diff --git a/cranelift/codegen/src/isa/x64/inst/mod.rs b/cranelift/codegen/src/isa/x64/inst/mod.rs
index e6cd016982..581fdb7fa7 100644
--- a/cranelift/codegen/src/isa/x64/inst/mod.rs
+++ b/cranelift/codegen/src/isa/x64/inst/mod.rs
@@ -1108,8 +1108,8 @@ impl PrettyPrint for Inst {
                 ..
             } => {
                 let src1 = pretty_print_reg(src1.to_reg(), 8, allocs);
-                let src2 = src2.pretty_print(8, allocs);
                 let dst = pretty_print_reg(dst.to_reg().to_reg(), 8, allocs);
+                let src2 = src2.pretty_print(8, allocs);
                 format!("{} {}, {}, {}", ljustify(op.to_string()), src1, src2, dst)
             }
 
diff --git a/cranelift/filetests/filetests/isa/x64/fastcall.clif b/cranelift/filetests/filetests/isa/x64/fastcall.clif
index 8300606476..247af5ac38 100644
--- a/cranelift/filetests/filetests/isa/x64/fastcall.clif
+++ b/cranelift/filetests/filetests/isa/x64/fastcall.clif
@@ -267,30 +267,30 @@ block0(v0: i64):
 ;   movsd   136(%rcx), %xmm3
 ;   movsd   144(%rcx), %xmm4
 ;   movdqu  rsp(80 + virtual offset), %xmm6
-;   addsd   %xmm0, %xmm0, %xmm6
+;   addsd   %xmm0, %xmm6, %xmm0
 ;   movdqu  rsp(0 + virtual offset), %xmm6
 ;   movdqu  rsp(64 + virtual offset), %xmm7
-;   addsd   %xmm6, %xmm6, %xmm7
+;   addsd   %xmm6, %xmm7, %xmm6
 ;   movdqu  rsp(48 + virtual offset), %xmm7
-;   addsd   %xmm14, %xmm14, %xmm7
+;   addsd   %xmm14, %xmm7, %xmm14
 ;   movdqu  rsp(32 + virtual offset), %xmm7
-;   addsd   %xmm9, %xmm9, %xmm7
+;   addsd   %xmm9, %xmm7, %xmm9
 ;   movdqu  rsp(16 + virtual offset), %xmm7
-;   addsd   %xmm13, %xmm13, %xmm7
-;   addsd   %xmm11, %xmm11, %xmm10
-;   addsd   %xmm5, %xmm5, %xmm12
-;   addsd   %xmm1, %xmm1, %xmm2
-;   addsd   %xmm8, %xmm8, %xmm3
-;   addsd   %xmm4, 152(%xmm4), %rcx
-;   addsd   %xmm0, %xmm0, %xmm6
-;   addsd   %xmm14, %xmm14, %xmm9
-;   addsd   %xmm13, %xmm13, %xmm11
-;   addsd   %xmm5, %xmm5, %xmm1
-;   addsd   %xmm8, %xmm8, %xmm4
-;   addsd   %xmm0, %xmm0, %xmm14
-;   addsd   %xmm13, %xmm13, %xmm5
-;   addsd   %xmm0, %xmm0, %xmm13
-;   addsd   %xmm0, %xmm0, %xmm8
+;   addsd   %xmm13, %xmm7, %xmm13
+;   addsd   %xmm11, %xmm10, %xmm11
+;   addsd   %xmm5, %xmm12, %xmm5
+;   addsd   %xmm1, %xmm2, %xmm1
+;   addsd   %xmm8, %xmm3, %xmm8
+;   addsd   %xmm4, 152(%rcx), %xmm4
+;   addsd   %xmm0, %xmm6, %xmm0
+;   addsd   %xmm14, %xmm9, %xmm14
+;   addsd   %xmm13, %xmm11, %xmm13
+;   addsd   %xmm5, %xmm1, %xmm5
+;   addsd   %xmm8, %xmm4, %xmm8
+;   addsd   %xmm0, %xmm14, %xmm0
+;   addsd   %xmm13, %xmm5, %xmm13
+;   addsd   %xmm0, %xmm13, %xmm0
+;   addsd   %xmm0, %xmm8, %xmm0
 ;   movdqu  96(%rsp), %xmm6
 ;   movdqu  112(%rsp), %xmm7
 ;   movdqu  128(%rsp), %xmm8
diff --git a/cranelift/filetests/filetests/isa/x64/floating-point.clif b/cranelift/filetests/filetests/isa/x64/floating-point.clif
index 153904de83..1c1dc03fdb 100644
--- a/cranelift/filetests/filetests/isa/x64/floating-point.clif
+++ b/cranelift/filetests/filetests/isa/x64/floating-point.clif
@@ -14,7 +14,7 @@ block0(v0: f64):
 ;   movabsq $9223372036854775807, %rdx
 ;   movq    %rdx, %xmm0
 ;   movdqa  %xmm5, %xmm7
-;   andpd   %xmm0, %xmm0, %xmm7
+;   andpd   %xmm0, %xmm7, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -32,7 +32,7 @@ block0(v0: i64):
 ;   movsd   0(%rdi), %xmm5
 ;   movabsq $9223372036854775807, %r8
 ;   movq    %r8, %xmm0
-;   andpd   %xmm0, %xmm0, %xmm5
+;   andpd   %xmm0, %xmm5, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
diff --git a/cranelift/filetests/filetests/isa/x64/simd-bitwise-compile.clif b/cranelift/filetests/filetests/isa/x64/simd-bitwise-compile.clif
index 7112afa311..987a5f619a 100644
--- a/cranelift/filetests/filetests/isa/x64/simd-bitwise-compile.clif
+++ b/cranelift/filetests/filetests/isa/x64/simd-bitwise-compile.clif
@@ -11,7 +11,7 @@ block0(v0: f32x4, v1: f32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   andps   %xmm0, %xmm0, %xmm1
+;   andps   %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -25,7 +25,7 @@ block0(v0: f64x2, v1: f64x2):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   andpd   %xmm0, %xmm0, %xmm1
+;   andpd   %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -39,7 +39,7 @@ block0(v0: i32x4, v1: i32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   pand    %xmm0, %xmm0, %xmm1
+;   pand    %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -53,7 +53,7 @@ block0(v0: f32x4, v1: f32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   orps    %xmm0, %xmm0, %xmm1
+;   orps    %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -67,7 +67,7 @@ block0(v0: f64x2, v1: f64x2):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   orpd    %xmm0, %xmm0, %xmm1
+;   orpd    %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -81,7 +81,7 @@ block0(v0: i32x4, v1: i32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   por     %xmm0, %xmm0, %xmm1
+;   por     %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -95,7 +95,7 @@ block0(v0: f32x4, v1: f32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   xorps   %xmm0, %xmm0, %xmm1
+;   xorps   %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -109,7 +109,7 @@ block0(v0: f64x2, v1: f64x2):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   xorpd   %xmm0, %xmm0, %xmm1
+;   xorpd   %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -123,7 +123,7 @@ block0(v0: i32x4, v1: i32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   pxor    %xmm0, %xmm0, %xmm1
+;   pxor    %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -143,9 +143,9 @@ block0:
 ;   load_const VCodeConstant(0), %xmm0
 ;   load_const VCodeConstant(0), %xmm5
 ;   load_const VCodeConstant(0), %xmm4
-;   pand    %xmm5, %xmm5, %xmm0
-;   pandn   %xmm0, %xmm0, %xmm4
-;   por     %xmm0, %xmm0, %xmm5
+;   pand    %xmm5, %xmm0, %xmm5
+;   pandn   %xmm0, %xmm4, %xmm0
+;   por     %xmm0, %xmm5, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -159,7 +159,7 @@ block0(v0: b16x8, v1: i16x8, v2: i16x8):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   pblendvb %xmm2, %xmm2, %xmm1
+;   pblendvb %xmm2, %xmm1, %xmm2
 ;   movdqa  %xmm2, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
@@ -174,7 +174,7 @@ block0(v0: b32x4, v1: f32x4, v2: f32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   blendvps %xmm2, %xmm2, %xmm1
+;   blendvps %xmm2, %xmm1, %xmm2
 ;   movdqa  %xmm2, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
@@ -189,7 +189,7 @@ block0(v0: b64x2, v1: f64x2, v2: f64x2):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   blendvpd %xmm2, %xmm2, %xmm1
+;   blendvpd %xmm2, %xmm1, %xmm2
 ;   movdqa  %xmm2, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
@@ -211,7 +211,7 @@ block0(v0: i32):
 ;   lea     const(VCodeConstant(0)), %rax
 ;   shlq    $4, %rdi, %rdi
 ;   movdqu  0(%rax,%rdi,1), %xmm13
-;   pand    %xmm0, %xmm0, %xmm13
+;   pand    %xmm0, %xmm13, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -230,7 +230,7 @@ block0:
 ;   load_const VCodeConstant(1), %xmm0
 ;   psrlw   %xmm0, $1, %xmm0
 ;   movdqu  const(VCodeConstant(0)), %xmm5
-;   pand    %xmm0, %xmm0, %xmm5
+;   pand    %xmm0, %xmm5, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -247,13 +247,13 @@ block0(v0: i32):
 ; block0:
 ;   load_const VCodeConstant(0), %xmm9
 ;   movdqa  %xmm9, %xmm0
-;   punpcklbw %xmm0, %xmm0, %xmm9
+;   punpcklbw %xmm0, %xmm9, %xmm0
 ;   punpckhbw %xmm9, %xmm9, %xmm9
 ;   addl    %edi, $8, %edi
 ;   movd    %edi, %xmm11
 ;   psraw   %xmm0, %xmm11, %xmm0
 ;   psraw   %xmm9, %xmm11, %xmm9
-;   packsswb %xmm0, %xmm0, %xmm9
+;   packsswb %xmm0, %xmm9, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -268,14 +268,14 @@ block0(v0: i8x16, v1: i32):
 ;   movq    %rsp, %rbp
 ; block0:
 ;   movdqa  %xmm0, %xmm9
-;   punpcklbw %xmm9, %xmm9, %xmm0
+;   punpcklbw %xmm9, %xmm0, %xmm9
 ;   punpckhbw %xmm0, %xmm0, %xmm0
 ;   movdqa  %xmm9, %xmm12
 ;   psraw   %xmm12, $11, %xmm12
 ;   movdqa  %xmm12, %xmm9
 ;   psraw   %xmm0, $11, %xmm0
 ;   movdqa  %xmm9, %xmm1
-;   packsswb %xmm1, %xmm1, %xmm0
+;   packsswb %xmm1, %xmm0, %xmm1
 ;   movdqa  %xmm1, %xmm9
 ;   movdqa  %xmm9, %xmm0
 ;   movq    %rbp, %rsp
diff --git a/cranelift/filetests/filetests/isa/x64/simd-comparison-legalize.clif b/cranelift/filetests/filetests/isa/x64/simd-comparison-legalize.clif
index 6a99987e29..187d2fca0f 100644
--- a/cranelift/filetests/filetests/isa/x64/simd-comparison-legalize.clif
+++ b/cranelift/filetests/filetests/isa/x64/simd-comparison-legalize.clif
@@ -11,9 +11,9 @@ block0(v0: i32x4, v1: i32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   pcmpeqd %xmm0, %xmm0, %xmm1
+;   pcmpeqd %xmm0, %xmm1, %xmm0
 ;   pcmpeqd %xmm7, %xmm7, %xmm7
-;   pxor    %xmm0, %xmm0, %xmm7
+;   pxor    %xmm0, %xmm7, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -27,10 +27,10 @@ block0(v0: i32x4, v1: i32x4):
 ;   pushq   %rbp
 ;   movq    %rsp, %rbp
 ; block0:
-;   pmaxud  %xmm0, %xmm0, %xmm1
-;   pcmpeqd %xmm0, %xmm0, %xmm1
+;   pmaxud  %xmm0, %xmm1, %xmm0
+;   pcmpeqd %xmm0, %xmm1, %xmm0
 ;   pcmpeqd %xmm9, %xmm9, %xmm9
-;   pxor    %xmm0, %xmm0, %xmm9
+;   pxor    %xmm0, %xmm9, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -45,8 +45,8 @@ block0(v0: i16x8, v1: i16x8):
 ;   movq    %rsp, %rbp
 ; block0:
 ;   movdqa  %xmm0, %xmm5
-;   pmaxsw  %xmm5, %xmm5, %xmm1
-;   pcmpeqw %xmm0, %xmm0, %xmm5
+;   pmaxsw  %xmm5, %xmm1, %xmm5
+;   pcmpeqw %xmm0, %xmm5, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -61,8 +61,8 @@ block0(v0: i8x16, v1: i8x16):
 ;   movq    %rsp, %rbp
 ; block0:
 ;   movdqa  %xmm0, %xmm5
-;   pmaxub  %xmm5, %xmm5, %xmm1
-;   pcmpeqb %xmm0, %xmm0, %xmm5
+;   pmaxub  %xmm5, %xmm1, %xmm5
+;   pcmpeqb %xmm0, %xmm5, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
diff --git a/cranelift/filetests/filetests/isa/x64/simd-lane-access-compile.clif b/cranelift/filetests/filetests/isa/x64/simd-lane-access-compile.clif
index 9d4b7b572e..d894de3163 100644
--- a/cranelift/filetests/filetests/isa/x64/simd-lane-access-compile.clif
+++ b/cranelift/filetests/filetests/isa/x64/simd-lane-access-compile.clif
@@ -18,10 +18,10 @@ block0:
 ;   load_const VCodeConstant(3), %xmm1
 ;   load_const VCodeConstant(2), %xmm0
 ;   load_const VCodeConstant(0), %xmm9
-;   pshufb  %xmm1, %xmm1, %xmm9
+;   pshufb  %xmm1, %xmm9, %xmm1
 ;   load_const VCodeConstant(1), %xmm12
-;   pshufb  %xmm0, %xmm0, %xmm12
-;   orps    %xmm0, %xmm0, %xmm1
+;   pshufb  %xmm0, %xmm12, %xmm0
+;   orps    %xmm0, %xmm1, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -38,7 +38,7 @@ block0:
 ; block0:
 ;   load_const VCodeConstant(1), %xmm0
 ;   load_const VCodeConstant(0), %xmm5
-;   pshufb  %xmm0, %xmm0, %xmm5
+;   pshufb  %xmm0, %xmm5, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -57,8 +57,8 @@ block0:
 ;   load_const VCodeConstant(1), %xmm0
 ;   load_const VCodeConstant(1), %xmm2
 ;   load_const VCodeConstant(0), %xmm7
-;   paddusb %xmm2, %xmm2, %xmm7
-;   pshufb  %xmm0, %xmm0, %xmm2
+;   paddusb %xmm2, %xmm7, %xmm2
+;   pshufb  %xmm0, %xmm2, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -75,7 +75,7 @@ block0(v0: i8):
 ;   uninit  %xmm0
 ;   pinsrb  $0, %xmm0, %rdi, %xmm0
 ;   pxor    %xmm6, %xmm6, %xmm6
-;   pshufb  %xmm0, %xmm0, %xmm6
+;   pshufb  %xmm0, %xmm6, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -127,8 +127,8 @@ block0(v0: f64):
 ;   movdqa  %xmm0, %xmm4
 ;   uninit  %xmm0
 ;   movdqa  %xmm4, %xmm5
-;   movsd   %xmm0, %xmm0, %xmm5
-;   movlhps %xmm0, %xmm0, %xmm5
+;   movsd   %xmm0, %xmm5, %xmm0
+;   movlhps %xmm0, %xmm5, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
diff --git a/cranelift/filetests/filetests/isa/x64/simd-logical-compile.clif b/cranelift/filetests/filetests/isa/x64/simd-logical-compile.clif
index 42849a3987..cad0c91c0d 100644
--- a/cranelift/filetests/filetests/isa/x64/simd-logical-compile.clif
+++ b/cranelift/filetests/filetests/isa/x64/simd-logical-compile.clif
@@ -12,7 +12,7 @@ block0(v0: b32x4):
 ;   movq    %rsp, %rbp
 ; block0:
 ;   pcmpeqd %xmm3, %xmm3, %xmm3
-;   pxor    %xmm0, %xmm0, %xmm3
+;   pxor    %xmm0, %xmm3, %xmm0
 ;   movq    %rbp, %rsp
 ;   popq    %rbp
 ;   ret
@@ -42,7 +42,7 @@ block0(v0: i64x2):
 ;   movq    %rsp, %rbp
 ; block0:
 ;   pxor    %xmm4, %xmm4, %xmm4
-;   pcmpeqq %xmm4, %xmm4, %xmm0
+;   pcmpeqq %xmm4, %xmm0, %xmm4
 ;   ptest   %xmm4, %xmm4
 ;   setz    %al
 ;   movq    %rbp, %rsp