Index: llvm/lib/Target/AArch64/AArch64InstrInfo.td
===================================================================
--- llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -7345,7 +7345,12 @@
                               (i64 (i64shift_sext_i16 imm0_63:$imm)))>;
 
 def : Pat<(shl (i64 (sext GPR32:$Rn)), (i64 imm0_63:$imm)),
-          (SBFMXri (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GPR32:$Rn, sub_32),
+          (SBFMXri (SUBREG_TO_REG (i64 0), GPR32:$Rn, sub_32),
+                   (i64 (i64shift_a        imm0_63:$imm)),
+                   (i64 (i64shift_sext_i32 imm0_63:$imm)))>;
+
+def : Pat<(shl (i64 (zext GPR32:$Rn)), (i64 imm0_63:$imm)),
+          (UBFMXri (SUBREG_TO_REG (i64 0), GPR32:$Rn, sub_32),
                    (i64 (i64shift_a        imm0_63:$imm)),
                    (i64 (i64shift_sext_i32 imm0_63:$imm)))>;
 
Index: llvm/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
===================================================================
--- llvm/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
+++ llvm/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
@@ -305,12 +305,11 @@
 ; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #40]
 ; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #56]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
-; CHECK: mov	w9, w0
-; CHECK: mov	 x10, sp
-; CHECK: lsl	x9, x9, #2
-; CHECK: add	x9, x9, #15
-; CHECK: and	x9, x9, #0x7fffffff0
-; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
+; CHECK: mov	 x9, sp
+; CHECK: ubfiz	 x10, x0, #2, #32
+; CHECK: add	 x10, x10, #15
+; CHECK: and	 x10, x10, #0x7fffffff0
+; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x9, x10
 ; CHECK: mov	 sp, x[[VLASPTMP]]
 ;   Check correct access to local variable, through frame pointer
 ; CHECK: ldur	w[[ILOC:[0-9]+]], [x29, #-4]
@@ -352,13 +351,12 @@
 ; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
 ; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
-; CHECK: mov	w9, w0
-; CHECK: mov	 x10, sp
-; CHECK: lsl	x9, x9, #2
-; CHECK: add	x9, x9, #15
-; CHECK: and	x9, x9, #0x7fffffff0
-; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
-; CHECK: mov	 sp, x[[VLASPTMP]]
+; CHECK: mov	x9, sp
+; CHECK: ubfiz	x10, x0, #2, #32
+; CHECK: add	x10, x10, #15
+; CHECK: and	x10, x10, #0x7fffffff0
+; CHECK: sub	x[[VLASPTMP:[0-9]+]], x9, x10
+; CHECK: mov	sp, x[[VLASPTMP]]
 ;   Check correct access to local variable, through frame pointer
 ; CHECK: ldur	w[[ILOC:[0-9]+]], [x29, #-4]
 ;   Check correct accessing of the VLA variable through the base pointer
@@ -414,12 +412,11 @@
 ; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #72]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
 ;   and set-up of base pointer (x19).
-; CHECK: mov	w9, w0
-; CHECK: mov	 x10, sp
-; CHECK: lsl	x9, x9, #2
-; CHECK: add	x9, x9, #15
-; CHECK: and	x9, x9, #0x7fffffff0
-; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
+; CHECK: mov	 x9, sp
+; CHECK: ubfiz	 x10, x0, #2, #32
+; CHECK: add	 x10, x10, #15
+; CHECK: and	 x10, x10, #0x7fffffff0
+; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x9, x10
 ; CHECK: mov	 sp, x[[VLASPTMP]]
 ;   Check correct access to local variable, through base pointer
 ; CHECK: ldr	w[[ILOC:[0-9]+]], [x19]
@@ -462,12 +459,11 @@
 ; CHECK-MACHO: ldr	d[[DARG:[0-9]+]], [x29, #32]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
 ;   and set-up of base pointer (x19).
-; CHECK-MACHO: mov	w9, w0
-; CHECK-MACHO: mov	 x10, sp
-; CHECK-MACHO: lsl	x9, x9, #2
-; CHECK-MACHO: add	x9, x9, #15
-; CHECK-MACHO: and	x9, x9, #0x7fffffff0
-; CHECK-MACHO: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
+; CHECK-MACHO: mov	 x9, sp
+; CHECK-MACHO: ubfiz	 x10, x0, #2, #32
+; CHECK-MACHO: add	 x10, x10, #15
+; CHECK-MACHO: and	 x10, x10, #0x7fffffff0
+; CHECK-MACHO: sub	 x[[VLASPTMP:[0-9]+]], x9, x10
 ; CHECK-MACHO: mov	 sp, x[[VLASPTMP]]
 ;   Check correct access to local variable, through base pointer
 ; CHECK-MACHO: ldr	w[[ILOC:[0-9]+]], [x19]
@@ -515,12 +511,11 @@
 ; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #56]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
 ;   and set-up of base pointer (x19).
-; CHECK: mov	w9, w0
-; CHECK: mov	 x10, sp
-; CHECK: lsl	x9, x9, #2
-; CHECK: add	x9, x9, #15
-; CHECK: and	x9, x9, #0x7fffffff0
-; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
+; CHECK: mov	 x9, sp
+; CHECK: ubfiz	 x10, x0, #2, #32
+; CHECK: add	 x10, x10, #15
+; CHECK: and	 x10, x10, #0x7fffffff0
+; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x9, x10
 ; CHECK: mov	 sp, x[[VLASPTMP]]
 ;   Check correct access to local variable, through base pointer
 ; CHECK: ldr	w[[ILOC:[0-9]+]], [x19]
@@ -550,12 +545,11 @@
 ; CHECK-MACHO: ldr	d[[DARG:[0-9]+]], [x29, #32]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
 ;   and set-up of base pointer (x19).
-; CHECK-MACHO: mov	w9, w0
-; CHECK-MACHO: mov	 x10, sp
-; CHECK-MACHO: lsl	x9, x9, #2
-; CHECK-MACHO: add	x9, x9, #15
-; CHECK-MACHO: and	x9, x9, #0x7fffffff0
-; CHECK-MACHO: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
+; CHECK-MACHO: mov	 x9, sp
+; CHECK-MACHO: ubfiz	 x10, x0, #2, #32
+; CHECK-MACHO: add 	 x10, x10, #15
+; CHECK-MACHO: and	 x10, x10, #0x7fffffff0
+; CHECK-MACHO: sub	 x[[VLASPTMP:[0-9]+]], x9, x10
 ; CHECK-MACHO: mov	 sp, x[[VLASPTMP]]
 ;   Check correct access to local variable, through base pointer
 ; CHECK-MACHO: ldr	w[[ILOC:[0-9]+]], [x19]
@@ -601,12 +595,11 @@
 ; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #56]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
 ;   and set-up of base pointer (x19).
-; CHECK: mov	w9, w0
-; CHECK: mov	 x10, sp
-; CHECK: lsl	x9, x9, #2
-; CHECK: add	x9, x9, #15
-; CHECK: and	x9, x9, #0x7fffffff0
-; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
+; CHECK: mov	 x9, sp
+; CHECK: ubfiz	 x10, x0, #2, #32
+; CHECK: add	 x10, x10, #15
+; CHECK: and	 x10, x10, #0x7fffffff0
+; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x9, x10
 ; CHECK: mov	 sp, x[[VLASPTMP]]
 ;   Check correct access to local variable, through base pointer
 ; CHECK: ldr	w[[ILOC:[0-9]+]], [x19]
@@ -636,12 +629,11 @@
 ; CHECK-MACHO: ldr	d[[DARG:[0-9]+]], [x29, #32]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
 ;   and set-up of base pointer (x19).
-; CHECK-MACHO: mov	w9, w0
-; CHECK-MACHO: mov	 x10, sp
-; CHECK-MACHO: lsl	x9, x9, #2
-; CHECK-MACHO: add	x9, x9, #15
-; CHECK-MACHO: and	x9, x9, #0x7fffffff0
-; CHECK-MACHO: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
+; CHECK-MACHO: mov	 x9, sp
+; CHECK-MACHO: ubfiz	 x10, x0, #2, #32
+; CHECK-MACHO: add	 x10, x10, #15
+; CHECK-MACHO: and	 x10, x10, #0x7fffffff0
+; CHECK-MACHO: sub	 x[[VLASPTMP:[0-9]+]], x9, x10
 ; CHECK-MACHO: mov	 sp, x[[VLASPTMP]]
 ;   Check correct access to local variable, through base pointer
 ; CHECK-MACHO: ldr	w[[ILOC:[0-9]+]], [x19]
Index: llvm/test/CodeGen/AArch64/aarch64-matrix-umull-smull.ll
===================================================================
--- llvm/test/CodeGen/AArch64/aarch64-matrix-umull-smull.ll
+++ llvm/test/CodeGen/AArch64/aarch64-matrix-umull-smull.ll
@@ -137,13 +137,13 @@
 ; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
 ; CHECK-NEXT:    dup v0.4h, w8
 ; CHECK-NEXT:    and x8, x0, #0xfffffff8
+; CHECK-NEXT:    // kill: def $w0 killed $w0 killed $x0 def $x0
 ; CHECK-NEXT:  .LBB2_1: // %vector.body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ldrh w9, [x2], #16
 ; CHECK-NEXT:    subs x8, x8, #8
 ; CHECK-NEXT:    dup v1.4h, w9
-; CHECK-NEXT:    mov w9, w0
-; CHECK-NEXT:    lsl x9, x9, #2
+; CHECK-NEXT:    ubfiz x9, x0, #2, #32
 ; CHECK-NEXT:    add w0, w0, #8
 ; CHECK-NEXT:    umull v1.4s, v0.4h, v1.4h
 ; CHECK-NEXT:    str q1, [x1, x9]
Index: llvm/test/CodeGen/AArch64/select_cc.ll
===================================================================
--- llvm/test/CodeGen/AArch64/select_cc.ll
+++ llvm/test/CodeGen/AArch64/select_cc.ll
@@ -6,7 +6,7 @@
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    fcmp s0, s1
 ; CHECK-NEXT:    cset w8, gt
-; CHECK-NEXT:    lsl x0, x8, #2
+; CHECK-NEXT:    ubfiz x0, x8, #2, #32
 ; CHECK-NEXT:    ret
 entry:
   %cc = fcmp ogt float %a, %b
@@ -19,7 +19,7 @@
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    fcmp s0, s1
 ; CHECK-NEXT:    cset w8, gt
-; CHECK-NEXT:    lsl x0, x8, #2
+; CHECK-NEXT:    ubfiz x0, x8, #2, #32
 ; CHECK-NEXT:    ret
 entry:
   %cc = fcmp ule float %a, %b
@@ -32,7 +32,7 @@
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    cmp w0, w1
 ; CHECK-NEXT:    cset w8, eq
-; CHECK-NEXT:    lsl x0, x8, #2
+; CHECK-NEXT:    ubfiz x0, x8, #2, #32
 ; CHECK-NEXT:    ret
 entry:
   %cc = icmp eq i32 %a, %b
@@ -45,7 +45,7 @@
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    cmp w0, w1
 ; CHECK-NEXT:    cset w8, eq
-; CHECK-NEXT:    lsl x0, x8, #2
+; CHECK-NEXT:    ubfiz x0, x8, #2, #32
 ; CHECK-NEXT:    ret
 entry:
   %cc = icmp ne i32 %a, %b
Index: llvm/test/CodeGen/AArch64/shrink-wrapping-vla.ll
===================================================================
--- llvm/test/CodeGen/AArch64/shrink-wrapping-vla.ll
+++ llvm/test/CodeGen/AArch64/shrink-wrapping-vla.ll
@@ -86,12 +86,13 @@
 
 
 ; VLA allocation
-; CHECK: mov [[X2:x[0-9]+]], sp
-; CHECK: mov [[SAVE:x[0-9]+]], sp
-; CHECK: add [[X1:x[0-9]+]], [[X1]], #15
-; CHECK: and [[X1]], [[X1]], #0x7fffffff0
+; CHECK: ubfiz	x9, x0, #2, #32
+; CHECK: mov	x8, sp
+; CHECK: add	x9, x9, #15
+; CHECK: mov	[[SAVE:x[0-9]+]], sp
+; CHECK: and	[[X1:x[0-9]+]], [[X1]], #0x7fffffff0
 ; Saving the SP via llvm.stacksave()
-; CHECK: sub [[X2]], [[X2]], [[X1]]
+; CHECK: sub	[[X2:x[0-9]+]], [[X2]], [[X1]]
 
 ; The next instruction comes from llvm.stackrestore()
 ; CHECK:      mov sp, [[SAVE]]
Index: llvm/test/CodeGen/AArch64/tbl-loops.ll
===================================================================
--- llvm/test/CodeGen/AArch64/tbl-loops.ll
+++ llvm/test/CodeGen/AArch64/tbl-loops.ll
@@ -151,7 +151,7 @@
 ; CHECK-NEXT:    cmp w8, #2
 ; CHECK-NEXT:    b.ls .LBB1_4
 ; CHECK-NEXT:  // %bb.2: // %vector.memcheck
-; CHECK-NEXT:    lsl x9, x8, #1
+; CHECK-NEXT:    ubfiz x9, x8, #1, #32
 ; CHECK-NEXT:    add x9, x9, #2
 ; CHECK-NEXT:    add x10, x1, x9, lsl #2
 ; CHECK-NEXT:    cmp x10, x0
@@ -535,7 +535,7 @@
 ; CHECK-NEXT:    cmp w8, #2
 ; CHECK-NEXT:    b.ls .LBB3_4
 ; CHECK-NEXT:  // %bb.2: // %vector.memcheck
-; CHECK-NEXT:    lsl x9, x8, #2
+; CHECK-NEXT:    ubfiz x9, x8, #2, #32
 ; CHECK-NEXT:    add x9, x9, #4
 ; CHECK-NEXT:    add x10, x1, x9, lsl #2
 ; CHECK-NEXT:    cmp x10, x0