d41e517748
We use the term "interchangeable instructions" to refer to different operators that have the same meaning (e.g., `add x, 0` is equivalent to `mul x, 1`). Non-constant values are not supported, as they may incur high costs with little benefit. --------- Co-authored-by: Alexey Bataev <a.bataev@gmx.com>
66 lines
2.7 KiB
LLVM
66 lines
2.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -passes=slp-vectorizer -mtriple=x86_64-apple-macosx -mattr=+avx2 < %s | FileCheck %s
|
|
|
|
define i64 @foo(i32 %tmp7) {
|
|
; CHECK-LABEL: @foo(
|
|
; CHECK-NEXT: bb:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <8 x i32> <i32 0, i32 0, i32 poison, i32 poison, i32 0, i32 poison, i32 poison, i32 poison>, i32 [[TMP8:%.*]], i32 3
|
|
; CHECK-NEXT: [[TMP4:%.*]] = sub <8 x i32> [[TMP0]], <i32 0, i32 0, i32 poison, i32 0, i32 0, i32 poison, i32 0, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 poison, i32 poison, i32 poison, i32 0>, <8 x i32> [[TMP4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 14, i32 poison, i32 poison, i32 7>
|
|
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x i32> [[TMP2]], i32 0, i32 5
|
|
; CHECK-NEXT: [[TMP5:%.*]] = sub nsw <8 x i32> [[TMP13]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP6:%.*]] = add nsw <8 x i32> [[TMP13]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <8 x i32> [[TMP5]], <8 x i32> [[TMP6]], <8 x i32> <i32 8, i32 1, i32 2, i32 3, i32 12, i32 13, i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP8:%.*]] = add <8 x i32> zeroinitializer, [[TMP7]]
|
|
; CHECK-NEXT: [[TMP9:%.*]] = xor <8 x i32> [[TMP8]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP10:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP9]])
|
|
; CHECK-NEXT: [[OP_RDX:%.*]] = add i32 0, [[TMP10]]
|
|
; CHECK-NEXT: [[TMP64:%.*]] = zext i32 [[OP_RDX]] to i64
|
|
; CHECK-NEXT: ret i64 [[TMP64]]
|
|
;
|
|
bb:
|
|
%tmp = sub i32 0, 0
|
|
%tmp2 = sub nsw i32 0, %tmp
|
|
%tmp3 = add i32 0, %tmp2
|
|
%tmp4 = xor i32 %tmp3, 0
|
|
%tmp6 = sub i32 0, 0
|
|
%tmp8 = sub i32 %tmp7, 0
|
|
%tmp9 = sub nsw i32 0, poison
|
|
%tmp10 = add nsw i32 0, %tmp6
|
|
%tmp11 = sub nsw i32 0, %tmp8
|
|
%tmp12 = add i32 0, %tmp10
|
|
%tmp13 = xor i32 %tmp12, 0
|
|
%tmp14 = add i32 0, %tmp9
|
|
%tmp15 = xor i32 %tmp14, 0
|
|
%tmp16 = add i32 0, %tmp11
|
|
%tmp17 = xor i32 %tmp16, 0
|
|
%tmp18 = add i32 %tmp13, %tmp4
|
|
%tmp19 = add i32 %tmp18, 0
|
|
%tmp20 = add i32 %tmp19, %tmp15
|
|
%tmp21 = add i32 %tmp20, %tmp17
|
|
%tmp22 = sub i32 0, 0
|
|
%tmp23 = add i32 0, 0
|
|
%tmp24 = sub i32 poison, 0
|
|
%tmp25 = add nsw i32 %tmp23, poison
|
|
%tmp26 = add nsw i32 %tmp24, %tmp22
|
|
%tmp27 = sub nsw i32 poison, %tmp24
|
|
%tmp28 = add i32 0, %tmp25
|
|
%tmp29 = xor i32 %tmp28, 0
|
|
%tmp30 = add i32 0, %tmp26
|
|
%tmp31 = xor i32 %tmp30, 0
|
|
%tmp32 = add i32 0, %tmp27
|
|
%tmp33 = xor i32 %tmp32, 0
|
|
%tmp34 = add i32 %tmp31, %tmp21
|
|
%tmp35 = add i32 %tmp34, %tmp29
|
|
%tmp36 = add i32 %tmp35, 0
|
|
%tmp37 = add i32 %tmp36, %tmp33
|
|
%tmp38 = sub nsw i32 0, poison
|
|
%tmp39 = add i32 0, %tmp38
|
|
%tmp40 = xor i32 %tmp39, 0
|
|
%tmp41 = add i32 0, %tmp37
|
|
%tmp42 = add i32 %tmp41, 0
|
|
%tmp43 = add i32 %tmp42, %tmp40
|
|
%tmp64 = zext i32 %tmp43 to i64
|
|
ret i64 %tmp64
|
|
}
|