; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-unknown-unknown | FileCheck %s
; Check that under certain conditions we can factor out a rotate
; from the following idioms:
; (a*c0) >> s1 | (a*c1)
; (a/c0) << s1 | (a/c1)
; This targets cases where instcombine has folded a shl/srl/mul/udiv
; with one of the shifts from the rotate idiom
define i64 @ror_extract_shl(i64 %i) nounwind {
; CHECK-LABEL: ror_extract_shl:
; CHECK: // %bb.0:
; CHECK-NEXT: lsl x8, x0, #3
; CHECK-NEXT: ror x0, x8, #57
; CHECK-NEXT: ret
%lhs_mul = shl i64 %i, 3
%rhs_mul = shl i64 %i, 10
%lhs_shift = lshr i64 %lhs_mul, 57
%out = or i64 %lhs_shift, %rhs_mul
ret i64 %out
}
define i32 @ror_extract_shrl(i32 %i) nounwind {
; CHECK-LABEL: ror_extract_shrl:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr w8, w0, #3
; CHECK-NEXT: ror w0, w8, #4
; CHECK-NEXT: ret
%lhs_div = lshr i32 %i, 7
%rhs_div = lshr i32 %i, 3
%rhs_shift = shl i32 %rhs_div, 28
%out = or i32 %lhs_div, %rhs_shift
ret i32 %out
}
define i32 @ror_extract_mul(i32 %i) nounwind {
; CHECK-LABEL: ror_extract_mul:
; CHECK: // %bb.0:
; CHECK-NEXT: add w8, w0, w0, lsl #3
; CHECK-NEXT: ror w0, w8, #25
; CHECK-NEXT: ret
%lhs_mul = mul i32 %i, 9
%rhs_mul = mul i32 %i, 1152
%lhs_shift = lshr i32 %lhs_mul, 25
%out = or i32 %lhs_shift, %rhs_mul
ret i32 %out
}
define i64 @ror_extract_udiv(i64 %i) nounwind {
; CHECK-LABEL: ror_extract_udiv:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x8, #-6148914691236517206 // =0xaaaaaaaaaaaaaaaa
; CHECK-NEXT: movk x8, #43691
; CHECK-NEXT: umulh x8, x0, x8
; CHECK-NEXT: lsr x8, x8, #1
; CHECK-NEXT: ror x0, x8, #4
; CHECK-NEXT: ret
%lhs_div = udiv i64 %i, 3
%rhs_div = udiv i64 %i, 48
%lhs_shift = shl i64 %lhs_div, 60
%out = or i64 %lhs_shift, %rhs_div
ret i64 %out
}
define i64 @ror_extract_mul_with_mask(i64 %i) nounwind {
; CHECK-LABEL: ror_extract_mul_with_mask:
; CHECK: // %bb.0:
; CHECK-NEXT: add x8, x0, x0, lsl #3
; CHECK-NEXT: ror x8, x8, #57
; CHECK-NEXT: and x0, x8, #0xff
; CHECK-NEXT: ret
%lhs_mul = mul i64 %i, 1152
%rhs_mul = mul i64 %i, 9
%lhs_and = and i64 %lhs_mul, 160
%rhs_shift = lshr i64 %rhs_mul, 57
%out = or i64 %lhs_and, %rhs_shift
ret i64 %out
}
; Result would undershift
define i64 @no_extract_shl(i64 %i) nounwind {
; CHECK-LABEL: no_extract_shl:
; CHECK: // %bb.0:
; CHECK-NEXT: lsl x8, x0, #10
; CHECK-NEXT: bfxil x8, x0, #52, #7
; CHECK-NEXT: mov x0, x8
; CHECK-NEXT: ret
%lhs_mul = shl i64 %i, 5
%rhs_mul = shl i64 %i, 10
%lhs_shift = lshr i64 %lhs_mul, 57
%out = or i64 %lhs_shift, %rhs_mul
ret i64 %out
}
; Result would overshift
define i32 @no_extract_shrl(i32 %i) nounwind {
; CHECK-LABEL: no_extract_shrl:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr w8, w0, #3
; CHECK-NEXT: lsr w0, w0, #9
; CHECK-NEXT: bfi w0, w8, #28, #4
; CHECK-NEXT: ret
%lhs_div = lshr i32 %i, 3
%rhs_div = lshr i32 %i, 9
%lhs_shift = shl i32 %lhs_div, 28
%out = or i32 %lhs_shift, %rhs_div
ret i32 %out
}
; Can factor 128 from 2304, but result is 18 instead of 9
define i64 @no_extract_mul(i64 %i) nounwind {
; CHECK-LABEL: no_extract_mul:
; CHECK: // %bb.0:
; CHECK-NEXT: add x8, x0, x0, lsl #3
; CHECK-NEXT: lsr x9, x8, #57
; CHECK-NEXT: orr x0, x9, x8, lsl #8
; CHECK-NEXT: ret
%lhs_mul = mul i64 %i, 2304
%rhs_mul = mul i64 %i, 9
%rhs_shift = lshr i64 %rhs_mul, 57
%out = or i64 %lhs_mul, %rhs_shift
ret i64 %out
}
; Can't evenly factor 16 from 49
define i32 @no_extract_udiv(i32 %i) nounwind {
; CHECK-LABEL: no_extract_udiv:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #43691 // =0xaaab
; CHECK-NEXT: mov w9, #33437 // =0x829d
; CHECK-NEXT: movk w8, #43690, lsl #16
; CHECK-NEXT: movk w9, #21399, lsl #16
; CHECK-NEXT: umull x8, w0, w8
; CHECK-NEXT: umull x9, w0, w9
; CHECK-NEXT: lsr x8, x8, #33
; CHECK-NEXT: lsr x9, x9, #32
; CHECK-NEXT: extr w0, w8, w9, #4
; CHECK-NEXT: ret
%lhs_div = udiv i32 %i, 3
%rhs_div = udiv i32 %i, 49
%lhs_shift = shl i32 %lhs_div, 28
%out = or i32 %lhs_shift, %rhs_div
ret i32 %out
}
Codebase Browser
llvm