite)
 define hidden void @accumulate8x2(ptr dead_on_unwind noalias writable sret(%struct.Output32x2) align 4 captures(none) %0, ptr noundef readonly captures(none) %1, i32 noundef %2) local_unnamed_addr #0 {
 ; CHECK-LABEL: accumulate8x2:
-; CHECK: loop
-; CHECK: v128.load64_zero
-; CHECK: i8x16.shuffle 1, 3, 5, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; CHECK: v128.load       16:p2align=0                
+; CHECK: i8x16.shuffle   9, 11, 13, 15, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
 ; CHECK: i16x8.extend_low_i8x16_u
 ; CHECK: i32x4.extend_low_i16x8_u
-; CHECK: i32x4.add
-; CHECK: i8x16.shuffle 0, 2, 4, 6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; CHECK: i32x4.add                                
+; CHECK: i8x16.shuffle   1, 3, 5, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; CHECK: i16x8.extend_low_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.add                        
+; CHECK: v128.load       0:p2align=0                
+; CHECK: i8x16.shuffle   9, 11, 13, 15, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; CHECK: i16x8.extend_low_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.add                                
+; CHECK: i8x16.shuffle   1, 3, 5, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; CHECK: i16x8.extend_low_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.add                                
+; CHECK: i8x16.shuffle   8, 10, 12, 14, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; CHECK: i16x8.extend_low_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.add                                
+; CHECK: i8x16.shuffle   0, 2, 4, 6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; CHECK: i16x8.extend_low_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.add                                
+; CHECK: i8x16.shuffle   8, 10, 12, 14, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+; CHECK: i16x8.extend_low_i8x16_u
+; CHECK: i32x4.extend_low_i16x8_u
+; CHECK: i32x4.add                                
+; CHECK: i8x16.shuffle   0, 2, 4, 6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
 ; CHECK: i16x8.extend_low_i8x16_u
 ; CHECK: i32x4.extend_low_i16x8_u
 ; CHECK: i32x4.add