if (OptLevel == CodeGenOpt::None)
return SDValue();
+ // If this is used only a single token factor, we should make sure we have a
+ // chance to merge them together. This prevents TF chains from inhibiting
+ // optimizations.
+ if (N->hasOneUse() && N->use_begin()->getOpcode() == ISD::TokenFactor)
+ AddToWorklist(*(N->use_begin()));
+
SmallVector<SDNode *, 8> TFs; // List of token factors to visit.
SmallVector<SDValue, 8> Ops; // Ops for replacing token factor.
SmallPtrSet<SDNode*, 16> SeenOps;
; CHECK: str x30, [sp, #-80]!
; CHECK: add x8, sp, #24
; CHECK: add x0, sp, #24
-; CHECK: stp x6, x7, [sp, #64]
-; CHECK: stp x4, x5, [sp, #48]
-; CHECK: stp x2, x3, [sp, #32]
-; CHECK: str x1, [sp, #24]
+; CHECK: stp x1, x2, [sp, #24]
+; CHECK: stp x3, x4, [sp, #40]
+; CHECK: stp x5, x6, [sp, #56]
+; CHECK: str x7, [sp, #72]
; CHECK: str x8, [sp, #8]
; CHECK: bl other_func
; CHECK: ldr x30, [sp], #80
; CHECK: sub sp, sp, #96
; CHECK: stp x29, x30, [sp, #16]
; CHECK: add x29, sp, #16
-; CHECK: str x1, [x29, #24]
+; CHECK: stp x1, x2, [x29, #24]
; CHECK: add x1, x29, #8
; CHECK: ldp x29, x30, [sp, #16]
; CHECK: add sp, sp, #96
; CHECK: stp x29, x30, [sp, #-16]!
; CHECK: mov x29, sp
; CHECK: sub sp, sp, #192
-; CHECK: stp q6, q7, [x29, #-96]
+; CHECK-DAG: stp q6, q7, [x29, #-96]
; [...]
-; CHECK: stp q0, q1, [x29, #-192]
+; CHECK-DAG: stp q0, q1, [x29, #-192]
-; CHECK: stp x6, x7, [x29, #-16]
+; CHECK-DAG: stp x5, x6, [x29, #-24]
; [...]
-; CHECK: stp x2, x3, [x29, #-48]
+; CHECK-DAG: stp x1, x2, [x29, #-56]
; CHECK-NOFP-ARM64: stp x29, x30, [sp, #-16]!
; CHECK-NOFP-ARM64: mov x29, sp
; CHECK-NOFP-ARM64: sub sp, sp, #64
-; CHECK-NOFP-ARM64: stp x6, x7, [x29, #-16]
+; CHECK-NOFP-ARM64-DAG: stp x5, x6, [x29, #-24]
; [...]
-; CHECK-NOFP-ARM64: stp x4, x5, [x29, #-32]
+; CHECK-NOFP-ARM64-DAG: stp x3, x4, [x29, #-40]
; [...]
-; CHECK-NOFP-ARM64: stp x2, x3, [x29, #-48]
+; CHECK-NOFP-ARM64-DAG: stp x1, x2, [x29, #-56]
; [...]
; CHECK-NOFP-ARM64: mov x8, sp
define i32 @t0() {
entry:
; CHECK-LABEL: t0:
-; CHECK: ldur [[REG0:w[0-9]+]], [x[[BASEREG:[0-9]+]], #7]
-; CHECK: stur [[REG0]], [x[[BASEREG2:[0-9]+]], #7]
-; CHECK: ldr [[REG2:x[0-9]+]],
-; CHECK: str [[REG2]],
+; CHECK-DAG: ldur [[REG0:w[0-9]+]], [x[[BASEREG:[0-9]+]], #7]
+; CHECK-DAG: stur [[REG0]], [x[[BASEREG2:[0-9]+]], #7]
+; CHECK-DAG: ldr [[REG2:x[0-9]+]],
+; CHECK-DAG: str [[REG2]],
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 getelementptr inbounds (%struct.x, %struct.x* @dst, i32 0, i32 0), i8* align 8 getelementptr inbounds (%struct.x, %struct.x* @src, i32 0, i32 0), i32 11, i1 false)
ret i32 0
}
define void @t6() nounwind {
entry:
; CHECK-LABEL: t6:
-; CHECK: ldur [[REG9:x[0-9]+]], [x{{[0-9]+}}, #6]
-; CHECK: stur [[REG9]], [x{{[0-9]+}}, #6]
-; CHECK: ldr
-; CHECK: str
+; CHECK-DAG: ldur [[REG9:x[0-9]+]], [x{{[0-9]+}}, #6]
+; CHECK-DAG: stur [[REG9]], [x{{[0-9]+}}, #6]
+; CHECK-DAG: ldr
+; CHECK-DAG: str
call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds ([512 x i8], [512 x i8]* @spool.splbuf, i64 0, i64 0), i8* getelementptr inbounds ([14 x i8], [14 x i8]* @.str6, i64 0, i64 0), i64 14, i1 false)
ret void
}
; CHECK: adrp x[[VA_LIST_HI:[0-9]+]], var
; CHECK: add x[[VA_LIST:[0-9]+]], {{x[0-9]+}}, :lo12:var
-; CHECK: stp x1, x2, [sp, #[[GR_BASE:[0-9]+]]]
+; CHECK-DAG: stp x6, x7, [sp, #
; ... omit middle ones ...
-; CHECK: str x7, [sp, #
+; CHECK-DAG: str x1, [sp, #[[GR_BASE:[0-9]+]]]
-; CHECK: stp q0, q1, [sp]
+; CHECK-DAG: stp q0, q1, [sp]
; ... omit middle ones ...
-; CHECK: stp q6, q7, [sp, #
+; CHECK-DAG: stp q6, q7, [sp, #
; CHECK: str [[STACK_TOP]], [x[[VA_LIST]]]
; CHECK: adrp x[[VA_LIST_HI:[0-9]+]], var
; CHECK: add x[[VA_LIST:[0-9]+]], {{x[0-9]+}}, :lo12:var
-; CHECK: stp x3, x4, [sp, #[[GR_BASE:[0-9]+]]]
+; CHECK-DAG: stp x6, x7, [sp, #
; ... omit middle ones ...
-; CHECK: str x7, [sp, #
+; CHECK-DAG: str x3, [sp, #[[GR_BASE:[0-9]+]]]
-; CHECK: stp q1, q2, [sp]
+; CHECK-DAG: stp q6, q7, [sp, #80]
; ... omit middle ones ...
-; CHECK: str q7, [sp, #
+; CHECK-DAG: str q1, [sp]
; CHECK: str [[STACK_TOP]], [x[[VA_LIST]]]
; __stack field should point just past them.
define void @test_offsetstack([8 x i64], [2 x i64], [3 x float], ...) {
; CHECK-LABEL: test_offsetstack:
-; CHECK: stp {{q[0-9]+}}, {{q[0-9]+}}, [sp, #-80]!
-; CHECK: add [[STACK_TOP:x[0-9]+]], sp, #96
-; CHECK: add x[[VAR:[0-9]+]], {{x[0-9]+}}, :lo12:var
-; CHECK: str [[STACK_TOP]], [x[[VAR]]]
+
+; CHECK-DAG: stp {{q[0-9]+}}, {{q[0-9]+}}, [sp, #48]
+; CHECK-DAG: stp {{q[0-9]+}}, {{q[0-9]+}}, [sp, #16]
+; CHECK-DAG: str {{q[0-9]+}}, [sp]
+; CHECK-DAG: add [[STACK_TOP:x[0-9]+]], sp, #96
+; CHECK-DAG: add x[[VAR:[0-9]+]], {{x[0-9]+}}, :lo12:var
+; CHECK-DAG: str [[STACK_TOP]], [x[[VAR]]]
%addr = bitcast %va_list* @var to i8*
call void @llvm.va_start(i8* %addr)
; CHECK: str x30, [sp, #-80]!
; CHECK: add x8, sp, #24
; CHECK: add x0, sp, #24
-; CHECK: stp x6, x7, [sp, #64]
-; CHECK: stp x4, x5, [sp, #48]
-; CHECK: stp x2, x3, [sp, #32]
-; CHECK: str x1, [sp, #24]
+; CHECK: stp x1, x2, [sp, #24]
+; CHECK: stp x3, x4, [sp, #40]
+; CHECK: stp x5, x6, [sp, #56]
+; CHECK: str x7, [sp, #72]
; CHECK: str x8, [sp, #8]
; CHECK: bl other_func
; CHECK: ldr x30, [sp], #80
; CHECK-LABEL: copy1:
; CHECK: sub sp, sp, #80
; CHECK: add x8, sp, #24
-; CHECK: stp x6, x7, [sp, #64]
-; CHECK: stp x4, x5, [sp, #48]
-; CHECK: stp x2, x3, [sp, #32]
-; CHECK: str x1, [sp, #24]
+; CHECK: stp x1, x2, [sp, #24]
+; CHECK: stp x3, x4, [sp, #40]
+; CHECK: stp x5, x6, [sp, #56]
+; CHECK: str x7, [sp, #72]
; CHECK: stp x8, x8, [sp], #80
; CHECK: ret
define void @copy1(i64 %a0, ...) nounwind {
; CHECK: mov x19, x2
; CHECK: mov x20, x1
; CHECK: mov x21, x0
-; CHECK: stp x6, x7, [x29, #48]
-; CHECK: stp x4, x5, [x29, #32]
-; CHECK: str x3, [x29, #24]
+; CHECK: stp x3, x4, [x29, #24]
+; CHECK: stp x5, x6, [x29, #40]
+; CHECK: str x7, [x29, #56]
; CHECK: str x8, [sp, #8]
; CHECK: bl __local_stdio_printf_options
; CHECK: ldr x8, [x0]
; CHECK: lsr x15, x8, #4
; CHECK: mov x19, x1
; CHECK: mov [[REG2:x[0-9]+]], sp
-; CHECK: stp x6, x7, [x29, #48]
-; CHECK: stp x4, x5, [x29, #32]
; CHECK: stp x2, x3, [x29, #16]
+; CHECK: stp x4, x5, [x29, #32]
+; CHECK: stp x6, x7, [x29, #48]
; CHECK: bl __chkstk
; CHECK: mov x8, sp
; CHECK: sub [[REG:x[0-9]+]], x8, x15, lsl #4
; CHECK-DAG: mov x19, x2
; CHECK-DAG: mov x20, x1
; CHECK-DAG: mov x21, x0
-; CHECK-DAG: stp x6, x7, [sp, #80]
-; CHECK-DAG: stp x4, x5, [sp, #64]
-; CHECK-DAG: str x3, [sp, #56]
+; CHECK-DAG: stp x3, x4, [sp, #56]
+; CHECK-DAG: stp x5, x6, [sp, #72]
+; CHECK-DAG: str x7, [sp, #88]
; CHECK-DAG: str x8, [sp, #8]
; CHECK-DAG: bl __local_stdio_printf_options
; CHECK-DAG: ldr x8, [x0]
; GCN: buffer_store_dword v33, off, s[0:3], s5 offset:12 ; 4-byte Folded Spill
; GCN: buffer_load_dword v32, off, s[0:3], s5 offset:4
; GCN: buffer_load_dword v33, off, s[0:3], s5 offset:8
-; GCN: buffer_store_dword v33, off, s[0:3], s5 offset:8
; GCN: buffer_store_dword v32, off, s[0:3], s5 offset:4
+; GCN: buffer_store_dword v33, off, s[0:3], s5 offset:8
; GCN: s_getpc_b64
; GCN: buffer_load_dword v33, off, s[0:3], s5 offset:12 ; 4-byte Folded Reload
; GCN: buffer_load_dword v32, off, s[0:3], s5 offset:16 ; 4-byte Folded Reload
; CHECK-LABEL: test_byval_8_bytes_alignment_fixed_arg:
; CHECK-NOT: str r1
-; CHECK: str r3, [sp, #12]
-; CHECK: str r2, [sp, #8]
+; CHECK-DAG: str r3, [sp, #12]
+; CHECK-DAG: str r2, [sp, #8]
; CHECK-NOT: str r1
define void @test_byval_8_bytes_alignment_fixed_arg(i32 %n1, %struct_t* byval %val) nounwind {
entry:
declare i32 @printf(i8*, ...)
; CHECK-LABEL: test_byval_usage_scheduling:
-; CHECK: str r3, [sp, #12]
-; CHECK: str r2, [sp, #8]
+; CHECK-DAG: str r3, [sp, #12]
+; CHECK-DAG: str r2, [sp, #8]
; CHECK: vldr d16, [sp, #8]
define void @test_byval_usage_scheduling(i32 %n1, i32 %n2, %struct_t* byval %val) nounwind {
entry:
; CHECK: sub sp, sp, #8
; CHECK: push {r11, lr}
; CHECK: add r0, sp, #8
-; CHECK: str r3, [sp, #12]
-; CHECK: str r2, [sp, #8]
+; CHECK-DAG: str r3, [sp, #12]
+; CHECK-DAG: str r2, [sp, #8]
; CHECK: bl usePtr
; CHECK: pop {r11, lr}
; CHECK: add sp, sp, #8
; CHECK: push {r11, lr}
; CHECK: str r0, [sp, #8]
; CHECK: add r0, sp, #16
-; CHECK: str r3, [sp, #20]
-; CHECK: str r2, [sp, #16]
+; CHECK-DAG: str r3, [sp, #20]
+; CHECK-DAG: str r2, [sp, #16]
; CHECK: bl usePtr
; CHECK: pop {r11, lr}
; CHECK: add sp, sp, #16
; CHECK-7A: vst1.16 {d{{[0-9]+}}, d{{[0-9]+}}}, [r2]
; CHECK-6M-LABEL: t2:
; CHECK-6M: movs [[REG:r[0-9]+]], #0
-; CHECK-6M: str [[REG]], [sp, #20]
-; CHECK-6M: str [[REG]], [sp, #16]
-; CHECK-6M: str [[REG]], [sp, #12]
-; CHECK-6M: str [[REG]], [sp, #8]
-; CHECK-6M: str [[REG]], [sp, #4]
-; CHECK-6M: str [[REG]], [sp]
+; CHECK-6M-DAG: str [[REG]], [sp, #20]
+; CHECK-6M-DAG: str [[REG]], [sp, #16]
+; CHECK-6M-DAG: str [[REG]], [sp, #12]
+; CHECK-6M-DAG: str [[REG]], [sp, #8]
+; CHECK-6M-DAG: str [[REG]], [sp, #4]
+; CHECK-6M-DAG: str [[REG]], [sp]
%buf = alloca [26 x i8], align 1
%0 = getelementptr inbounds [26 x i8], [26 x i8]* %buf, i32 0, i32 0
call void @llvm.memset.p0i8.i32(i8* %0, i8 0, i32 26, i1 false)
; Epilogue
; --------
-; CHECK-V4T: ldr [[POP:r[4567]]], [sp, #12]
+; CHECK-V4T: ldr [[POP:r[4567]]], [sp, #16]
; CHECK-V4T-NEXT: mov lr, [[POP]]
; CHECK-V4T-NEXT: pop {[[SAVED]]}
; CHECK-V4T-NEXT: add sp, #16
; CHECK-V4T-NEXT: bx lr
; CHECK-V5T: lsls r4
; CHECK-V5T-NEXT: mov sp, r4
-; CHECK-V5T: ldr [[POP:r[4567]]], [sp, #12]
+; CHECK-V5T: ldr [[POP:r[4567]]], [sp, #16]
; CHECK-V5T-NEXT: mov lr, [[POP]]
; CHECK-V5T-NEXT: pop {[[SAVED]]}
; CHECK-V5T-NEXT: add sp, #16
define void @t(i8* nocapture %a, i8* nocapture %b) nounwind {
entry:
; EXPANDED-LABEL: t:
-; EXPANDED: ldrb [[R2:r[0-9]+]]
-; EXPANDED: ldrb [[R3:r[0-9]+]]
-; EXPANDED: ldrb [[R12:r[0-9]+]]
-; EXPANDED: ldrb [[R1:r[0-9]+]]
-; EXPANDED: strb [[R1]]
-; EXPANDED: strb [[R12]]
-; EXPANDED: strb [[R3]]
-; EXPANDED: strb [[R2]]
+; EXPANDED-DAG: ldrb [[R2:r[0-9]+]]
+; EXPANDED-DAG: ldrb [[R3:r[0-9]+]]
+; EXPANDED-DAG: ldrb [[R12:r[0-9]+]]
+; EXPANDED-DAG: ldrb [[R1:r[0-9]+]]
+; EXPANDED-DAG: strb [[R1]]
+; EXPANDED-DAG: strb [[R12]]
+; EXPANDED-DAG: strb [[R3]]
+; EXPANDED-DAG: strb [[R2]]
; UNALIGNED-LABEL: t:
; UNALIGNED: ldr r1
; CHECK-LABEL: ret_void_args_i64_i64
define void @ret_void_args_i64_i64(i64 %a, i64 %b) {
- ; CHECK: sts 11, r25
- ; CHECK-NEXT: sts 10, r24
- ; CHECK-NEXT: sts 9, r23
- ; CHECK-NEXT: sts 8, r22
- ; CHECK-NEXT: sts 7, r21
- ; CHECK-NEXT: sts 6, r20
- ; CHECK-NEXT: sts 5, r19
- ; CHECK-NEXT: sts 4, r18
+ ; CHECK-DAG: sts 11, r25
+ ; CHECK-DAG: sts 10, r24
+ ; CHECK-DAG: sts 9, r23
+ ; CHECK-DAG: sts 8, r22
+ ; CHECK-DAG: sts 7, r21
+ ; CHECK-DAG: sts 6, r20
+ ; CHECK-DAG: sts 5, r19
+ ; CHECK-DAG: sts 4, r18
store volatile i64 %a, i64* inttoptr (i64 4 to i64*)
- ; CHECK-NEXT: sts 11, r17
- ; CHECK-NEXT: sts 10, r16
- ; CHECK-NEXT: sts 9, r15
- ; CHECK-NEXT: sts 8, r14
- ; CHECK-NEXT: sts 7, r13
- ; CHECK-NEXT: sts 6, r12
- ; CHECK-NEXT: sts 5, r11
- ; CHECK-NEXT: sts 4, r10
+ ; CHECK-DAG: sts 11, r17
+ ; CHECK-DAG: sts 10, r16
+ ; CHECK-DAG: sts 9, r15
+ ; CHECK-DAG: sts 8, r14
+ ; CHECK-DAG: sts 7, r13
+ ; CHECK-DAG: sts 6, r12
+ ; CHECK-DAG: sts 5, r11
+ ; CHECK-DAG: sts 4, r10
store volatile i64 %b, i64* inttoptr (i64 4 to i64*)
ret void
}
; CHECK: sbci r23, 255
; CHECK: sbci r24, 255
; CHECK: sbci r25, 255
-; CHECK: sts long.static+3, r25
-; CHECK: sts long.static+2, r24
-; CHECK: sts long.static+1, r23
-; CHECK: sts long.static, r22
+; CHECK-DAG: sts long.static+3, r25
+; CHECK-DAG: sts long.static+2, r24
+; CHECK-DAG: sts long.static+1, r23
+; CHECK-DAG: sts long.static, r22
%1 = load i32, i32* @long.static
%inc = add nsw i32 %1, 1
store i32 %inc, i32* @long.static
; CHECK: sbci r23, 255
; CHECK: sbci r24, 255
; CHECK: sbci r25, 255
-; CHECK: sts longlong.static+7, r25
-; CHECK: sts longlong.static+6, r24
-; CHECK: sts longlong.static+5, r23
-; CHECK: sts longlong.static+4, r22
-; CHECK: sts longlong.static+3, r21
-; CHECK: sts longlong.static+2, r20
-; CHECK: sts longlong.static+1, r19
-; CHECK: sts longlong.static, r18
+; CHECK-DAG: sts longlong.static+7, r25
+; CHECK-DAG: sts longlong.static+6, r24
+; CHECK-DAG: sts longlong.static+5, r23
+; CHECK-DAG: sts longlong.static+4, r22
+; CHECK-DAG: sts longlong.static+3, r21
+; CHECK-DAG: sts longlong.static+2, r20
+; CHECK-DAG: sts longlong.static+1, r19
+; CHECK-DAG: sts longlong.static, r18
%1 = load i64, i64* @longlong.static
%inc = add nsw i64 %1, 1
store i64 %inc, i64* @longlong.static
; CHECK: *(u64 *)(r10 - 8) = r1
; CHECK: r1 = 0
-; CHECK: *(u16 *)(r10 + 24) = r1
-; CHECK: *(u16 *)(r10 + 22) = r1
-; CHECK: *(u16 *)(r10 + 20) = r1
-; CHECK: *(u16 *)(r10 + 18) = r1
-; CHECK: *(u16 *)(r10 + 16) = r1
-; CHECK: *(u16 *)(r10 + 14) = r1
-; CHECK: *(u16 *)(r10 + 12) = r1
-; CHECK: *(u16 *)(r10 + 10) = r1
-; CHECK: *(u16 *)(r10 + 8) = r1
-; CHECK: *(u16 *)(r10 + 6) = r1
-; CHECK: *(u16 *)(r10 + 4) = r1
-; CHECK: *(u16 *)(r10 + 2) = r1
-; CHECK: *(u16 *)(r10 + 0) = r1
-; CHECK: *(u16 *)(r10 + 26) = r1
+; CHECK-DAG: *(u16 *)(r10 + 24) = r1
+; CHECK-DAG: *(u16 *)(r10 + 22) = r1
+; CHECK-DAG: *(u16 *)(r10 + 20) = r1
+; CHECK-DAG: *(u16 *)(r10 + 18) = r1
+; CHECK-DAG: *(u16 *)(r10 + 16) = r1
+; CHECK-DAG: *(u16 *)(r10 + 14) = r1
+; CHECK-DAG: *(u16 *)(r10 + 12) = r1
+; CHECK-DAG: *(u16 *)(r10 + 10) = r1
+; CHECK-DAG: *(u16 *)(r10 + 8) = r1
+; CHECK-DAG: *(u16 *)(r10 + 6) = r1
+; CHECK-DAG: *(u16 *)(r10 + 4) = r1
+; CHECK-DAG: *(u16 *)(r10 + 2) = r1
+; CHECK-DAG: *(u16 *)(r10 + 0) = r1
+; CHECK-DAG: *(u16 *)(r10 + 26) = r1
; CHECK: r2 = r10
; CHECK: r2 += -8
; CHECK: mov r13, &g_i64+2
; CHECK: mov r12, &g_i64
store volatile i64 %a, i64* @g_i64, align 2
-; CHECK: mov 10(r4), &g_i64+6
-; CHECK: mov 8(r4), &g_i64+4
-; CHECK: mov 6(r4), &g_i64+2
-; CHECK: mov 4(r4), &g_i64
+; CHECK-DAG: mov 10(r4), &g_i64+6
+; CHECK-DAG: mov 8(r4), &g_i64+4
+; CHECK-DAG: mov 6(r4), &g_i64+2
+; CHECK-DAG: mov 4(r4), &g_i64
store volatile i64 %b, i64* @g_i64, align 2
ret void
}
; CHECK-NEXT: .cfi_def_cfa_register 30
; CHECK-NEXT: addiu $1, $zero, -16
; CHECK-NEXT: and $sp, $sp, $1
-; CHECK-NEXT: lw $1, 8($4)
-; CHECK-NEXT: lw $2, 4($4)
-; CHECK-NEXT: lw $3, 12($4)
-; CHECK-NEXT: sw $3, 12($sp)
-; CHECK-NEXT: sw $1, 8($sp)
-; CHECK-NEXT: sw $2, 4($sp)
-; CHECK-NEXT: lw $1, 0($4)
-; CHECK-NEXT: sw $1, 0($sp)
-; CHECK-NEXT: mtc1 $1, $f0
+; CHECK-NEXT: lw $1, 12($4)
+; CHECK-NEXT: lw $2, 0($4)
+; CHECK-NEXT: lw $3, 8($4)
+; CHECK-NEXT: sw $3, 8($sp)
+; CHECK-NEXT: sw $1, 12($sp)
+; CHECK-NEXT: sw $2, 0($sp)
+; CHECK-NEXT: lw $1, 4($4)
+; CHECK-NEXT: sw $1, 4($sp)
+; CHECK-NEXT: mtc1 $2, $f0
; CHECK-NEXT: move $sp, $fp
; CHECK-NEXT: lw $fp, 28($sp) # 4-byte Folded Reload
; CHECK-NEXT: jr $ra
; CHECK-NEXT: addiu $sp, $sp, 32
-; CHECK-NEXT: .set at
-; CHECK-NEXT: .set macro
-; CHECK-NEXT: .set reorder
-; CHECK-NEXT: .end f
entry:
%m = alloca <8 x i16>
%0 = load <8 x i16>, <8 x i16>* %a
align 16 %a) {
; CHECK-LABEL: testStruct_03:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: std r10, 88(r1)
-; CHECK-NEXT: std r9, 80(r1)
-; CHECK-NEXT: std r8, 72(r1)
-; CHECK-NEXT: std r7, 64(r1)
-; CHECK-NEXT: std r6, 56(r1)
-; CHECK-NEXT: std r5, 48(r1)
-; CHECK-NEXT: std r4, 40(r1)
-; CHECK-NEXT: std r3, 32(r1)
+; CHECK-DAG: std r10, 88(r1)
+; CHECK-DAG: std r9, 80(r1)
+; CHECK-DAG: std r8, 72(r1)
+; CHECK-DAG: std r7, 64(r1)
+; CHECK-DAG: std r6, 56(r1)
+; CHECK-DAG: std r5, 48(r1)
+; CHECK-DAG: std r4, 40(r1)
+; CHECK-DAG: std r3, 32(r1)
; CHECK-NEXT: lxv v2, 128(r1)
; CHECK-NEXT: blr
; CHECK-BE-LABEL: testStruct_03:
; CHECK-BE: # %bb.0: # %entry
-; CHECK-BE-NEXT: std r10, 104(r1)
-; CHECK-BE-NEXT: std r9, 96(r1)
-; CHECK-BE-NEXT: std r8, 88(r1)
-; CHECK-BE-NEXT: std r7, 80(r1)
-; CHECK-BE-NEXT: std r6, 72(r1)
-; CHECK-BE-NEXT: std r5, 64(r1)
-; CHECK-BE-NEXT: std r4, 56(r1)
-; CHECK-BE-NEXT: std r3, 48(r1)
+; CHECK-BE-DAG: std r10, 104(r1)
+; CHECK-BE-DAG: std r9, 96(r1)
+; CHECK-BE-DAG: std r8, 88(r1)
+; CHECK-BE-DAG: std r7, 80(r1)
+; CHECK-BE-DAG: std r6, 72(r1)
+; CHECK-BE-DAG: std r5, 64(r1)
+; CHECK-BE-DAG: std r4, 56(r1)
+; CHECK-BE-DAG: std r3, 48(r1)
; CHECK-BE-NEXT: lxv v2, 144(r1)
; CHECK-BE-NEXT: blr
entry:
define fp128 @testNestedAggregate(%struct.MixedC* byval nocapture readonly align 16 %a) {
; CHECK-LABEL: testNestedAggregate:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: std r8, 72(r1)
-; CHECK-NEXT: std r7, 64(r1)
-; CHECK-NEXT: std r10, 88(r1)
-; CHECK-NEXT: std r9, 80(r1)
-; CHECK-NEXT: std r6, 56(r1)
-; CHECK-NEXT: std r5, 48(r1)
-; CHECK-NEXT: std r4, 40(r1)
-; CHECK-NEXT: std r3, 32(r1)
+; CHECK-DAG: std r10, 88(r1)
+; CHECK-DAG: std r9, 80(r1)
+; CHECK-DAG: std r8, 72(r1)
+; CHECK-DAG: std r7, 64(r1)
+; CHECK-DAG: std r6, 56(r1)
+; CHECK-DAG: std r5, 48(r1)
+; CHECK-DAG: std r4, 40(r1)
+; CHECK-DAG: std r3, 32(r1)
; CHECK-NEXT: lxv v2, 64(r1)
; CHECK-NEXT: blr
; CHECK-BE-LABEL: testNestedAggregate:
; CHECK-BE: # %bb.0: # %entry
-; CHECK-BE-NEXT: std r8, 88(r1)
-; CHECK-BE-NEXT: std r7, 80(r1)
-; CHECK-BE-NEXT: std r10, 104(r1)
-; CHECK-BE-NEXT: std r9, 96(r1)
-; CHECK-BE-NEXT: std r6, 72(r1)
-; CHECK-BE-NEXT: std r5, 64(r1)
-; CHECK-BE-NEXT: std r4, 56(r1)
-; CHECK-BE-NEXT: std r3, 48(r1)
+; CHECK-BE-DAG: std r8, 88(r1)
+; CHECK-BE-DAG: std r7, 80(r1)
+; CHECK-BE-DAG: std r10, 104(r1)
+; CHECK-BE-DAG: std r9, 96(r1)
+; CHECK-BE-DAG: std r6, 72(r1)
+; CHECK-BE-DAG: std r5, 64(r1)
+; CHECK-BE-DAG: std r4, 56(r1)
+; CHECK-BE-DAG: std r3, 48(r1)
; CHECK-BE-NEXT: lxv v2, 80(r1)
; CHECK-BE-NEXT: blr
entry:
define fp128 @sum_float128(i32 signext %count, ...) {
; CHECK-LABEL: sum_float128:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: std r10, 88(r1)
-; CHECK-NEXT: std r9, 80(r1)
-; CHECK-NEXT: std r8, 72(r1)
-; CHECK-NEXT: std r7, 64(r1)
-; CHECK-NEXT: std r6, 56(r1)
-; CHECK-NEXT: cmpwi cr0, r3, 1
-; CHECK-NEXT: std r4, 40(r1)
-; CHECK-NEXT: addis [[REG:r[0-9]+]], r2, .LCPI17_0@toc@ha
-; CHECK-NEXT: addi [[REG1:r[0-9]+]], [[REG]], .LCPI17_0@toc@l
-; CHECK-NEXT: lxvx v2, 0, [[REG1]]
-; CHECK-NEXT: std r5, 48(r1)
+; CHECK-DAG: std r10, 88(r1)
+; CHECK-DAG: std r9, 80(r1)
+; CHECK-DAG: std r8, 72(r1)
+; CHECK-DAG: std r7, 64(r1)
+; CHECK-DAG: std r6, 56(r1)
+; CHECK-DAG: std r4, 40(r1)
+; CHECK-DAG: cmpwi cr0, r3, 1
+; CHECK-DAG: std r5, 48(r1)
+; CHECK-DAG: addis [[REG:r[0-9]+]], r2, .LCPI17_0@toc@ha
+; CHECK-DAG: addi [[REG1:r[0-9]+]], [[REG]], .LCPI17_0@toc@l
+; CHECK-DAG: lxvx v2, 0, [[REG1]]
; CHECK-NEXT: bltlr cr0
; CHECK-NEXT: # %bb.1: # %if.end
; CHECK-NEXT: addi r3, r1, 40
ret i64 %0
}
; CHECK-LABEL: @callee2
-; CHECK: ld 3, 128(1)
+; CHECK: ld {{[0-9]+}}, 128(1)
; CHECK: blr
declare i64 @test2(%struct.pad* byval, i32 signext, %struct.test* byval align 16)
; Setup frame pointer
; CHECK: add r7, sp, #8
; Register varargs stored via FP
-; CHECK: str r3, [r7, #16]
-; CHECK-NEXT: str r2, [r7, #12]
-; CHECK-NEXT: str r1, [r7, #8]
+; CHECK-DAG: str r3, [r7, #16]
+; CHECK-DAG: str r2, [r7, #12]
+; CHECK-DAG: str r1, [r7, #8]
; Moving SP, access via SP
; int test_args_moving_sp(int a, int b, int c, int d, int e) {
define void @test128(i128* %a) {
; CHECK-LABEL: test128:
-; CHECK: ldr r1, [r0, #4]
+; CHECK: ldr r1, [r0, #8]
; CHECK-NEXT: ldr r2, .LCPI8_0
; CHECK-NEXT: eors r2, r1
-; CHECK-NEXT: str r2, [r0, #4]
+; CHECK-NEXT: str r2, [r0, #8]
; CHECK-NEXT: ldr r1, [r0]
; CHECK-NEXT: ldr r2, .LCPI8_1
; CHECK-NEXT: eors r2, r1
; CHECK-NEXT: str r2, [r0]
-; CHECK-NEXT: ldr r1, [r0, #8]
+; CHECK-NEXT: ldr r1, [r0, #4]
; CHECK-NEXT: ldr r2, .LCPI8_2
; CHECK-NEXT: eors r2, r1
-; CHECK-NEXT: str r2, [r0, #8]
+; CHECK-NEXT: str r2, [r0, #4]
; CHECK-NEXT: bx lr
; CHECK-NEXT: .p2align 2
; CHECK-NEXT: .LCPI8_0:
-; CHECK-NEXT: .long 4075008415
+; CHECK-NEXT: .long 6692605
; CHECK-NEXT: .LCPI8_1:
; CHECK-NEXT: .long 2080661269
; CHECK-NEXT: .LCPI8_2:
-; CHECK-NEXT: .long 6692605
+; CHECK-NEXT: .long 4075008415
%x = load i128, i128* %a
%xn = xor i128 %x, 123456789123456789123456789
store i128 %xn, i128* %a
store i8* %overflow_arg_area.next, i8** %overflow_arg_area_p, align 8
; X32: leal 68(%esp), [[REG:%.*]]
; X32: movl [[REG]], 16(%esp)
-; X64: leaq 232(%rsp), [[REG:%.*]]
+; X64: leaq 256(%rsp), [[REG:%.*]]
; X64: movq [[REG]], 184(%rsp)
; X64: leaq 176(%rsp), %rdi
call void @qux(%struct.__va_list_tag* %arraydecay)
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X32-NEXT: movl {{[0-9]+}}(%esp), %edi
-; X32-NEXT: movl %edi, 12(%esi)
-; X32-NEXT: movl %edx, 8(%esi)
-; X32-NEXT: movl %ecx, 4(%esi)
+; X32-NEXT: movl %edi, 8(%esi)
+; X32-NEXT: movl %edx, 12(%esi)
; X32-NEXT: movl %eax, (%esi)
+; X32-NEXT: movl %ecx, 4(%esi)
; X32-NEXT: movl %esi, %eax
; X32-NEXT: leal -8(%ebp), %esp
; X32-NEXT: popl %esi
; CHECK: # %bb.0:
; CHECK-NEXT: vmovups (%rsi), %xmm0
; CHECK-NEXT: vmovups 16(%rsi), %xmm1
-; CHECK-NEXT: vmovups %xmm0, (%rdi)
; CHECK-NEXT: vmovups %xmm1, 16(%rdi)
+; CHECK-NEXT: vmovups %xmm0, (%rdi)
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: add8i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovaps (%rsi), %xmm0
; CHECK-NEXT: vmovaps 16(%rsi), %xmm1
-; CHECK-NEXT: vmovaps %xmm0, (%rdi)
; CHECK-NEXT: vmovaps %xmm1, 16(%rdi)
+; CHECK-NEXT: vmovaps %xmm0, (%rdi)
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: add4i64a16:
; X86-NEXT: .LBB33_2:
; X86-NEXT: notl %esi
; X86-NEXT: notl %edx
-; X86-NEXT: andl %esi, 4(%eax)
; X86-NEXT: andl %edx, (%eax)
+; X86-NEXT: andl %esi, 4(%eax)
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
; X86-NEXT: movl %edx, %esi
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: .LBB34_2:
-; X86-NEXT: orl %esi, 4(%eax)
; X86-NEXT: orl %edx, (%eax)
+; X86-NEXT: orl %esi, 4(%eax)
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
; X86-NEXT: movl %edx, %esi
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: .LBB35_2:
-; X86-NEXT: xorl %esi, 4(%eax)
; X86-NEXT: xorl %edx, (%eax)
+; X86-NEXT: xorl %esi, 4(%eax)
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
; X86-NEXT: movzbl %bl, %ecx
; X86-NEXT: subl %ecx, %edx
; X86-NEXT: sbbl $0, %ebp
-; X86-NEXT: movl %edi, 4(%eax)
; X86-NEXT: movl %esi, (%eax)
+; X86-NEXT: movl %edi, 4(%eax)
; X86-NEXT: movl %edx, 8(%eax)
; X86-NEXT: movl %ebp, 12(%eax)
; X86-NEXT: popl %esi
; CHECK-NEXT: movd %eax, %xmm0
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: mulss %xmm0, %xmm1
-; CHECK-NEXT: movq $0, (%rdi)
+; CHECK-NEXT: movl $0, (%rdi)
; CHECK-NEXT: movss %xmm1, 4(%rdi)
; CHECK-NEXT: retq
entry:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa (%rdi), %ymm0
; CHECK-NEXT: vmovdqa 32(%rdi), %ymm1
-; CHECK-NEXT: vpaddd (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vpaddd 32(%rsi), %ymm1, %ymm1
-; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
+; CHECK-NEXT: vpaddd (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vmovdqa %ymm0, (%rdx)
+; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%d = load <16 x i32>, <16 x i32>* %a
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa (%rdi), %ymm0
; CHECK-NEXT: vmovdqa 32(%rdi), %ymm1
-; CHECK-NEXT: vpmaddwd (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vpmaddwd 32(%rsi), %ymm1, %ymm1
-; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
+; CHECK-NEXT: vpmaddwd (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vmovdqa %ymm0, (%rdx)
+; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%A = load <32 x i16>, <32 x i16>* %APtr
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa (%rdi), %ymm0
; CHECK-NEXT: vmovdqa 32(%rdi), %ymm1
-; CHECK-NEXT: vpsubusb (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vpsubusb 32(%rsi), %ymm1, %ymm1
-; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
+; CHECK-NEXT: vpsubusb (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vmovdqa %ymm0, (%rdx)
+; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%x = load <64 x i8>, <64 x i8>* %xptr
; CHECK-NEXT: vmovdqa 32(%rdi), %ymm1
; CHECK-NEXT: vmovdqa (%rsi), %ymm2
; CHECK-NEXT: vmovdqa 32(%rsi), %ymm3
-; CHECK-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm2[8],ymm0[8],ymm2[9],ymm0[9],ymm2[10],ymm0[10],ymm2[11],ymm0[11],ymm2[12],ymm0[12],ymm2[13],ymm0[13],ymm2[14],ymm0[14],ymm2[15],ymm0[15],ymm2[24],ymm0[24],ymm2[25],ymm0[25],ymm2[26],ymm0[26],ymm2[27],ymm0[27],ymm2[28],ymm0[28],ymm2[29],ymm0[29],ymm2[30],ymm0[30],ymm2[31],ymm0[31]
-; CHECK-NEXT: vpunpckhbw {{.*#+}} ymm5 = ymm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15,24,24,25,25,26,26,27,27,28,28,29,29,30,30,31,31]
+; CHECK-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm3[8],ymm0[8],ymm3[9],ymm0[9],ymm3[10],ymm0[10],ymm3[11],ymm0[11],ymm3[12],ymm0[12],ymm3[13],ymm0[13],ymm3[14],ymm0[14],ymm3[15],ymm0[15],ymm3[24],ymm0[24],ymm3[25],ymm0[25],ymm3[26],ymm0[26],ymm3[27],ymm0[27],ymm3[28],ymm0[28],ymm3[29],ymm0[29],ymm3[30],ymm0[30],ymm3[31],ymm0[31]
+; CHECK-NEXT: vpunpckhbw {{.*#+}} ymm5 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31]
; CHECK-NEXT: vpmullw %ymm4, %ymm5, %ymm4
; CHECK-NEXT: vmovdqa {{.*#+}} ymm5 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; CHECK-NEXT: vpand %ymm5, %ymm4, %ymm4
-; CHECK-NEXT: vpunpcklbw {{.*#+}} ymm2 = ymm2[0],ymm0[0],ymm2[1],ymm0[1],ymm2[2],ymm0[2],ymm2[3],ymm0[3],ymm2[4],ymm0[4],ymm2[5],ymm0[5],ymm2[6],ymm0[6],ymm2[7],ymm0[7],ymm2[16],ymm0[16],ymm2[17],ymm0[17],ymm2[18],ymm0[18],ymm2[19],ymm0[19],ymm2[20],ymm0[20],ymm2[21],ymm0[21],ymm2[22],ymm0[22],ymm2[23],ymm0[23]
-; CHECK-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,16,16,17,17,18,18,19,19,20,20,21,21,22,22,23,23]
-; CHECK-NEXT: vpmullw %ymm2, %ymm0, %ymm0
-; CHECK-NEXT: vpand %ymm5, %ymm0, %ymm0
-; CHECK-NEXT: vpackuswb %ymm4, %ymm0, %ymm0
-; CHECK-NEXT: vpunpckhbw {{.*#+}} ymm2 = ymm3[8],ymm0[8],ymm3[9],ymm0[9],ymm3[10],ymm0[10],ymm3[11],ymm0[11],ymm3[12],ymm0[12],ymm3[13],ymm0[13],ymm3[14],ymm0[14],ymm3[15],ymm0[15],ymm3[24],ymm0[24],ymm3[25],ymm0[25],ymm3[26],ymm0[26],ymm3[27],ymm0[27],ymm3[28],ymm0[28],ymm3[29],ymm0[29],ymm3[30],ymm0[30],ymm3[31],ymm0[31]
-; CHECK-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31]
-; CHECK-NEXT: vpmullw %ymm2, %ymm4, %ymm2
-; CHECK-NEXT: vpand %ymm5, %ymm2, %ymm2
; CHECK-NEXT: vpunpcklbw {{.*#+}} ymm3 = ymm3[0],ymm0[0],ymm3[1],ymm0[1],ymm3[2],ymm0[2],ymm3[3],ymm0[3],ymm3[4],ymm0[4],ymm3[5],ymm0[5],ymm3[6],ymm0[6],ymm3[7],ymm0[7],ymm3[16],ymm0[16],ymm3[17],ymm0[17],ymm3[18],ymm0[18],ymm3[19],ymm0[19],ymm3[20],ymm0[20],ymm3[21],ymm0[21],ymm3[22],ymm0[22],ymm3[23],ymm0[23]
; CHECK-NEXT: vpunpcklbw {{.*#+}} ymm1 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
; CHECK-NEXT: vpmullw %ymm3, %ymm1, %ymm1
; CHECK-NEXT: vpand %ymm5, %ymm1, %ymm1
-; CHECK-NEXT: vpackuswb %ymm2, %ymm1, %ymm1
-; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
+; CHECK-NEXT: vpackuswb %ymm4, %ymm1, %ymm1
+; CHECK-NEXT: vpunpckhbw {{.*#+}} ymm3 = ymm2[8],ymm0[8],ymm2[9],ymm0[9],ymm2[10],ymm0[10],ymm2[11],ymm0[11],ymm2[12],ymm0[12],ymm2[13],ymm0[13],ymm2[14],ymm0[14],ymm2[15],ymm0[15],ymm2[24],ymm0[24],ymm2[25],ymm0[25],ymm2[26],ymm0[26],ymm2[27],ymm0[27],ymm2[28],ymm0[28],ymm2[29],ymm0[29],ymm2[30],ymm0[30],ymm2[31],ymm0[31]
+; CHECK-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15,24,24,25,25,26,26,27,27,28,28,29,29,30,30,31,31]
+; CHECK-NEXT: vpmullw %ymm3, %ymm4, %ymm3
+; CHECK-NEXT: vpand %ymm5, %ymm3, %ymm3
+; CHECK-NEXT: vpunpcklbw {{.*#+}} ymm2 = ymm2[0],ymm0[0],ymm2[1],ymm0[1],ymm2[2],ymm0[2],ymm2[3],ymm0[3],ymm2[4],ymm0[4],ymm2[5],ymm0[5],ymm2[6],ymm0[6],ymm2[7],ymm0[7],ymm2[16],ymm0[16],ymm2[17],ymm0[17],ymm2[18],ymm0[18],ymm2[19],ymm0[19],ymm2[20],ymm0[20],ymm2[21],ymm0[21],ymm2[22],ymm0[22],ymm2[23],ymm0[23]
+; CHECK-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,16,16,17,17,18,18,19,19,20,20,21,21,22,22,23,23]
+; CHECK-NEXT: vpmullw %ymm2, %ymm0, %ymm0
+; CHECK-NEXT: vpand %ymm5, %ymm0, %ymm0
+; CHECK-NEXT: vpackuswb %ymm3, %ymm0, %ymm0
; CHECK-NEXT: vmovdqa %ymm0, (%rdx)
+; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%d = load <64 x i8>, <64 x i8>* %a
; LINUX-NEXT: movaps %xmm6, {{[0-9]+}}(%rsp)
; LINUX-NEXT: movaps %xmm7, {{[0-9]+}}(%rsp)
; LINUX-NEXT: .LBB0_2:
-; LINUX-NEXT: movq %r15, {{[0-9]+}}(%rsp)
-; LINUX-NEXT: movq %r12, {{[0-9]+}}(%rsp)
-; LINUX-NEXT: movq %r13, {{[0-9]+}}(%rsp)
-; LINUX-NEXT: movq %rbp, {{[0-9]+}}(%rsp)
; LINUX-NEXT: movq %rbx, {{[0-9]+}}(%rsp)
+; LINUX-NEXT: movq %rbp, {{[0-9]+}}(%rsp)
+; LINUX-NEXT: movq %r13, {{[0-9]+}}(%rsp)
+; LINUX-NEXT: movq %r12, {{[0-9]+}}(%rsp)
+; LINUX-NEXT: movq %r15, {{[0-9]+}}(%rsp)
; LINUX-NEXT: leaq {{[0-9]+}}(%rsp), %rax
; LINUX-NEXT: movq %rax, {{[0-9]+}}(%rsp)
; LINUX-NEXT: leaq {{[0-9]+}}(%rsp), %rax
; LINUX-X32-NEXT: movaps %xmm6, {{[0-9]+}}(%esp)
; LINUX-X32-NEXT: movaps %xmm7, {{[0-9]+}}(%esp)
; LINUX-X32-NEXT: .LBB0_2:
-; LINUX-X32-NEXT: movq %r15, {{[0-9]+}}(%esp)
-; LINUX-X32-NEXT: movq %r12, {{[0-9]+}}(%esp)
-; LINUX-X32-NEXT: movq %r13, {{[0-9]+}}(%esp)
-; LINUX-X32-NEXT: movq %rbp, {{[0-9]+}}(%esp)
; LINUX-X32-NEXT: movq %rbx, {{[0-9]+}}(%esp)
+; LINUX-X32-NEXT: movq %rbp, {{[0-9]+}}(%esp)
+; LINUX-X32-NEXT: movq %r13, {{[0-9]+}}(%esp)
+; LINUX-X32-NEXT: movq %r12, {{[0-9]+}}(%esp)
+; LINUX-X32-NEXT: movq %r15, {{[0-9]+}}(%esp)
; LINUX-X32-NEXT: leal {{[0-9]+}}(%rsp), %eax
; LINUX-X32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; LINUX-X32-NEXT: leal {{[0-9]+}}(%rsp), %eax
; WINDOWS-NEXT: movq %r8, %rdi
; WINDOWS-NEXT: movq %rdx, %rbx
; WINDOWS-NEXT: movq %rcx, %rbp
-; WINDOWS-NEXT: movq %r9, {{[0-9]+}}(%rsp)
-; WINDOWS-NEXT: movq %r8, {{[0-9]+}}(%rsp)
; WINDOWS-NEXT: movq %rdx, {{[0-9]+}}(%rsp)
+; WINDOWS-NEXT: movq %r8, {{[0-9]+}}(%rsp)
+; WINDOWS-NEXT: movq %r9, {{[0-9]+}}(%rsp)
; WINDOWS-NEXT: leaq {{[0-9]+}}(%rsp), %rax
; WINDOWS-NEXT: movq %rax, {{[0-9]+}}(%rsp)
; WINDOWS-NEXT: callq get_f
; CHECK-LABEL: t4:
; CHECK: incl %[[r:.*]]
; CHECK: decl %[[n:.*]]
-; CHECK: movl %[[r]], {{[0-9]+}}(%esp)
-; CHECK: movl %[[n]], {{[0-9]+}}(%esp)
+; CHECK-DAG: movl %[[r]], {{[0-9]+}}(%esp)
+; CHECK-DAG: movl %[[n]], {{[0-9]+}}(%esp)
; CHECK: jmpl *%{{.*}}
entry:
; CHECK: incl %[[r:.*]]
; CHECK: decl %[[n:.*]]
; Store them through ebp, since that's the only stable arg pointer.
-; CHECK: movl %[[r]], {{[0-9]+}}(%ebp)
-; CHECK: movl %[[n]], {{[0-9]+}}(%ebp)
+; CHECK-DAG: movl %[[r]], {{[0-9]+}}(%ebp)
+; CHECK-DAG: movl %[[n]], {{[0-9]+}}(%ebp)
; Epilogue.
; CHECK: leal {{[-0-9]+}}(%ebp), %esp
; CHECK: popl %esi
; X32-NEXT: subl $48, %esp
; X32-NEXT: movl 8(%ebp), %eax
; X32-NEXT: movl 24(%eax), %ecx
-; X32-NEXT: movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X32-NEXT: movl 28(%eax), %ecx
; X32-NEXT: movl %ecx, (%esp) # 4-byte Spill
; X32-NEXT: movl 16(%eax), %esi
; X32-NEXT: movl %esi, {{[0-9]+}}(%esp)
; X32-NEXT: movl (%esp), %eax # 4-byte Reload
; X32-NEXT: movl %eax, {{[0-9]+}}(%esp)
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
; X32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; X32-NEXT: movl 12(%ebp), %eax
; X32-NEXT: fildll {{[0-9]+}}(%esp)
; X32-NEXT: adcl 4(%ecx), %edx
; X32-NEXT: addl 8(%ecx), %edi
; X32-NEXT: adcl 12(%ecx), %esi
-; X32-NEXT: movl %esi, 12(%eax)
; X32-NEXT: movl %edi, 8(%eax)
-; X32-NEXT: movl %edx, 4(%eax)
+; X32-NEXT: movl %esi, 12(%eax)
; X32-NEXT: movl %ebx, (%eax)
+; X32-NEXT: movl %edx, 4(%eax)
; X32-NEXT: popl %esi
; X32-NEXT: popl %edi
; X32-NEXT: popl %ebx
define void @interleave_24i32_in(<24 x i32>* %p, <8 x i32>* %q1, <8 x i32>* %q2, <8 x i32>* %q3) nounwind {
; SSE2-LABEL: interleave_24i32_in:
; SSE2: # %bb.0:
-; SSE2-NEXT: movups (%rsi), %xmm5
-; SSE2-NEXT: movups 16(%rsi), %xmm8
-; SSE2-NEXT: movups (%rdx), %xmm6
-; SSE2-NEXT: movups 16(%rdx), %xmm3
-; SSE2-NEXT: movups (%rcx), %xmm0
-; SSE2-NEXT: movups 16(%rcx), %xmm4
-; SSE2-NEXT: movaps %xmm0, %xmm7
-; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,0],xmm5[1,0]
-; SSE2-NEXT: movaps %xmm5, %xmm1
-; SSE2-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm6[0],xmm1[1],xmm6[1]
-; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm7[0,2]
+; SSE2-NEXT: movups (%rsi), %xmm1
+; SSE2-NEXT: movups 16(%rsi), %xmm0
+; SSE2-NEXT: movups (%rdx), %xmm8
+; SSE2-NEXT: movups 16(%rdx), %xmm5
+; SSE2-NEXT: movups (%rcx), %xmm3
+; SSE2-NEXT: movups 16(%rcx), %xmm6
+; SSE2-NEXT: movaps %xmm3, %xmm7
+; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,0],xmm1[1,0]
+; SSE2-NEXT: movaps %xmm1, %xmm9
+; SSE2-NEXT: unpcklps {{.*#+}} xmm9 = xmm9[0],xmm8[0],xmm9[1],xmm8[1]
+; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,1],xmm7[0,2]
; SSE2-NEXT: movaps %xmm5, %xmm7
-; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[2,0],xmm6[2,1]
-; SSE2-NEXT: movaps %xmm0, %xmm2
-; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,0],xmm6[1,0]
+; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[3,2],xmm6[3,2]
+; SSE2-NEXT: movaps %xmm6, %xmm4
+; SSE2-NEXT: unpckhps {{.*#+}} xmm4 = xmm4[2],xmm0[2],xmm4[3],xmm0[3]
+; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,3],xmm7[0,2]
+; SSE2-NEXT: movaps %xmm0, %xmm7
+; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[2,0],xmm5[2,1]
+; SSE2-NEXT: movaps %xmm6, %xmm2
+; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,0],xmm5[1,0]
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[2,0],xmm7[0,2]
-; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[3,2],xmm0[3,2]
-; SSE2-NEXT: unpckhps {{.*#+}} xmm0 = xmm0[2],xmm5[2],xmm0[3],xmm5[3]
-; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,3],xmm6[0,2]
-; SSE2-NEXT: movaps %xmm4, %xmm5
-; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,0],xmm8[1,0]
-; SSE2-NEXT: movaps %xmm8, %xmm6
-; SSE2-NEXT: unpcklps {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
-; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,1],xmm5[0,2]
+; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,0],xmm0[1,0]
+; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1]
+; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm6[0,2]
; SSE2-NEXT: movaps %xmm8, %xmm5
-; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[2,0],xmm3[2,1]
-; SSE2-NEXT: movaps %xmm4, %xmm7
-; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[1,0],xmm3[1,0]
-; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[2,0],xmm5[0,2]
-; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[3,2],xmm4[3,2]
-; SSE2-NEXT: unpckhps {{.*#+}} xmm4 = xmm4[2],xmm8[2],xmm4[3],xmm8[3]
-; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,3],xmm3[0,2]
+; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[3,2],xmm3[3,2]
+; SSE2-NEXT: movaps %xmm3, %xmm6
+; SSE2-NEXT: unpckhps {{.*#+}} xmm6 = xmm6[2],xmm1[2],xmm6[3],xmm1[3]
+; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,3],xmm5[0,2]
+; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm8[2,1]
+; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[1,0],xmm8[1,0]
+; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[2,0],xmm1[0,2]
+; SSE2-NEXT: movups %xmm3, 16(%rdi)
+; SSE2-NEXT: movups %xmm6, 32(%rdi)
+; SSE2-NEXT: movups %xmm0, 48(%rdi)
+; SSE2-NEXT: movups %xmm2, 64(%rdi)
; SSE2-NEXT: movups %xmm4, 80(%rdi)
-; SSE2-NEXT: movups %xmm7, 64(%rdi)
-; SSE2-NEXT: movups %xmm6, 48(%rdi)
-; SSE2-NEXT: movups %xmm0, 32(%rdi)
-; SSE2-NEXT: movups %xmm2, 16(%rdi)
-; SSE2-NEXT: movups %xmm1, (%rdi)
+; SSE2-NEXT: movups %xmm9, (%rdi)
; SSE2-NEXT: retq
;
; SSE42-LABEL: interleave_24i32_in:
; SSE42: # %bb.0:
-; SSE42-NEXT: movdqu (%rsi), %xmm5
-; SSE42-NEXT: movdqu 16(%rsi), %xmm2
-; SSE42-NEXT: movdqu (%rdx), %xmm6
-; SSE42-NEXT: movdqu 16(%rdx), %xmm1
-; SSE42-NEXT: movdqu (%rcx), %xmm7
-; SSE42-NEXT: movdqu 16(%rcx), %xmm4
-; SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm6[0,0,1,1]
-; SSE42-NEXT: pshufd {{.*#+}} xmm3 = xmm5[0,1,0,1]
-; SSE42-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0,1],xmm0[2,3],xmm3[4,5,6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm7[0,1,0,1]
-; SSE42-NEXT: pblendw {{.*#+}} xmm0 = xmm3[0,1,2,3],xmm0[4,5],xmm3[6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm3 = xmm6[1,1,2,2]
-; SSE42-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0,1],xmm7[2,3],xmm3[4,5,6,7]
-; SSE42-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0,1,2,3],xmm5[4,5],xmm3[6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm5 = xmm5[2,3,0,1]
-; SSE42-NEXT: pshufd {{.*#+}} xmm7 = xmm7[2,3,2,3]
-; SSE42-NEXT: pblendw {{.*#+}} xmm7 = xmm7[0,1],xmm5[2,3],xmm7[4,5,6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm5 = xmm6[2,2,3,3]
-; SSE42-NEXT: pblendw {{.*#+}} xmm5 = xmm7[0,1,2,3],xmm5[4,5],xmm7[6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm6 = xmm1[0,0,1,1]
-; SSE42-NEXT: pshufd {{.*#+}} xmm7 = xmm2[0,1,0,1]
-; SSE42-NEXT: pblendw {{.*#+}} xmm7 = xmm7[0,1],xmm6[2,3],xmm7[4,5,6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm6 = xmm4[0,1,0,1]
-; SSE42-NEXT: pblendw {{.*#+}} xmm6 = xmm7[0,1,2,3],xmm6[4,5],xmm7[6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm7 = xmm1[1,1,2,2]
-; SSE42-NEXT: pblendw {{.*#+}} xmm7 = xmm7[0,1],xmm4[2,3],xmm7[4,5,6,7]
-; SSE42-NEXT: pblendw {{.*#+}} xmm7 = xmm7[0,1,2,3],xmm2[4,5],xmm7[6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
-; SSE42-NEXT: pshufd {{.*#+}} xmm4 = xmm4[2,3,2,3]
-; SSE42-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm2[2,3],xmm4[4,5,6,7]
-; SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,2,3,3]
-; SSE42-NEXT: pblendw {{.*#+}} xmm1 = xmm4[0,1,2,3],xmm1[4,5],xmm4[6,7]
-; SSE42-NEXT: movdqu %xmm1, 80(%rdi)
-; SSE42-NEXT: movdqu %xmm7, 64(%rdi)
-; SSE42-NEXT: movdqu %xmm6, 48(%rdi)
-; SSE42-NEXT: movdqu %xmm5, 32(%rdi)
-; SSE42-NEXT: movdqu %xmm3, 16(%rdi)
-; SSE42-NEXT: movdqu %xmm0, (%rdi)
+; SSE42-NEXT: movdqu (%rsi), %xmm8
+; SSE42-NEXT: movdqu 16(%rsi), %xmm4
+; SSE42-NEXT: movdqu (%rdx), %xmm2
+; SSE42-NEXT: movdqu 16(%rdx), %xmm5
+; SSE42-NEXT: movdqu (%rcx), %xmm3
+; SSE42-NEXT: movdqu 16(%rcx), %xmm6
+; SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,0,1,1]
+; SSE42-NEXT: pshufd {{.*#+}} xmm7 = xmm8[0,1,0,1]
+; SSE42-NEXT: pblendw {{.*#+}} xmm7 = xmm7[0,1],xmm1[2,3],xmm7[4,5,6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm3[0,1,0,1]
+; SSE42-NEXT: pblendw {{.*#+}} xmm1 = xmm7[0,1,2,3],xmm1[4,5],xmm7[6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm7 = xmm4[2,3,0,1]
+; SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm6[2,3,2,3]
+; SSE42-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm7[2,3],xmm0[4,5,6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm7 = xmm5[2,2,3,3]
+; SSE42-NEXT: pblendw {{.*#+}} xmm7 = xmm0[0,1,2,3],xmm7[4,5],xmm0[6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm5[1,1,2,2]
+; SSE42-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm6[2,3],xmm0[4,5,6,7]
+; SSE42-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm4[4,5],xmm0[6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm5 = xmm5[0,0,1,1]
+; SSE42-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,1,0,1]
+; SSE42-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm5[2,3],xmm4[4,5,6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm5 = xmm6[0,1,0,1]
+; SSE42-NEXT: pblendw {{.*#+}} xmm5 = xmm4[0,1,2,3],xmm5[4,5],xmm4[6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm4 = xmm8[2,3,0,1]
+; SSE42-NEXT: pshufd {{.*#+}} xmm6 = xmm3[2,3,2,3]
+; SSE42-NEXT: pblendw {{.*#+}} xmm6 = xmm6[0,1],xmm4[2,3],xmm6[4,5,6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm4 = xmm2[2,2,3,3]
+; SSE42-NEXT: pblendw {{.*#+}} xmm4 = xmm6[0,1,2,3],xmm4[4,5],xmm6[6,7]
+; SSE42-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,2,2]
+; SSE42-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1],xmm3[2,3],xmm2[4,5,6,7]
+; SSE42-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm8[4,5],xmm2[6,7]
+; SSE42-NEXT: movdqu %xmm2, 16(%rdi)
+; SSE42-NEXT: movdqu %xmm4, 32(%rdi)
+; SSE42-NEXT: movdqu %xmm5, 48(%rdi)
+; SSE42-NEXT: movdqu %xmm0, 64(%rdi)
+; SSE42-NEXT: movdqu %xmm7, 80(%rdi)
+; SSE42-NEXT: movdqu %xmm1, (%rdi)
; SSE42-NEXT: retq
;
; AVX1-LABEL: interleave_24i32_in:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovupd (%rsi), %ymm0
; AVX1-NEXT: vmovupd (%rcx), %ymm1
-; AVX1-NEXT: vmovups (%rdx), %xmm2
-; AVX1-NEXT: vmovups 16(%rdx), %xmm3
-; AVX1-NEXT: vmovups (%rsi), %xmm4
-; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm4[2,0],xmm2[2,0]
-; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm2[1,1],xmm5[0,2]
-; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[0,0],xmm4[0,0]
-; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[2,0],xmm4[2,1]
+; AVX1-NEXT: vmovups 16(%rcx), %xmm2
+; AVX1-NEXT: vmovups (%rdx), %xmm3
+; AVX1-NEXT: vmovups 16(%rdx), %xmm4
+; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm4[3,0],xmm2[3,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm2[2,1],xmm5[0,2]
+; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[1,0],xmm4[1,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[2,0],xmm4[2,2]
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm2, %ymm2
-; AVX1-NEXT: vmovddup {{.*#+}} xmm4 = xmm1[0,0]
-; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm4, %ymm4
-; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3,4],ymm4[5],ymm2[6,7]
-; AVX1-NEXT: vmovups 16(%rcx), %xmm4
-; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm3[3,0],xmm4[3,0]
-; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm4[2,1],xmm5[0,2]
-; AVX1-NEXT: vshufps {{.*#+}} xmm4 = xmm4[1,0],xmm3[1,0]
-; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm4[2,0],xmm3[2,2]
-; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
; AVX1-NEXT: vpermilpd {{.*#+}} ymm4 = ymm0[1,1,3,3]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm4 = ymm4[2,3,2,3]
+; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3,4],ymm4[5],ymm2[6,7]
+; AVX1-NEXT: vmovups (%rsi), %xmm4
+; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm4[2,0],xmm3[2,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm3[1,1],xmm5[0,2]
+; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm3[0,0],xmm4[0,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm3[2,0],xmm4[2,1]
+; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
+; AVX1-NEXT: vmovddup {{.*#+}} xmm4 = xmm1[0,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm4, %ymm4
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1],ymm4[2],ymm3[3,4],ymm4[5],ymm3[6,7]
; AVX1-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,2]
; AVX1-NEXT: vpermilpd {{.*#+}} ymm1 = ymm1[1,1,2,2]
; AVX1-NEXT: vpermilps {{.*#+}} ymm1 = mem[0,0,3,3,4,4,7,7]
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3,4],ymm1[5],ymm0[6,7]
; AVX1-NEXT: vmovups %ymm0, 32(%rdi)
-; AVX1-NEXT: vmovups %ymm3, 64(%rdi)
-; AVX1-NEXT: vmovups %ymm2, (%rdi)
+; AVX1-NEXT: vmovups %ymm3, (%rdi)
+; AVX1-NEXT: vmovups %ymm2, 64(%rdi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0],ymm4[1],ymm3[2,3],ymm4[4],ymm3[5,6],ymm4[7]
; AVX2-FAST-NEXT: vpermpd {{.*#+}} ymm4 = ymm0[0,3,3,3]
; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1],ymm4[2],ymm3[3,4],ymm4[5],ymm3[6,7]
-; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm4 = [1,0,2,2,1,0,2,2]
-; AVX2-FAST-NEXT: vpermps %ymm1, %ymm4, %ymm4
-; AVX2-FAST-NEXT: vpermpd {{.*#+}} ymm5 = ymm0[0,0,2,1]
-; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm4 = ymm5[0],ymm4[1],ymm5[2,3],ymm4[4],ymm5[5,6],ymm4[7]
-; AVX2-FAST-NEXT: vbroadcastsd (%rcx), %ymm5
-; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm4 = ymm4[0,1],ymm5[2],ymm4[3,4],ymm5[5],ymm4[6,7]
-; AVX2-FAST-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[1,1,2,2]
+; AVX2-FAST-NEXT: vpermpd {{.*#+}} ymm4 = ymm0[1,1,2,2]
; AVX2-FAST-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[1,1,2,2]
-; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0],ymm0[1],ymm2[2,3],ymm0[4],ymm2[5,6],ymm0[7]
-; AVX2-FAST-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,0,3,3,4,4,7,7]
+; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0],ymm4[1],ymm2[2,3],ymm4[4],ymm2[5,6],ymm4[7]
+; AVX2-FAST-NEXT: vpermilps {{.*#+}} ymm4 = ymm1[0,0,3,3,4,4,7,7]
+; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3,4],ymm4[5],ymm2[6,7]
+; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm4 = [1,0,2,2,1,0,2,2]
+; AVX2-FAST-NEXT: vpermps %ymm1, %ymm4, %ymm1
+; AVX2-FAST-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,0,2,1]
+; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3],ymm1[4],ymm0[5,6],ymm1[7]
+; AVX2-FAST-NEXT: vbroadcastsd (%rcx), %ymm1
; AVX2-FAST-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3,4],ymm1[5],ymm0[6,7]
-; AVX2-FAST-NEXT: vmovups %ymm0, 32(%rdi)
-; AVX2-FAST-NEXT: vmovups %ymm4, (%rdi)
+; AVX2-FAST-NEXT: vmovups %ymm0, (%rdi)
+; AVX2-FAST-NEXT: vmovups %ymm2, 32(%rdi)
; AVX2-FAST-NEXT: vmovups %ymm3, 64(%rdi)
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
; XOP: # %bb.0:
; XOP-NEXT: vmovupd (%rsi), %ymm0
; XOP-NEXT: vmovups (%rcx), %ymm1
-; XOP-NEXT: vmovups (%rdx), %xmm2
-; XOP-NEXT: vmovups 16(%rdx), %xmm3
-; XOP-NEXT: vmovups (%rsi), %xmm4
-; XOP-NEXT: vshufps {{.*#+}} xmm5 = xmm4[2,0],xmm2[2,0]
-; XOP-NEXT: vshufps {{.*#+}} xmm5 = xmm2[1,1],xmm5[0,2]
-; XOP-NEXT: vshufps {{.*#+}} xmm2 = xmm2[0,0],xmm4[0,0]
-; XOP-NEXT: vshufps {{.*#+}} xmm2 = xmm2[2,0],xmm4[2,1]
+; XOP-NEXT: vmovups 16(%rcx), %xmm2
+; XOP-NEXT: vmovups (%rdx), %xmm3
+; XOP-NEXT: vmovups 16(%rdx), %xmm4
+; XOP-NEXT: vshufps {{.*#+}} xmm5 = xmm4[3,0],xmm2[3,0]
+; XOP-NEXT: vshufps {{.*#+}} xmm5 = xmm2[2,1],xmm5[0,2]
+; XOP-NEXT: vshufps {{.*#+}} xmm2 = xmm2[1,0],xmm4[1,0]
+; XOP-NEXT: vshufps {{.*#+}} xmm2 = xmm2[2,0],xmm4[2,2]
; XOP-NEXT: vinsertf128 $1, %xmm5, %ymm2, %ymm2
-; XOP-NEXT: vmovddup {{.*#+}} xmm4 = xmm1[0,0]
-; XOP-NEXT: vinsertf128 $1, %xmm4, %ymm4, %ymm4
-; XOP-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3,4],ymm4[5],ymm2[6,7]
-; XOP-NEXT: vmovups 16(%rcx), %xmm4
-; XOP-NEXT: vshufps {{.*#+}} xmm5 = xmm3[3,0],xmm4[3,0]
-; XOP-NEXT: vshufps {{.*#+}} xmm5 = xmm4[2,1],xmm5[0,2]
-; XOP-NEXT: vshufps {{.*#+}} xmm4 = xmm4[1,0],xmm3[1,0]
-; XOP-NEXT: vshufps {{.*#+}} xmm3 = xmm4[2,0],xmm3[2,2]
-; XOP-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
; XOP-NEXT: vpermilpd {{.*#+}} ymm4 = ymm0[1,1,3,3]
; XOP-NEXT: vperm2f128 {{.*#+}} ymm4 = ymm4[2,3,2,3]
+; XOP-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3,4],ymm4[5],ymm2[6,7]
+; XOP-NEXT: vmovups (%rsi), %xmm4
+; XOP-NEXT: vshufps {{.*#+}} xmm5 = xmm4[2,0],xmm3[2,0]
+; XOP-NEXT: vshufps {{.*#+}} xmm5 = xmm3[1,1],xmm5[0,2]
+; XOP-NEXT: vshufps {{.*#+}} xmm3 = xmm3[0,0],xmm4[0,0]
+; XOP-NEXT: vshufps {{.*#+}} xmm3 = xmm3[2,0],xmm4[2,1]
+; XOP-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
+; XOP-NEXT: vmovddup {{.*#+}} xmm4 = xmm1[0,0]
+; XOP-NEXT: vinsertf128 $1, %xmm4, %ymm4, %ymm4
; XOP-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1],ymm4[2],ymm3[3,4],ymm4[5],ymm3[6,7]
; XOP-NEXT: vpermil2ps {{.*#+}} ymm0 = ymm1[2],ymm0[3],ymm1[2,3],ymm0[4],ymm1[5,4],ymm0[5]
; XOP-NEXT: vpermilps {{.*#+}} ymm1 = mem[0,0,3,3,4,4,7,7]
; XOP-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3,4],ymm1[5],ymm0[6,7]
; XOP-NEXT: vmovups %ymm0, 32(%rdi)
-; XOP-NEXT: vmovups %ymm3, 64(%rdi)
-; XOP-NEXT: vmovups %ymm2, (%rdi)
+; XOP-NEXT: vmovups %ymm3, (%rdi)
+; XOP-NEXT: vmovups %ymm2, 64(%rdi)
; XOP-NEXT: vzeroupper
; XOP-NEXT: retq
%s1 = load <8 x i32>, <8 x i32>* %q1, align 4
; CHECK-NEXT: movq (%rdi), %rax
; CHECK-NEXT: xorps %xmm0, %xmm0
; CHECK-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT: movq $0, {{[0-9]+}}(%rsp)
+; CHECK-NEXT: movq $170, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movaps {{.*#+}} xmm0 = [12297829382473034410,12297829382473034410]
; CHECK-NEXT: movaps %xmm0, (%rsp)
; CHECK-NEXT: movabsq $-6148914691236517206, %rcx # imm = 0xAAAAAAAAAAAAAAAA
; CHECK-NEXT: movq %rcx, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movq %rcx, {{[0-9]+}}(%rsp)
-; CHECK-NEXT: movb $-86, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movzwl 2(%rax), %ecx
; CHECK-NEXT: andl $8191, %ecx # imm = 0x1FFF
; CHECK-NEXT: movl %ecx, {{[0-9]+}}(%rsp)
; X86-NEXT: movl %edx, %esi
; X86-NEXT: shldl $31, %ecx, %esi
; X86-NEXT: shldl $31, %edx, %ecx
-; X86-NEXT: movl %ecx, 4(%eax)
; X86-NEXT: movl %esi, (%eax)
+; X86-NEXT: movl %ecx, 4(%eax)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X86-NEXT: .cfi_offset %ebp, -8
; X86-NEXT: movb {{[0-9]+}}(%esp), %cl
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT: movl (%eax), %edx
+; X86-NEXT: movl (%eax), %esi
; X86-NEXT: movl 4(%eax), %ebx
-; X86-NEXT: movl %edx, %esi
-; X86-NEXT: shll %cl, %esi
+; X86-NEXT: movl %esi, %edx
+; X86-NEXT: shll %cl, %edx
; X86-NEXT: movl %ebx, %edi
-; X86-NEXT: shldl %cl, %edx, %edi
+; X86-NEXT: shldl %cl, %esi, %edi
; X86-NEXT: testb $32, %cl
; X86-NEXT: je .LBB6_2
; X86-NEXT: # %bb.1:
-; X86-NEXT: movl %esi, %edi
-; X86-NEXT: xorl %esi, %esi
+; X86-NEXT: movl %edx, %edi
+; X86-NEXT: xorl %edx, %edx
; X86-NEXT: .LBB6_2:
; X86-NEXT: negb %cl
; X86-NEXT: movl %ebx, %ebp
; X86-NEXT: shrl %cl, %ebp
-; X86-NEXT: shrdl %cl, %ebx, %edx
+; X86-NEXT: shrdl %cl, %ebx, %esi
; X86-NEXT: testb $32, %cl
; X86-NEXT: je .LBB6_4
; X86-NEXT: # %bb.3:
-; X86-NEXT: movl %ebp, %edx
+; X86-NEXT: movl %ebp, %esi
; X86-NEXT: xorl %ebp, %ebp
; X86-NEXT: .LBB6_4:
+; X86-NEXT: orl %esi, %edx
; X86-NEXT: orl %ebp, %edi
-; X86-NEXT: orl %edx, %esi
+; X86-NEXT: movl %edx, (%eax)
; X86-NEXT: movl %edi, 4(%eax)
-; X86-NEXT: movl %esi, (%eax)
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 16
; X86-NEXT: popl %edi
; X86-NEXT: movl %ebp, %esi
; X86-NEXT: xorl %ebp, %ebp
; X86-NEXT: .LBB7_4:
-; X86-NEXT: orl %esi, %edx
; X86-NEXT: orl %ebp, %edi
-; X86-NEXT: movl %edx, 4(%eax)
+; X86-NEXT: orl %esi, %edx
; X86-NEXT: movl %edi, (%eax)
+; X86-NEXT: movl %edx, 4(%eax)
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 16
; X86-NEXT: popl %edi
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %xmm0
; AVX1-NEXT: vmovdqa 16(%rdi), %xmm1
-; AVX1-NEXT: vpaddsw (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vpaddsw 16(%rsi), %xmm1, %xmm1
-; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
+; AVX1-NEXT: vpaddsw (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vmovdqa %xmm0, (%rdx)
+; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
; AVX1-NEXT: retq
;
; AVX2-LABEL: v12i16:
; X32-NEXT: movl %esi, %edx
; X32-NEXT: xorl %esi, %esi
; X32-NEXT: .LBB5_2:
-; X32-NEXT: movl %esi, 4(%eax)
; X32-NEXT: movl %edx, (%eax)
+; X32-NEXT: movl %esi, 4(%eax)
; X32-NEXT: popl %esi
; X32-NEXT: popl %edi
; X32-NEXT: retl
; X86-SSE-NEXT: pmulhuw %xmm0, %xmm4
; X86-SSE-NEXT: pmullw %xmm0, %xmm2
; X86-SSE-NEXT: movdqa %xmm2, %xmm0
-; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; X86-SSE-NEXT: movdqa %xmm3, %xmm4
; X86-SSE-NEXT: pmulhuw %xmm1, %xmm4
; X86-SSE-NEXT: pmullw %xmm1, %xmm3
; X86-SSE-NEXT: movdqa %xmm3, %xmm1
-; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; X86-SSE-NEXT: movdqu %xmm3, 48(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm1, 32(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm2, 16(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm0, (%esi,%ecx,4)
+; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
+; X86-SSE-NEXT: movdqu %xmm3, 32(%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm1, 48(%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm2, (%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm0, 16(%esi,%ecx,4)
; X86-SSE-NEXT: popl %esi
; X86-SSE-NEXT: retl
;
; X64-SSE-NEXT: pmulhuw %xmm0, %xmm4
; X64-SSE-NEXT: pmullw %xmm0, %xmm2
; X64-SSE-NEXT: movdqa %xmm2, %xmm0
-; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; X64-SSE-NEXT: movdqa %xmm3, %xmm4
; X64-SSE-NEXT: pmulhuw %xmm1, %xmm4
; X64-SSE-NEXT: pmullw %xmm1, %xmm3
; X64-SSE-NEXT: movdqa %xmm3, %xmm1
-; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; X64-SSE-NEXT: movdqu %xmm3, 48(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm1, 32(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm2, 16(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm0, (%rax,%rdx,4)
+; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
+; X64-SSE-NEXT: movdqu %xmm3, 32(%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm1, 48(%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm2, (%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm0, 16(%rax,%rdx,4)
; X64-SSE-NEXT: retq
;
; X64-AVX1-LABEL: mul_16xi16:
; X86-SSE-NEXT: pmulhw %xmm0, %xmm4
; X86-SSE-NEXT: pmullw %xmm0, %xmm2
; X86-SSE-NEXT: movdqa %xmm2, %xmm0
-; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; X86-SSE-NEXT: movdqa %xmm3, %xmm4
; X86-SSE-NEXT: pmulhw %xmm1, %xmm4
; X86-SSE-NEXT: pmullw %xmm1, %xmm3
; X86-SSE-NEXT: movdqa %xmm3, %xmm1
-; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; X86-SSE-NEXT: movdqu %xmm3, 48(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm1, 32(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm2, 16(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm0, (%esi,%ecx,4)
+; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
+; X86-SSE-NEXT: movdqu %xmm3, 32(%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm1, 48(%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm2, (%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm0, 16(%esi,%ecx,4)
; X86-SSE-NEXT: popl %esi
; X86-SSE-NEXT: retl
;
; X64-SSE-NEXT: pmulhw %xmm0, %xmm4
; X64-SSE-NEXT: pmullw %xmm0, %xmm2
; X64-SSE-NEXT: movdqa %xmm2, %xmm0
-; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; X64-SSE-NEXT: movdqa %xmm3, %xmm4
; X64-SSE-NEXT: pmulhw %xmm1, %xmm4
; X64-SSE-NEXT: pmullw %xmm1, %xmm3
; X64-SSE-NEXT: movdqa %xmm3, %xmm1
-; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; X64-SSE-NEXT: movdqu %xmm3, 48(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm1, 32(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm2, 16(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm0, (%rax,%rdx,4)
+; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
+; X64-SSE-NEXT: movdqu %xmm3, 32(%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm1, 48(%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm2, (%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm0, 16(%rax,%rdx,4)
; X64-SSE-NEXT: retq
;
; X64-AVX1-LABEL: mul_16xi16_sext:
; X86-SSE-NEXT: pmulhuw %xmm0, %xmm4
; X86-SSE-NEXT: pmullw %xmm0, %xmm2
; X86-SSE-NEXT: movdqa %xmm2, %xmm0
-; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; X86-SSE-NEXT: movdqa %xmm3, %xmm4
; X86-SSE-NEXT: pmulhuw %xmm1, %xmm4
; X86-SSE-NEXT: pmullw %xmm1, %xmm3
; X86-SSE-NEXT: movdqa %xmm3, %xmm1
-; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; X86-SSE-NEXT: movdqu %xmm3, 48(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm1, 32(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm2, 16(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm0, (%esi,%ecx,4)
+; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
+; X86-SSE-NEXT: movdqu %xmm3, 32(%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm1, 48(%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm2, (%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm0, 16(%esi,%ecx,4)
; X86-SSE-NEXT: popl %esi
; X86-SSE-NEXT: retl
;
; X64-SSE-NEXT: pmulhuw %xmm0, %xmm4
; X64-SSE-NEXT: pmullw %xmm0, %xmm2
; X64-SSE-NEXT: movdqa %xmm2, %xmm0
-; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; X64-SSE-NEXT: movdqa %xmm3, %xmm4
; X64-SSE-NEXT: pmulhuw %xmm1, %xmm4
; X64-SSE-NEXT: pmullw %xmm1, %xmm3
; X64-SSE-NEXT: movdqa %xmm3, %xmm1
-; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; X64-SSE-NEXT: movdqu %xmm3, 48(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm1, 32(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm2, 16(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm0, (%rax,%rdx,4)
+; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
+; X64-SSE-NEXT: movdqu %xmm3, 32(%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm1, 48(%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm2, (%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm0, 16(%rax,%rdx,4)
; X64-SSE-NEXT: retq
;
; X64-AVX1-LABEL: mul_16xi16:
; X86-SSE-NEXT: pmulhw %xmm0, %xmm4
; X86-SSE-NEXT: pmullw %xmm0, %xmm2
; X86-SSE-NEXT: movdqa %xmm2, %xmm0
-; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; X86-SSE-NEXT: movdqa %xmm3, %xmm4
; X86-SSE-NEXT: pmulhw %xmm1, %xmm4
; X86-SSE-NEXT: pmullw %xmm1, %xmm3
; X86-SSE-NEXT: movdqa %xmm3, %xmm1
-; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; X86-SSE-NEXT: movdqu %xmm3, 48(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm1, 32(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm2, 16(%esi,%ecx,4)
-; X86-SSE-NEXT: movdqu %xmm0, (%esi,%ecx,4)
+; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
+; X86-SSE-NEXT: movdqu %xmm3, 32(%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm1, 48(%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm2, (%esi,%ecx,4)
+; X86-SSE-NEXT: movdqu %xmm0, 16(%esi,%ecx,4)
; X86-SSE-NEXT: popl %esi
; X86-SSE-NEXT: retl
;
; X64-SSE-NEXT: pmulhw %xmm0, %xmm4
; X64-SSE-NEXT: pmullw %xmm0, %xmm2
; X64-SSE-NEXT: movdqa %xmm2, %xmm0
-; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
-; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; X64-SSE-NEXT: movdqa %xmm3, %xmm4
; X64-SSE-NEXT: pmulhw %xmm1, %xmm4
; X64-SSE-NEXT: pmullw %xmm1, %xmm3
; X64-SSE-NEXT: movdqa %xmm3, %xmm1
-; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; X64-SSE-NEXT: movdqu %xmm3, 48(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm1, 32(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm2, 16(%rax,%rdx,4)
-; X64-SSE-NEXT: movdqu %xmm0, (%rax,%rdx,4)
+; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
+; X64-SSE-NEXT: movdqu %xmm3, 32(%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm1, 48(%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm2, (%rax,%rdx,4)
+; X64-SSE-NEXT: movdqu %xmm0, 16(%rax,%rdx,4)
; X64-SSE-NEXT: retq
;
; X64-AVX1-LABEL: mul_16xi16_sext:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %xmm0
; AVX1-NEXT: vmovdqa 16(%rdi), %xmm1
-; AVX1-NEXT: vpsubsw (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vpsubsw 16(%rsi), %xmm1, %xmm1
-; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
+; AVX1-NEXT: vpsubsw (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vmovdqa %xmm0, (%rdx)
+; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
; AVX1-NEXT: retq
;
; AVX2-LABEL: v12i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %xmm0
; AVX1-NEXT: vmovdqa 16(%rdi), %xmm1
-; AVX1-NEXT: vpaddusw (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vpaddusw 16(%rsi), %xmm1, %xmm1
-; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
+; AVX1-NEXT: vpaddusw (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vmovdqa %xmm0, (%rdx)
+; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
; AVX1-NEXT: retq
;
; AVX2-LABEL: v12i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %xmm0
; AVX1-NEXT: vmovdqa 16(%rdi), %xmm1
-; AVX1-NEXT: vpsubusw (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vpsubusw 16(%rsi), %xmm1, %xmm1
-; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
+; AVX1-NEXT: vpsubusw (%rsi), %xmm0, %xmm0
; AVX1-NEXT: vmovdqa %xmm0, (%rdx)
+; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
; AVX1-NEXT: retq
;
; AVX2-LABEL: v12i16:
; CHECK-NEXT: movaps %xmm6, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movaps %xmm7, {{[0-9]+}}(%rsp)
; CHECK-NEXT: LBB0_2: ## %entry
-; CHECK-NEXT: movq %r9, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: movq %r8, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: movq %rcx, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: movq %rdx, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movq %rsi, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT: movq %rdx, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT: movq %rcx, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT: movq %r8, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT: movq %r9, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testl $512, %edi ## imm = 0x200
; CHECK-NEXT: je LBB0_4
; X32-SSE: # %bb.0: # %entry
; X32-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x08]
; X32-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx # encoding: [0x8b,0x4c,0x24,0x04]
-; X32-SSE-NEXT: cvtps2pd (%ecx), %xmm0 # encoding: [0x0f,0x5a,0x01]
-; X32-SSE-NEXT: cvtps2pd 8(%ecx), %xmm1 # encoding: [0x0f,0x5a,0x49,0x08]
-; X32-SSE-NEXT: cvtps2pd 16(%ecx), %xmm2 # encoding: [0x0f,0x5a,0x51,0x10]
-; X32-SSE-NEXT: cvtps2pd 24(%ecx), %xmm3 # encoding: [0x0f,0x5a,0x59,0x18]
-; X32-SSE-NEXT: movups %xmm3, 48(%eax) # encoding: [0x0f,0x11,0x58,0x30]
-; X32-SSE-NEXT: movups %xmm2, 32(%eax) # encoding: [0x0f,0x11,0x50,0x20]
-; X32-SSE-NEXT: movups %xmm1, 16(%eax) # encoding: [0x0f,0x11,0x48,0x10]
-; X32-SSE-NEXT: movups %xmm0, (%eax) # encoding: [0x0f,0x11,0x00]
+; X32-SSE-NEXT: cvtps2pd 8(%ecx), %xmm0 # encoding: [0x0f,0x5a,0x41,0x08]
+; X32-SSE-NEXT: cvtps2pd (%ecx), %xmm1 # encoding: [0x0f,0x5a,0x09]
+; X32-SSE-NEXT: cvtps2pd 24(%ecx), %xmm2 # encoding: [0x0f,0x5a,0x51,0x18]
+; X32-SSE-NEXT: cvtps2pd 16(%ecx), %xmm3 # encoding: [0x0f,0x5a,0x59,0x10]
+; X32-SSE-NEXT: movups %xmm3, 32(%eax) # encoding: [0x0f,0x11,0x58,0x20]
+; X32-SSE-NEXT: movups %xmm2, 48(%eax) # encoding: [0x0f,0x11,0x50,0x30]
+; X32-SSE-NEXT: movups %xmm1, (%eax) # encoding: [0x0f,0x11,0x08]
+; X32-SSE-NEXT: movups %xmm0, 16(%eax) # encoding: [0x0f,0x11,0x40,0x10]
; X32-SSE-NEXT: retl # encoding: [0xc3]
;
; X32-AVX-LABEL: fpext_frommem8:
;
; X64-SSE-LABEL: fpext_frommem8:
; X64-SSE: # %bb.0: # %entry
-; X64-SSE-NEXT: cvtps2pd (%rdi), %xmm0 # encoding: [0x0f,0x5a,0x07]
-; X64-SSE-NEXT: cvtps2pd 8(%rdi), %xmm1 # encoding: [0x0f,0x5a,0x4f,0x08]
-; X64-SSE-NEXT: cvtps2pd 16(%rdi), %xmm2 # encoding: [0x0f,0x5a,0x57,0x10]
-; X64-SSE-NEXT: cvtps2pd 24(%rdi), %xmm3 # encoding: [0x0f,0x5a,0x5f,0x18]
-; X64-SSE-NEXT: movups %xmm3, 48(%rsi) # encoding: [0x0f,0x11,0x5e,0x30]
-; X64-SSE-NEXT: movups %xmm2, 32(%rsi) # encoding: [0x0f,0x11,0x56,0x20]
-; X64-SSE-NEXT: movups %xmm1, 16(%rsi) # encoding: [0x0f,0x11,0x4e,0x10]
-; X64-SSE-NEXT: movups %xmm0, (%rsi) # encoding: [0x0f,0x11,0x06]
+; X64-SSE-NEXT: cvtps2pd 8(%rdi), %xmm0 # encoding: [0x0f,0x5a,0x47,0x08]
+; X64-SSE-NEXT: cvtps2pd (%rdi), %xmm1 # encoding: [0x0f,0x5a,0x0f]
+; X64-SSE-NEXT: cvtps2pd 24(%rdi), %xmm2 # encoding: [0x0f,0x5a,0x57,0x18]
+; X64-SSE-NEXT: cvtps2pd 16(%rdi), %xmm3 # encoding: [0x0f,0x5a,0x5f,0x10]
+; X64-SSE-NEXT: movups %xmm3, 32(%rsi) # encoding: [0x0f,0x11,0x5e,0x20]
+; X64-SSE-NEXT: movups %xmm2, 48(%rsi) # encoding: [0x0f,0x11,0x56,0x30]
+; X64-SSE-NEXT: movups %xmm1, (%rsi) # encoding: [0x0f,0x11,0x0e]
+; X64-SSE-NEXT: movups %xmm0, 16(%rsi) # encoding: [0x0f,0x11,0x46,0x10]
; X64-SSE-NEXT: retq # encoding: [0xc3]
;
; X64-AVX-LABEL: fpext_frommem8:
; CHECK-NEXT: movdqa 16(%edx,%eax), %xmm2
; CHECK-NEXT: psubw %xmm0, %xmm1
; CHECK-NEXT: psubw %xmm0, %xmm2
-; CHECK-NEXT: pextrd $2, %xmm2, 24(%ecx,%eax)
-; CHECK-NEXT: pextrd $1, %xmm2, 20(%ecx,%eax)
; CHECK-NEXT: movd %xmm2, 16(%ecx,%eax)
+; CHECK-NEXT: pextrd $1, %xmm2, 20(%ecx,%eax)
+; CHECK-NEXT: pextrd $2, %xmm2, 24(%ecx,%eax)
; CHECK-NEXT: movdqa %xmm1, (%ecx,%eax)
; CHECK-NEXT: incl (%esp)
; CHECK-NEXT: cmpl $3, (%esp)
; X86-NEXT: pinsrd $1, 4(%ecx), %xmm1
; X86-NEXT: pinsrd $2, 8(%ecx), %xmm1
; X86-NEXT: paddd %xmm0, %xmm1
-; X86-NEXT: pextrd $2, %xmm1, 8(%eax)
; X86-NEXT: pextrd $1, %xmm1, 4(%eax)
+; X86-NEXT: pextrd $2, %xmm1, 8(%eax)
; X86-NEXT: movd %xmm1, (%eax)
; X86-NEXT: retl $4
;
; X86-NEXT: movdqa 16(%edx), %xmm1
; X86-NEXT: paddd (%ecx), %xmm0
; X86-NEXT: paddd 16(%ecx), %xmm1
-; X86-NEXT: pextrd $2, %xmm1, 24(%eax)
-; X86-NEXT: pextrd $1, %xmm1, 20(%eax)
; X86-NEXT: movd %xmm1, 16(%eax)
+; X86-NEXT: pextrd $1, %xmm1, 20(%eax)
+; X86-NEXT: pextrd $2, %xmm1, 24(%eax)
; X86-NEXT: movdqa %xmm0, (%eax)
; X86-NEXT: retl $4
;
; X64-NEXT: movdqa 16(%rsi), %xmm1
; X64-NEXT: paddd (%rdx), %xmm0
; X64-NEXT: paddd 16(%rdx), %xmm1
-; X64-NEXT: pextrd $2, %xmm1, 24(%rdi)
; X64-NEXT: movq %xmm1, 16(%rdi)
+; X64-NEXT: pextrd $2, %xmm1, 24(%rdi)
; X64-NEXT: movdqa %xmm0, (%rdi)
; X64-NEXT: retq
%a = load %i32vec7, %i32vec7* %ap, align 16
; X86-NEXT: movdqa (%edx), %xmm1
; X86-NEXT: movdqa 16(%edx), %xmm2
; X86-NEXT: paddd (%ecx), %xmm1
-; X86-NEXT: paddd 16(%ecx), %xmm2
; X86-NEXT: paddd 32(%ecx), %xmm0
-; X86-NEXT: movdqa %xmm0, 32(%eax)
+; X86-NEXT: paddd 16(%ecx), %xmm2
; X86-NEXT: movdqa %xmm2, 16(%eax)
+; X86-NEXT: movdqa %xmm0, 32(%eax)
; X86-NEXT: movdqa %xmm1, (%eax)
; X86-NEXT: retl $4
;
; X64-NEXT: movdqa 16(%rsi), %xmm1
; X64-NEXT: movdqa 32(%rsi), %xmm2
; X64-NEXT: paddd (%rdx), %xmm0
-; X64-NEXT: paddd 16(%rdx), %xmm1
; X64-NEXT: paddd 32(%rdx), %xmm2
-; X64-NEXT: movdqa %xmm2, 32(%rdi)
+; X64-NEXT: paddd 16(%rdx), %xmm1
; X64-NEXT: movdqa %xmm1, 16(%rdi)
+; X64-NEXT: movdqa %xmm2, 32(%rdi)
; X64-NEXT: movdqa %xmm0, (%rdi)
; X64-NEXT: retq
%a = load %i32vec12, %i32vec12* %ap, align 16
; X86-NEXT: movdqa 16(%edx), %xmm1
; X86-NEXT: paddw (%ecx), %xmm0
; X86-NEXT: paddw 16(%ecx), %xmm1
-; X86-NEXT: pextrd $1, %xmm1, 20(%eax)
; X86-NEXT: movd %xmm1, 16(%eax)
+; X86-NEXT: pextrd $1, %xmm1, 20(%eax)
; X86-NEXT: movdqa %xmm0, (%eax)
; X86-NEXT: retl $4
;
; X86-NEXT: movdqa (%edx), %xmm1
; X86-NEXT: movdqa 16(%edx), %xmm2
; X86-NEXT: paddw (%ecx), %xmm1
-; X86-NEXT: paddw 16(%ecx), %xmm2
; X86-NEXT: paddw 32(%ecx), %xmm0
-; X86-NEXT: movd %xmm0, 32(%eax)
+; X86-NEXT: paddw 16(%ecx), %xmm2
; X86-NEXT: movdqa %xmm2, 16(%eax)
+; X86-NEXT: movd %xmm0, 32(%eax)
; X86-NEXT: movdqa %xmm1, (%eax)
; X86-NEXT: retl $4
;
; X64-NEXT: movdqa 16(%rsi), %xmm1
; X64-NEXT: movdqa 32(%rsi), %xmm2
; X64-NEXT: paddw (%rdx), %xmm0
-; X64-NEXT: paddw 16(%rdx), %xmm1
; X64-NEXT: paddw 32(%rdx), %xmm2
-; X64-NEXT: movd %xmm2, 32(%rdi)
+; X64-NEXT: paddw 16(%rdx), %xmm1
; X64-NEXT: movdqa %xmm1, 16(%rdi)
+; X64-NEXT: movd %xmm2, 32(%rdi)
; X64-NEXT: movdqa %xmm0, (%rdi)
; X64-NEXT: retq
%a = load %i16vec18, %i16vec18* %ap, align 16
; X86-NEXT: movdqa 16(%edx), %xmm1
; X86-NEXT: paddb (%ecx), %xmm0
; X86-NEXT: paddb 16(%ecx), %xmm1
-; X86-NEXT: pextrb $14, %xmm1, 30(%eax)
-; X86-NEXT: pextrw $6, %xmm1, 28(%eax)
-; X86-NEXT: pextrd $2, %xmm1, 24(%eax)
-; X86-NEXT: pextrd $1, %xmm1, 20(%eax)
; X86-NEXT: movd %xmm1, 16(%eax)
+; X86-NEXT: pextrd $1, %xmm1, 20(%eax)
+; X86-NEXT: pextrd $2, %xmm1, 24(%eax)
+; X86-NEXT: pextrw $6, %xmm1, 28(%eax)
+; X86-NEXT: pextrb $14, %xmm1, 30(%eax)
; X86-NEXT: movdqa %xmm0, (%eax)
; X86-NEXT: retl $4
;
; X64-NEXT: movdqa 16(%rsi), %xmm1
; X64-NEXT: paddb (%rdx), %xmm0
; X64-NEXT: paddb 16(%rdx), %xmm1
-; X64-NEXT: pextrb $14, %xmm1, 30(%rdi)
-; X64-NEXT: pextrw $6, %xmm1, 28(%rdi)
-; X64-NEXT: pextrd $2, %xmm1, 24(%rdi)
; X64-NEXT: movq %xmm1, 16(%rdi)
+; X64-NEXT: pextrd $2, %xmm1, 24(%rdi)
+; X64-NEXT: pextrw $6, %xmm1, 28(%rdi)
+; X64-NEXT: pextrb $14, %xmm1, 30(%rdi)
; X64-NEXT: movdqa %xmm0, (%rdi)
; X64-NEXT: retq
%a = load %i8vec31, %i8vec31* %ap, align 16
; ALL-NEXT: movq %rsp, %rbp
; ALL-NEXT: .seh_setframe 5, 0
; ALL-NEXT: .seh_endprologue
-; ALL-NEXT: movq %r9, 48(%rbp)
-; ALL-NEXT: movq %r8, 40(%rbp)
; ALL-NEXT: movq %rdx, 32(%rbp)
+; ALL-NEXT: movq %r8, 40(%rbp)
+; ALL-NEXT: movq %r9, 48(%rbp)
; ALL-NEXT: leaq 32(%rbp), %rax
; ALL-NEXT: movq %rax, (%rbp)
; ALL-NEXT: addq $8, %rsp
define void @average_va(i32 %count, ...) nounwind {
entry:
; CHECK: pushq
-; CHECK: movq %r9, 40(%rsp)
-; CHECK: movq %r8, 32(%rsp)
-; CHECK: movq %rdx, 24(%rsp)
+; CHECK-DAG: movq %r9, 40(%rsp)
+; CHECK-DAG: movq %r8, 32(%rsp)
+; CHECK-DAG: movq %rdx, 24(%rsp)
; CHECK: leaq 24(%rsp), %rax
%ap = alloca i8*, align 8 ; <i8**> [#uses=1]
define win64cc void @average_va(i32 %count, ...) nounwind {
entry:
; CHECK: pushq
-; CHECK: movq %r9, 40(%rsp)
-; CHECK: movq %r8, 32(%rsp)
-; CHECK: movq %rdx, 24(%rsp)
+; CHECK-DAG: movq %r9, 40(%rsp)
+; CHECK-DAG: movq %r8, 32(%rsp)
+; CHECK-DAG: movq %rdx, 24(%rsp)
; CHECK: leaq 24(%rsp), %rax
%ap = alloca i8*, align 8 ; <i8**> [#uses=1]
; CHECK-LABEL: copy1:
; CHECK: leaq 32(%rsp), [[REG_copy1:%[a-z]+]]
-; CHECK: movq [[REG_copy1]], 8(%rsp)
-; CHECK: movq [[REG_copy1]], (%rsp)
+; CHECK-DAG: movq [[REG_copy1]], 8(%rsp)
+; CHECK-DAG: movq [[REG_copy1]], (%rsp)
; CHECK: ret
define win64cc void @copy1(i64 %a0, ...) nounwind {
entry:
; CHECK: extsp 4
; CHECK: stw lr, sp[1]
; CHECK: mov r11, r1
-; CHECK: stw r2, sp[3]
-; CHECK: stw r3, sp[4]
+; CHECK-DAG: stw r2, sp[3]
+; CHECK-DAG: stw r3, sp[4]
; CHECK: ldw r0, r0[0]
; CHECK: stw r0, sp[2]
; CHECK: ldaw r1, sp[2]
projects / llvm / commitdiff