diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
index 794db887bd073..b733312d855bf 100644
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
@@ -394,6 +394,17 @@ WebAssemblyTargetLowering::WebAssemblyTargetLowering(
   // is equivalent to a simple branch. This reduces code size for wasm, and we
   // defer possible jump table optimizations to the VM.
   setMinimumJumpTableEntries(2);
+
+  // Align bulk memory usage when optimizing for size or otherwise. As well as
+  // reducing code size, prefering high-level primitives can make it easier for
+  // runtimes to make optimisations, especially when explicit bounds checking is
+  // employed.
+  if (Subtarget->hasBulkMemory()) {
+    MaxStoresPerMemset = MaxStoresPerMemsetOptSize;
+    MaxStoresPerMemcpy = MaxStoresPerMemcpyOptSize;
+    MaxStoresPerMemmove = MaxStoresPerMemmoveOptSize;
+    MaxLoadsPerMemcmp = MaxLoadsPerMemcmpOptSize;
+  }
 }
 
 MVT WebAssemblyTargetLowering::getPointerTy(const DataLayout &DL,
diff --git a/llvm/test/CodeGen/WebAssembly/bulk-memory.ll b/llvm/test/CodeGen/WebAssembly/bulk-memory.ll
index ae170d757a305..d154c44856f8b 100644
--- a/llvm/test/CodeGen/WebAssembly/bulk-memory.ll
+++ b/llvm/test/CodeGen/WebAssembly/bulk-memory.ll
@@ -29,6 +29,27 @@ define void @memcpy_i8(ptr %dest, ptr %src, i8 zeroext %len) {
   ret void
 }
 
+; CHECK-LABEL: memcpy_i8_fixed_32
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+define void @memcpy_i8_fixed_32(ptr %dest, ptr %src) {
+  call void @llvm.memcpy.p0.p0.i8(ptr %dest, ptr %src, i8 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memcpy_i8_fixed_36
+; BULK-MEM: memory.copy
+define void @memcpy_i8_fixed_36(ptr %dest, ptr %src) {
+  call void @llvm.memcpy.p0.p0.i8(ptr %dest, ptr %src, i8 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memmove_i8:
 ; NO-BULK-MEM-NOT: memory.copy
 ; BULK-MEM-NEXT: .functype memmove_i8 (i32, i32, i32) -> ()
@@ -44,6 +65,27 @@ define void @memmove_i8(ptr %dest, ptr %src, i8 zeroext %len) {
   ret void
 }
 
+; CHECK-LABEL: memmove_i8_fixed_32
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+define void @memmove_i8_fixed_32(ptr %dest, ptr %src) {
+  call void @llvm.memmove.p0.p0.i8(ptr %dest, ptr %src, i8 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memmove_i8_fixed_36
+; BULK-MEM: memory.copy
+define void @memmove_i8_fixed_36(ptr %dest, ptr %src) {
+  call void @llvm.memmove.p0.p0.i8(ptr %dest, ptr %src, i8 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memset_i8:
 ; NO-BULK-MEM-NOT: memory.fill
 ; BULK-MEM-NEXT: .functype memset_i8 (i32, i32, i32) -> ()
@@ -59,6 +101,23 @@ define void @memset_i8(ptr %dest, i8 %val, i8 zeroext %len) {
   ret void
 }
 
+; CHECK-LABEL: memset_i8_fixed_32
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+define void @memset_i8_fixed_32(ptr %dest, i8 %val) {
+  call void @llvm.memset.p0.i8(ptr %dest, i8 %val, i8 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memset_i8_fixed_36
+; BULK-MEM: memory.fill
+define void @memset_i8_fixed_36(ptr %dest, i8 %val) {
+  call void @llvm.memset.p0.i8(ptr %dest, i8 %val, i8 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memcpy_i32:
 ; NO-BULK-MEM-NOT: memory.copy
 ; BULK-MEM-NEXT: .functype memcpy_i32 (i32, i32, i32) -> ()
@@ -74,6 +133,27 @@ define void @memcpy_i32(ptr %dest, ptr %src, i32 %len) {
   ret void
 }
 
+; CHECK-LABEL: memcpy_i32_fixed_32
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+define void @memcpy_i32_fixed_32(ptr %dest, ptr %src) {
+  call void @llvm.memcpy.p0.p0.i32(ptr %dest, ptr %src, i32 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memcpy_i32_fixed_36
+; BULK-MEM: memory.copy
+define void @memcpy_i32_fixed_36(ptr %dest, ptr %src) {
+  call void @llvm.memcpy.p0.p0.i32(ptr %dest, ptr %src, i32 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memmove_i32:
 ; NO-BULK-MEM-NOT: memory.copy
 ; BULK-MEM-NEXT: .functype memmove_i32 (i32, i32, i32) -> ()
@@ -89,6 +169,27 @@ define void @memmove_i32(ptr %dest, ptr %src, i32 %len) {
   ret void
 }
 
+; CHECK-LABEL: memmove_i32_fixed_32
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+define void @memmove_i32_fixed_32(ptr %dest, ptr %src) {
+  call void @llvm.memmove.p0.p0.i32(ptr %dest, ptr %src, i32 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memmove_i32_fixed_36
+; BULK-MEM: memory.copy
+define void @memmove_i32_fixed_36(ptr %dest, ptr %src) {
+  call void @llvm.memmove.p0.p0.i32(ptr %dest, ptr %src, i32 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memset_i32:
 ; NO-BULK-MEM-NOT: memory.fill
 ; BULK-MEM-NEXT: .functype memset_i32 (i32, i32, i32) -> ()
@@ -104,6 +205,23 @@ define void @memset_i32(ptr %dest, i8 %val, i32 %len) {
   ret void
 }
 
+; CHECK-LABEL: memset_i32_fixed_32
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+define void @memset_i32_fixed_32(ptr %dest, i8 %val) {
+  call void @llvm.memset.p0.i32(ptr %dest, i8 %val, i32 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memset_i32_fixed_36
+; BULK-MEM: memory.fill
+define void @memset_i32_fixed_36(ptr %dest, i8 %val) {
+  call void @llvm.memset.p0.i32(ptr %dest, i8 %val, i32 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memcpy_1:
 ; CHECK-NEXT: .functype memcpy_1 (i32, i32) -> ()
 ; CHECK-NEXT: i32.load8_u $push[[L0:[0-9]+]]=, 0($1)
diff --git a/llvm/test/CodeGen/WebAssembly/bulk-memory64.ll b/llvm/test/CodeGen/WebAssembly/bulk-memory64.ll
index 0cf8493a995f9..910e7ac5c96c4 100644
--- a/llvm/test/CodeGen/WebAssembly/bulk-memory64.ll
+++ b/llvm/test/CodeGen/WebAssembly/bulk-memory64.ll
@@ -31,6 +31,27 @@ define void @memcpy_i8(ptr %dest, ptr %src, i8 zeroext %len) {
   ret void
 }
 
+; CHECK-LABEL: memcpy_i8_fixed_32
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+define void @memcpy_i8_fixed_32(ptr %dest, ptr %src) {
+  call void @llvm.memcpy.p0.p0.i8(ptr %dest, ptr %src, i8 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memcpy_i8_fixed_36
+; BULK-MEM: memory.copy
+define void @memcpy_i8_fixed_36(ptr %dest, ptr %src) {
+  call void @llvm.memcpy.p0.p0.i8(ptr %dest, ptr %src, i8 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memmove_i8:
 ; NO-BULK-MEM-NOT: memory.copy
 ; BULK-MEM-NEXT: .functype memmove_i8 (i64, i64, i32) -> ()
@@ -48,6 +69,27 @@ define void @memmove_i8(ptr %dest, ptr %src, i8 zeroext %len) {
   ret void
 }
 
+; CHECK-LABEL: memmove_i8_fixed_32
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+define void @memmove_i8_fixed_32(ptr %dest, ptr %src) {
+  call void @llvm.memmove.p0.p0.i8(ptr %dest, ptr %src, i8 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memmove_i8_fixed_36
+; BULK-MEM: memory.copy
+define void @memmove_i8_fixed_36(ptr %dest, ptr %src) {
+  call void @llvm.memmove.p0.p0.i8(ptr %dest, ptr %src, i8 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memset_i8:
 ; NO-BULK-MEM-NOT: memory.fill
 ; BULK-MEM-NEXT: .functype memset_i8 (i64, i32, i32) -> ()
@@ -65,6 +107,23 @@ define void @memset_i8(ptr %dest, i8 %val, i8 zeroext %len) {
   ret void
 }
 
+; CHECK-LABEL: memset_i8_fixed_32
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+define void @memset_i8_fixed_32(ptr %dest, i8 %val) {
+  call void @llvm.memset.p0.i8(ptr %dest, i8 %val, i8 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memset_i8_fixed_36
+; BULK-MEM: memory.fill
+define void @memset_i8_fixed_36(ptr %dest, i8 %val) {
+  call void @llvm.memset.p0.i8(ptr %dest, i8 %val, i8 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memcpy_i32:
 ; NO-BULK-MEM-NOT: memory.copy
 ; BULK-MEM-NEXT: .functype memcpy_i32 (i64, i64, i64) -> ()
@@ -80,6 +139,27 @@ define void @memcpy_i32(ptr %dest, ptr %src, i64 %len) {
   ret void
 }
 
+; CHECK-LABEL: memcpy_i32_fixed_32
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.load
+; CHECK: i64.store
+define void @memcpy_i32_fixed_32(ptr %dest, ptr %src) {
+  call void @llvm.memcpy.p0.p0.i32(ptr %dest, ptr %src, i32 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memcpy_i32_fixed_36
+; BULK-MEM: memory.copy
+define void @memcpy_i32_fixed_36(ptr %dest, ptr %src) {
+  call void @llvm.memcpy.p0.p0.i32(ptr %dest, ptr %src, i32 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memmove_i32:
 ; NO-BULK-MEM-NOT: memory.copy
 ; BULK-MEM-NEXT: .functype memmove_i32 (i64, i64, i64) -> ()
@@ -95,6 +175,27 @@ define void @memmove_i32(ptr %dest, ptr %src, i64 %len) {
   ret void
 }
 
+; CHECK-LABEL: memmove_i32_fixed_32
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.load
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+define void @memmove_i32_fixed_32(ptr %dest, ptr %src) {
+  call void @llvm.memmove.p0.p0.i32(ptr %dest, ptr %src, i32 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memmove_i32_fixed_36
+; BULK-MEM: memory.copy
+define void @memmove_i32_fixed_36(ptr %dest, ptr %src) {
+  call void @llvm.memmove.p0.p0.i32(ptr %dest, ptr %src, i32 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memset_i32:
 ; NO-BULK-MEM-NOT: memory.fill
 ; BULK-MEM-NEXT: .functype memset_i32 (i64, i32, i64) -> ()
@@ -110,6 +211,23 @@ define void @memset_i32(ptr %dest, i8 %val, i64 %len) {
   ret void
 }
 
+; CHECK-LABEL: memset_i32_fixed_32
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+; CHECK: i64.store
+define void @memset_i32_fixed_32(ptr %dest, i8 %val) {
+  call void @llvm.memset.p0.i32(ptr %dest, i8 %val, i32 32, i1 0)
+  ret void
+}
+
+; CHECK-LABEL: memset_i32_fixed_36
+; BULK-MEM: memory.fill
+define void @memset_i32_fixed_36(ptr %dest, i8 %val) {
+  call void @llvm.memset.p0.i32(ptr %dest, i8 %val, i32 36, i1 0)
+  ret void
+}
+
 ; CHECK-LABEL: memcpy_1:
 ; CHECK-NEXT: .functype memcpy_1 (i64, i64) -> ()
 ; CHECK-NEXT: i32.load8_u $push[[L0:[0-9]+]]=, 0($1)