1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 10:42:39 +01:00
llvm-mirror/test/CodeGen/AArch64/urem-seteq-optsize.ll
Roman Lebedev 35f00e690f [NFC][CodeGen][SelectionDAG] Tests for X % C == 0 codegen improvement.
Hacker's Delight 10-17: when C is constant,
the result of X % C == 0 can be computed more cheaply
without actually calculating the remainder.

The motivation is discussed here:
https://bugs.llvm.org/show_bug.cgi?id=35479.

Patch by: hermord (Dmytro Shynkevych)!

For https://reviews.llvm.org/D50222

llvm-svn: 341047
2018-08-30 09:32:21 +00:00

42 lines
1.3 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s
; On AArch64, division in expensive. BuildRemEqFold should therefore run even
; when optimizing for size. Only optimizing for minimum size retains a plain div.
define i32 @test_minsize(i32 %X) optsize minsize nounwind readnone {
; CHECK-LABEL: test_minsize:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #5
; CHECK-NEXT: udiv w8, w0, w8
; CHECK-NEXT: add w8, w8, w8, lsl #2
; CHECK-NEXT: mov w9, #-10
; CHECK-NEXT: cmp w0, w8
; CHECK-NEXT: mov w8, #42
; CHECK-NEXT: csel w0, w8, w9, eq
; CHECK-NEXT: ret
%rem = urem i32 %X, 5
%cmp = icmp eq i32 %rem, 0
%ret = select i1 %cmp, i32 42, i32 -10
ret i32 %ret
}
define i32 @test_optsize(i32 %X) optsize nounwind readnone {
; CHECK-LABEL: test_optsize:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #52429
; CHECK-NEXT: movk w8, #52428, lsl #16
; CHECK-NEXT: umull x8, w0, w8
; CHECK-NEXT: lsr x8, x8, #34
; CHECK-NEXT: add w8, w8, w8, lsl #2
; CHECK-NEXT: mov w9, #-10
; CHECK-NEXT: cmp w0, w8
; CHECK-NEXT: mov w8, #42
; CHECK-NEXT: csel w0, w8, w9, eq
; CHECK-NEXT: ret
%rem = urem i32 %X, 5
%cmp = icmp eq i32 %rem, 0
%ret = select i1 %cmp, i32 42, i32 -10
ret i32 %ret
}