260 lines
9.6 KiB
LLVM
260 lines
9.6 KiB
LLVM
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||
|
; RUN: llc < %s -mtriple=aarch64-unknown-unknown | FileCheck %s --check-prefixes=SDAG
|
||
|
; RUN: llc < %s -mtriple=aarch64-unknown-unknown -global-isel | FileCheck %s --check-prefixes=GISEL
|
||
|
|
||
|
; These tests are taken from the combine-udiv.ll in X86.
|
||
|
define <8 x i16> @combine_vec_udiv_uniform(<8 x i16> %x) {
|
||
|
; SDAG-LABEL: combine_vec_udiv_uniform:
|
||
|
; SDAG: // %bb.0:
|
||
|
; SDAG-NEXT: mov w8, #25645 // =0x642d
|
||
|
; SDAG-NEXT: dup v1.8h, w8
|
||
|
; SDAG-NEXT: umull2 v2.4s, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: umull v1.4s, v0.4h, v1.4h
|
||
|
; SDAG-NEXT: uzp2 v1.8h, v1.8h, v2.8h
|
||
|
; SDAG-NEXT: sub v0.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: usra v1.8h, v0.8h, #1
|
||
|
; SDAG-NEXT: ushr v0.8h, v1.8h, #4
|
||
|
; SDAG-NEXT: ret
|
||
|
;
|
||
|
; GISEL-LABEL: combine_vec_udiv_uniform:
|
||
|
; GISEL: // %bb.0:
|
||
|
; GISEL-NEXT: adrp x8, .LCPI0_0
|
||
|
; GISEL-NEXT: ldr q1, [x8, :lo12:.LCPI0_0]
|
||
|
; GISEL-NEXT: umull2 v2.4s, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: umull v1.4s, v0.4h, v1.4h
|
||
|
; GISEL-NEXT: uzp2 v1.8h, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: sub v0.8h, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: usra v1.8h, v0.8h, #1
|
||
|
; GISEL-NEXT: ushr v0.8h, v1.8h, #4
|
||
|
; GISEL-NEXT: ret
|
||
|
%1 = udiv <8 x i16> %x, <i16 23, i16 23, i16 23, i16 23, i16 23, i16 23, i16 23, i16 23>
|
||
|
ret <8 x i16> %1
|
||
|
}
|
||
|
|
||
|
define <8 x i16> @combine_vec_udiv_nonuniform(<8 x i16> %x) {
|
||
|
; SDAG-LABEL: combine_vec_udiv_nonuniform:
|
||
|
; SDAG: // %bb.0:
|
||
|
; SDAG-NEXT: adrp x8, .LCPI1_0
|
||
|
; SDAG-NEXT: ldr q1, [x8, :lo12:.LCPI1_0]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI1_1
|
||
|
; SDAG-NEXT: ldr q2, [x8, :lo12:.LCPI1_1]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI1_2
|
||
|
; SDAG-NEXT: ushl v1.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: umull2 v3.4s, v1.8h, v2.8h
|
||
|
; SDAG-NEXT: umull v1.4s, v1.4h, v2.4h
|
||
|
; SDAG-NEXT: ldr q2, [x8, :lo12:.LCPI1_2]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI1_3
|
||
|
; SDAG-NEXT: uzp2 v1.8h, v1.8h, v3.8h
|
||
|
; SDAG-NEXT: sub v0.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: umull2 v3.4s, v0.8h, v2.8h
|
||
|
; SDAG-NEXT: umull v0.4s, v0.4h, v2.4h
|
||
|
; SDAG-NEXT: uzp2 v0.8h, v0.8h, v3.8h
|
||
|
; SDAG-NEXT: add v0.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: ldr q1, [x8, :lo12:.LCPI1_3]
|
||
|
; SDAG-NEXT: ushl v0.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: ret
|
||
|
;
|
||
|
; GISEL-LABEL: combine_vec_udiv_nonuniform:
|
||
|
; GISEL: // %bb.0:
|
||
|
; GISEL-NEXT: adrp x8, .LCPI1_3
|
||
|
; GISEL-NEXT: ldr q1, [x8, :lo12:.LCPI1_3]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI1_2
|
||
|
; GISEL-NEXT: ldr q2, [x8, :lo12:.LCPI1_2]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI1_1
|
||
|
; GISEL-NEXT: neg v1.8h, v1.8h
|
||
|
; GISEL-NEXT: ushl v1.8h, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: umull2 v3.4s, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: umull v1.4s, v1.4h, v2.4h
|
||
|
; GISEL-NEXT: uzp2 v1.8h, v1.8h, v3.8h
|
||
|
; GISEL-NEXT: ldr q3, [x8, :lo12:.LCPI1_1]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI1_0
|
||
|
; GISEL-NEXT: sub v2.8h, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: umull2 v4.4s, v2.8h, v3.8h
|
||
|
; GISEL-NEXT: umull v2.4s, v2.4h, v3.4h
|
||
|
; GISEL-NEXT: ldr q3, [x8, :lo12:.LCPI1_0]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI1_4
|
||
|
; GISEL-NEXT: uzp2 v2.8h, v2.8h, v4.8h
|
||
|
; GISEL-NEXT: ldr q4, [x8, :lo12:.LCPI1_4]
|
||
|
; GISEL-NEXT: add v1.8h, v2.8h, v1.8h
|
||
|
; GISEL-NEXT: neg v2.8h, v3.8h
|
||
|
; GISEL-NEXT: movi v3.8h, #1
|
||
|
; GISEL-NEXT: ushl v1.8h, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: cmeq v2.8h, v4.8h, v3.8h
|
||
|
; GISEL-NEXT: bif v0.16b, v1.16b, v2.16b
|
||
|
; GISEL-NEXT: ret
|
||
|
%1 = udiv <8 x i16> %x, <i16 23, i16 34, i16 -23, i16 56, i16 128, i16 -1, i16 -256, i16 -32768>
|
||
|
ret <8 x i16> %1
|
||
|
}
|
||
|
|
||
|
define <8 x i16> @combine_vec_udiv_nonuniform2(<8 x i16> %x) {
|
||
|
; SDAG-LABEL: combine_vec_udiv_nonuniform2:
|
||
|
; SDAG: // %bb.0:
|
||
|
; SDAG-NEXT: adrp x8, .LCPI2_0
|
||
|
; SDAG-NEXT: ldr q1, [x8, :lo12:.LCPI2_0]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI2_1
|
||
|
; SDAG-NEXT: ushl v0.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: ldr q1, [x8, :lo12:.LCPI2_1]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI2_2
|
||
|
; SDAG-NEXT: umull2 v2.4s, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: umull v0.4s, v0.4h, v1.4h
|
||
|
; SDAG-NEXT: ldr q1, [x8, :lo12:.LCPI2_2]
|
||
|
; SDAG-NEXT: uzp2 v0.8h, v0.8h, v2.8h
|
||
|
; SDAG-NEXT: ushl v0.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: ret
|
||
|
;
|
||
|
; GISEL-LABEL: combine_vec_udiv_nonuniform2:
|
||
|
; GISEL: // %bb.0:
|
||
|
; GISEL-NEXT: adrp x8, .LCPI2_2
|
||
|
; GISEL-NEXT: ldr q1, [x8, :lo12:.LCPI2_2]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI2_1
|
||
|
; GISEL-NEXT: ldr q2, [x8, :lo12:.LCPI2_1]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI2_0
|
||
|
; GISEL-NEXT: neg v1.8h, v1.8h
|
||
|
; GISEL-NEXT: ushl v1.8h, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: umull2 v3.4s, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: umull v1.4s, v1.4h, v2.4h
|
||
|
; GISEL-NEXT: ldr q2, [x8, :lo12:.LCPI2_0]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI2_3
|
||
|
; GISEL-NEXT: neg v2.8h, v2.8h
|
||
|
; GISEL-NEXT: ldr q4, [x8, :lo12:.LCPI2_3]
|
||
|
; GISEL-NEXT: uzp2 v1.8h, v1.8h, v3.8h
|
||
|
; GISEL-NEXT: movi v3.8h, #1
|
||
|
; GISEL-NEXT: ushl v1.8h, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: cmeq v2.8h, v4.8h, v3.8h
|
||
|
; GISEL-NEXT: bif v0.16b, v1.16b, v2.16b
|
||
|
; GISEL-NEXT: ret
|
||
|
%1 = udiv <8 x i16> %x, <i16 -34, i16 35, i16 36, i16 -37, i16 38, i16 -39, i16 40, i16 -41>
|
||
|
ret <8 x i16> %1
|
||
|
}
|
||
|
|
||
|
define <8 x i16> @combine_vec_udiv_nonuniform3(<8 x i16> %x) {
|
||
|
; SDAG-LABEL: combine_vec_udiv_nonuniform3:
|
||
|
; SDAG: // %bb.0:
|
||
|
; SDAG-NEXT: adrp x8, .LCPI3_0
|
||
|
; SDAG-NEXT: ldr q1, [x8, :lo12:.LCPI3_0]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI3_1
|
||
|
; SDAG-NEXT: umull2 v2.4s, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: umull v1.4s, v0.4h, v1.4h
|
||
|
; SDAG-NEXT: uzp2 v1.8h, v1.8h, v2.8h
|
||
|
; SDAG-NEXT: sub v0.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: usra v1.8h, v0.8h, #1
|
||
|
; SDAG-NEXT: ldr q0, [x8, :lo12:.LCPI3_1]
|
||
|
; SDAG-NEXT: ushl v0.8h, v1.8h, v0.8h
|
||
|
; SDAG-NEXT: ret
|
||
|
;
|
||
|
; GISEL-LABEL: combine_vec_udiv_nonuniform3:
|
||
|
; GISEL: // %bb.0:
|
||
|
; GISEL-NEXT: adrp x8, .LCPI3_1
|
||
|
; GISEL-NEXT: movi v3.8h, #1
|
||
|
; GISEL-NEXT: ldr q1, [x8, :lo12:.LCPI3_1]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI3_0
|
||
|
; GISEL-NEXT: umull2 v2.4s, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: umull v1.4s, v0.4h, v1.4h
|
||
|
; GISEL-NEXT: uzp2 v1.8h, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: sub v2.8h, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: usra v1.8h, v2.8h, #1
|
||
|
; GISEL-NEXT: ldr q2, [x8, :lo12:.LCPI3_0]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI3_2
|
||
|
; GISEL-NEXT: ldr q4, [x8, :lo12:.LCPI3_2]
|
||
|
; GISEL-NEXT: neg v2.8h, v2.8h
|
||
|
; GISEL-NEXT: ushl v1.8h, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: cmeq v2.8h, v4.8h, v3.8h
|
||
|
; GISEL-NEXT: bif v0.16b, v1.16b, v2.16b
|
||
|
; GISEL-NEXT: ret
|
||
|
%1 = udiv <8 x i16> %x, <i16 7, i16 23, i16 25, i16 27, i16 31, i16 47, i16 63, i16 127>
|
||
|
ret <8 x i16> %1
|
||
|
}
|
||
|
|
||
|
define <16 x i8> @combine_vec_udiv_nonuniform4(<16 x i8> %x) {
|
||
|
; SDAG-LABEL: combine_vec_udiv_nonuniform4:
|
||
|
; SDAG: // %bb.0:
|
||
|
; SDAG-NEXT: movi v1.16b, #171
|
||
|
; SDAG-NEXT: adrp x8, .LCPI4_0
|
||
|
; SDAG-NEXT: adrp x9, .LCPI4_1
|
||
|
; SDAG-NEXT: ldr q3, [x9, :lo12:.LCPI4_1]
|
||
|
; SDAG-NEXT: umull2 v2.8h, v0.16b, v1.16b
|
||
|
; SDAG-NEXT: umull v1.8h, v0.8b, v1.8b
|
||
|
; SDAG-NEXT: and v0.16b, v0.16b, v3.16b
|
||
|
; SDAG-NEXT: uzp2 v1.16b, v1.16b, v2.16b
|
||
|
; SDAG-NEXT: ldr q2, [x8, :lo12:.LCPI4_0]
|
||
|
; SDAG-NEXT: ushr v1.16b, v1.16b, #7
|
||
|
; SDAG-NEXT: and v1.16b, v1.16b, v2.16b
|
||
|
; SDAG-NEXT: orr v0.16b, v0.16b, v1.16b
|
||
|
; SDAG-NEXT: ret
|
||
|
;
|
||
|
; GISEL-LABEL: combine_vec_udiv_nonuniform4:
|
||
|
; GISEL: // %bb.0:
|
||
|
; GISEL-NEXT: adrp x8, .LCPI4_1
|
||
|
; GISEL-NEXT: ldr q1, [x8, :lo12:.LCPI4_1]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI4_0
|
||
|
; GISEL-NEXT: ldr q3, [x8, :lo12:.LCPI4_0]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI4_2
|
||
|
; GISEL-NEXT: umull2 v2.8h, v0.16b, v1.16b
|
||
|
; GISEL-NEXT: umull v1.8h, v0.8b, v1.8b
|
||
|
; GISEL-NEXT: ldr q4, [x8, :lo12:.LCPI4_2]
|
||
|
; GISEL-NEXT: uzp2 v1.16b, v1.16b, v2.16b
|
||
|
; GISEL-NEXT: neg v2.16b, v3.16b
|
||
|
; GISEL-NEXT: movi v3.16b, #1
|
||
|
; GISEL-NEXT: ushl v1.16b, v1.16b, v2.16b
|
||
|
; GISEL-NEXT: cmeq v2.16b, v4.16b, v3.16b
|
||
|
; GISEL-NEXT: bif v0.16b, v1.16b, v2.16b
|
||
|
; GISEL-NEXT: ret
|
||
|
%div = udiv <16 x i8> %x, <i8 -64, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
|
||
|
ret <16 x i8> %div
|
||
|
}
|
||
|
|
||
|
define <8 x i16> @pr38477(<8 x i16> %a0) {
|
||
|
; SDAG-LABEL: pr38477:
|
||
|
; SDAG: // %bb.0:
|
||
|
; SDAG-NEXT: adrp x8, .LCPI5_0
|
||
|
; SDAG-NEXT: adrp x9, .LCPI5_4
|
||
|
; SDAG-NEXT: ldr q1, [x8, :lo12:.LCPI5_0]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI5_1
|
||
|
; SDAG-NEXT: ldr q3, [x8, :lo12:.LCPI5_1]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI5_2
|
||
|
; SDAG-NEXT: umull2 v2.4s, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: umull v1.4s, v0.4h, v1.4h
|
||
|
; SDAG-NEXT: uzp2 v1.8h, v1.8h, v2.8h
|
||
|
; SDAG-NEXT: sub v2.8h, v0.8h, v1.8h
|
||
|
; SDAG-NEXT: umull2 v4.4s, v2.8h, v3.8h
|
||
|
; SDAG-NEXT: umull v2.4s, v2.4h, v3.4h
|
||
|
; SDAG-NEXT: ldr q3, [x9, :lo12:.LCPI5_4]
|
||
|
; SDAG-NEXT: and v0.16b, v0.16b, v3.16b
|
||
|
; SDAG-NEXT: uzp2 v2.8h, v2.8h, v4.8h
|
||
|
; SDAG-NEXT: add v1.8h, v2.8h, v1.8h
|
||
|
; SDAG-NEXT: ldr q2, [x8, :lo12:.LCPI5_2]
|
||
|
; SDAG-NEXT: adrp x8, .LCPI5_3
|
||
|
; SDAG-NEXT: ushl v1.8h, v1.8h, v2.8h
|
||
|
; SDAG-NEXT: ldr q2, [x8, :lo12:.LCPI5_3]
|
||
|
; SDAG-NEXT: and v1.16b, v1.16b, v2.16b
|
||
|
; SDAG-NEXT: orr v0.16b, v0.16b, v1.16b
|
||
|
; SDAG-NEXT: ret
|
||
|
;
|
||
|
; GISEL-LABEL: pr38477:
|
||
|
; GISEL: // %bb.0:
|
||
|
; GISEL-NEXT: adrp x8, .LCPI5_2
|
||
|
; GISEL-NEXT: ldr q1, [x8, :lo12:.LCPI5_2]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI5_1
|
||
|
; GISEL-NEXT: ldr q3, [x8, :lo12:.LCPI5_1]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI5_0
|
||
|
; GISEL-NEXT: umull2 v2.4s, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: umull v1.4s, v0.4h, v1.4h
|
||
|
; GISEL-NEXT: uzp2 v1.8h, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: sub v2.8h, v0.8h, v1.8h
|
||
|
; GISEL-NEXT: umull2 v4.4s, v2.8h, v3.8h
|
||
|
; GISEL-NEXT: umull v2.4s, v2.4h, v3.4h
|
||
|
; GISEL-NEXT: ldr q3, [x8, :lo12:.LCPI5_0]
|
||
|
; GISEL-NEXT: adrp x8, .LCPI5_3
|
||
|
; GISEL-NEXT: uzp2 v2.8h, v2.8h, v4.8h
|
||
|
; GISEL-NEXT: ldr q4, [x8, :lo12:.LCPI5_3]
|
||
|
; GISEL-NEXT: add v1.8h, v2.8h, v1.8h
|
||
|
; GISEL-NEXT: neg v2.8h, v3.8h
|
||
|
; GISEL-NEXT: movi v3.8h, #1
|
||
|
; GISEL-NEXT: ushl v1.8h, v1.8h, v2.8h
|
||
|
; GISEL-NEXT: cmeq v2.8h, v4.8h, v3.8h
|
||
|
; GISEL-NEXT: bif v0.16b, v1.16b, v2.16b
|
||
|
; GISEL-NEXT: ret
|
||
|
%1 = udiv <8 x i16> %a0, <i16 1, i16 119, i16 73, i16 -111, i16 -3, i16 118, i16 32, i16 31>
|
||
|
ret <8 x i16> %1
|
||
|
}
|