forked from OSchip/llvm-project
339 lines
11 KiB
LLVM
339 lines
11 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve %s -o - | FileCheck %s
|
|
|
|
define <4 x i32> @v4i32(i32 %index, i32 %BTC, <4 x i32> %V1, <4 x i32> %V2) {
|
|
; CHECK-LABEL: v4i32:
|
|
; CHECK: @ %bb.0:
|
|
; CHECK-NEXT: adr.w r12, .LCPI0_0
|
|
; CHECK-NEXT: vdup.32 q1, r0
|
|
; CHECK-NEXT: vldrw.u32 q0, [r12]
|
|
; CHECK-NEXT: vadd.i32 q0, q0, r0
|
|
; CHECK-NEXT: add r0, sp, #8
|
|
; CHECK-NEXT: vcmp.u32 hi, q1, q0
|
|
; CHECK-NEXT: vdup.32 q1, r1
|
|
; CHECK-NEXT: vpnot
|
|
; CHECK-NEXT: vpst
|
|
; CHECK-NEXT: vcmpt.u32 cs, q1, q0
|
|
; CHECK-NEXT: vmov d0, r2, r3
|
|
; CHECK-NEXT: vldr d1, [sp]
|
|
; CHECK-NEXT: vldrw.u32 q1, [r0]
|
|
; CHECK-NEXT: vpsel q0, q0, q1
|
|
; CHECK-NEXT: vmov r0, r1, d0
|
|
; CHECK-NEXT: vmov r2, r3, d1
|
|
; CHECK-NEXT: bx lr
|
|
; CHECK-NEXT: .p2align 4
|
|
; CHECK-NEXT: @ %bb.1:
|
|
; CHECK-NEXT: .LCPI0_0:
|
|
; CHECK-NEXT: .long 0 @ 0x0
|
|
; CHECK-NEXT: .long 1 @ 0x1
|
|
; CHECK-NEXT: .long 2 @ 0x2
|
|
; CHECK-NEXT: .long 3 @ 0x3
|
|
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %BTC)
|
|
%select = select <4 x i1> %active.lane.mask, <4 x i32> %V1, <4 x i32> %V2
|
|
ret <4 x i32> %select
|
|
}
|
|
|
|
define <8 x i16> @v8i16(i32 %index, i32 %BTC, <8 x i16> %V1, <8 x i16> %V2) {
|
|
; CHECK-LABEL: v8i16:
|
|
; CHECK: @ %bb.0:
|
|
; CHECK-NEXT: vpush {d8, d9, d10, d11, d12, d13}
|
|
; CHECK-NEXT: adr.w r12, .LCPI1_0
|
|
; CHECK-NEXT: vdup.32 q5, r1
|
|
; CHECK-NEXT: vldrw.u32 q0, [r12]
|
|
; CHECK-NEXT: vmov.i8 q1, #0x0
|
|
; CHECK-NEXT: vmov.i8 q2, #0xff
|
|
; CHECK-NEXT: vadd.i32 q3, q0, r0
|
|
; CHECK-NEXT: vcmp.u32 cs, q5, q3
|
|
; CHECK-NEXT: vpsel q4, q2, q1
|
|
; CHECK-NEXT: vmov r1, s16
|
|
; CHECK-NEXT: vmov.16 q0[0], r1
|
|
; CHECK-NEXT: vmov r1, s17
|
|
; CHECK-NEXT: vmov.16 q0[1], r1
|
|
; CHECK-NEXT: vmov r1, s18
|
|
; CHECK-NEXT: vmov.16 q0[2], r1
|
|
; CHECK-NEXT: vmov r1, s19
|
|
; CHECK-NEXT: vmov.16 q0[3], r1
|
|
; CHECK-NEXT: adr r1, .LCPI1_1
|
|
; CHECK-NEXT: vldrw.u32 q4, [r1]
|
|
; CHECK-NEXT: vadd.i32 q4, q4, r0
|
|
; CHECK-NEXT: vcmp.u32 cs, q5, q4
|
|
; CHECK-NEXT: vpsel q5, q2, q1
|
|
; CHECK-NEXT: vmov r1, s20
|
|
; CHECK-NEXT: vmov.16 q0[4], r1
|
|
; CHECK-NEXT: vmov r1, s21
|
|
; CHECK-NEXT: vmov.16 q0[5], r1
|
|
; CHECK-NEXT: vmov r1, s22
|
|
; CHECK-NEXT: vmov.16 q0[6], r1
|
|
; CHECK-NEXT: vmov r1, s23
|
|
; CHECK-NEXT: vdup.32 q5, r0
|
|
; CHECK-NEXT: vmov.16 q0[7], r1
|
|
; CHECK-NEXT: vcmp.u32 hi, q5, q3
|
|
; CHECK-NEXT: vpsel q6, q2, q1
|
|
; CHECK-NEXT: vcmp.u32 hi, q5, q4
|
|
; CHECK-NEXT: vmov r0, s24
|
|
; CHECK-NEXT: vpsel q1, q2, q1
|
|
; CHECK-NEXT: vmov.16 q3[0], r0
|
|
; CHECK-NEXT: vmov r0, s25
|
|
; CHECK-NEXT: vmov.16 q3[1], r0
|
|
; CHECK-NEXT: vmov r0, s26
|
|
; CHECK-NEXT: vmov.16 q3[2], r0
|
|
; CHECK-NEXT: vmov r0, s27
|
|
; CHECK-NEXT: vmov.16 q3[3], r0
|
|
; CHECK-NEXT: vmov r0, s4
|
|
; CHECK-NEXT: vmov.16 q3[4], r0
|
|
; CHECK-NEXT: vmov r0, s5
|
|
; CHECK-NEXT: vmov.16 q3[5], r0
|
|
; CHECK-NEXT: vmov r0, s6
|
|
; CHECK-NEXT: vmov.16 q3[6], r0
|
|
; CHECK-NEXT: vmov r0, s7
|
|
; CHECK-NEXT: vmov.16 q3[7], r0
|
|
; CHECK-NEXT: add r0, sp, #56
|
|
; CHECK-NEXT: vcmp.i16 ne, q3, zr
|
|
; CHECK-NEXT: vldrw.u32 q1, [r0]
|
|
; CHECK-NEXT: vpnot
|
|
; CHECK-NEXT: vpst
|
|
; CHECK-NEXT: vcmpt.i16 ne, q0, zr
|
|
; CHECK-NEXT: vmov d0, r2, r3
|
|
; CHECK-NEXT: vldr d1, [sp, #48]
|
|
; CHECK-NEXT: vpsel q0, q0, q1
|
|
; CHECK-NEXT: vmov r0, r1, d0
|
|
; CHECK-NEXT: vmov r2, r3, d1
|
|
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13}
|
|
; CHECK-NEXT: bx lr
|
|
; CHECK-NEXT: .p2align 4
|
|
; CHECK-NEXT: @ %bb.1:
|
|
; CHECK-NEXT: .LCPI1_0:
|
|
; CHECK-NEXT: .long 0 @ 0x0
|
|
; CHECK-NEXT: .long 1 @ 0x1
|
|
; CHECK-NEXT: .long 2 @ 0x2
|
|
; CHECK-NEXT: .long 3 @ 0x3
|
|
; CHECK-NEXT: .LCPI1_1:
|
|
; CHECK-NEXT: .long 4 @ 0x4
|
|
; CHECK-NEXT: .long 5 @ 0x5
|
|
; CHECK-NEXT: .long 6 @ 0x6
|
|
; CHECK-NEXT: .long 7 @ 0x7
|
|
%active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %BTC)
|
|
%select = select <8 x i1> %active.lane.mask, <8 x i16> %V1, <8 x i16> %V2
|
|
ret <8 x i16> %select
|
|
}
|
|
|
|
define <16 x i8> @v16i8(i32 %index, i32 %BTC, <16 x i8> %V1, <16 x i8> %V2) {
|
|
; CHECK-LABEL: v16i8:
|
|
; CHECK: @ %bb.0:
|
|
; CHECK-NEXT: vpush {d8, d9, d10, d11, d12, d13, d14, d15}
|
|
; CHECK-NEXT: sub sp, #16
|
|
; CHECK-NEXT: adr.w r12, .LCPI2_0
|
|
; CHECK-NEXT: vdup.32 q7, r1
|
|
; CHECK-NEXT: vldrw.u32 q0, [r12]
|
|
; CHECK-NEXT: vmov.i8 q5, #0x0
|
|
; CHECK-NEXT: vmov.i8 q4, #0xff
|
|
; CHECK-NEXT: vadd.i32 q1, q0, r0
|
|
; CHECK-NEXT: vcmp.u32 cs, q7, q1
|
|
; CHECK-NEXT: vpsel q0, q4, q5
|
|
; CHECK-NEXT: vmov r1, s0
|
|
; CHECK-NEXT: vmov.16 q2[0], r1
|
|
; CHECK-NEXT: vmov r1, s1
|
|
; CHECK-NEXT: vmov.16 q2[1], r1
|
|
; CHECK-NEXT: vmov r1, s2
|
|
; CHECK-NEXT: vmov.16 q2[2], r1
|
|
; CHECK-NEXT: vmov r1, s3
|
|
; CHECK-NEXT: vmov.16 q2[3], r1
|
|
; CHECK-NEXT: adr r1, .LCPI2_1
|
|
; CHECK-NEXT: vldrw.u32 q0, [r1]
|
|
; CHECK-NEXT: vadd.i32 q3, q0, r0
|
|
; CHECK-NEXT: vcmp.u32 cs, q7, q3
|
|
; CHECK-NEXT: vpsel q0, q4, q5
|
|
; CHECK-NEXT: vmov r1, s0
|
|
; CHECK-NEXT: vmov.16 q2[4], r1
|
|
; CHECK-NEXT: vmov r1, s1
|
|
; CHECK-NEXT: vmov.16 q2[5], r1
|
|
; CHECK-NEXT: vmov r1, s2
|
|
; CHECK-NEXT: vmov.16 q2[6], r1
|
|
; CHECK-NEXT: vmov r1, s3
|
|
; CHECK-NEXT: vmov.16 q2[7], r1
|
|
; CHECK-NEXT: vcmp.i16 ne, q2, zr
|
|
; CHECK-NEXT: vpsel q0, q4, q5
|
|
; CHECK-NEXT: vmov.u16 r1, q0[0]
|
|
; CHECK-NEXT: vmov.8 q2[0], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[1]
|
|
; CHECK-NEXT: vmov.8 q2[1], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[2]
|
|
; CHECK-NEXT: vmov.8 q2[2], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[3]
|
|
; CHECK-NEXT: vmov.8 q2[3], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[4]
|
|
; CHECK-NEXT: vmov.8 q2[4], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[5]
|
|
; CHECK-NEXT: vmov.8 q2[5], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[6]
|
|
; CHECK-NEXT: vmov.8 q2[6], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[7]
|
|
; CHECK-NEXT: vmov.8 q2[7], r1
|
|
; CHECK-NEXT: adr r1, .LCPI2_2
|
|
; CHECK-NEXT: vldrw.u32 q0, [r1]
|
|
; CHECK-NEXT: vadd.i32 q0, q0, r0
|
|
; CHECK-NEXT: vcmp.u32 cs, q7, q0
|
|
; CHECK-NEXT: vstrw.32 q0, [sp] @ 16-byte Spill
|
|
; CHECK-NEXT: vpsel q6, q4, q5
|
|
; CHECK-NEXT: vmov r1, s24
|
|
; CHECK-NEXT: vmov.16 q0[0], r1
|
|
; CHECK-NEXT: vmov r1, s25
|
|
; CHECK-NEXT: vmov.16 q0[1], r1
|
|
; CHECK-NEXT: vmov r1, s26
|
|
; CHECK-NEXT: vmov.16 q0[2], r1
|
|
; CHECK-NEXT: vmov r1, s27
|
|
; CHECK-NEXT: vmov.16 q0[3], r1
|
|
; CHECK-NEXT: adr r1, .LCPI2_3
|
|
; CHECK-NEXT: vldrw.u32 q6, [r1]
|
|
; CHECK-NEXT: vadd.i32 q6, q6, r0
|
|
; CHECK-NEXT: vcmp.u32 cs, q7, q6
|
|
; CHECK-NEXT: vpsel q7, q4, q5
|
|
; CHECK-NEXT: vmov r1, s28
|
|
; CHECK-NEXT: vmov.16 q0[4], r1
|
|
; CHECK-NEXT: vmov r1, s29
|
|
; CHECK-NEXT: vmov.16 q0[5], r1
|
|
; CHECK-NEXT: vmov r1, s30
|
|
; CHECK-NEXT: vmov.16 q0[6], r1
|
|
; CHECK-NEXT: vmov r1, s31
|
|
; CHECK-NEXT: vmov.16 q0[7], r1
|
|
; CHECK-NEXT: vdup.32 q7, r0
|
|
; CHECK-NEXT: vcmp.i16 ne, q0, zr
|
|
; CHECK-NEXT: vpsel q0, q4, q5
|
|
; CHECK-NEXT: vcmp.u32 hi, q7, q1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[0]
|
|
; CHECK-NEXT: vpsel q1, q4, q5
|
|
; CHECK-NEXT: vmov.8 q2[8], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[1]
|
|
; CHECK-NEXT: vmov.8 q2[9], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[2]
|
|
; CHECK-NEXT: vmov.8 q2[10], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[3]
|
|
; CHECK-NEXT: vmov.8 q2[11], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[4]
|
|
; CHECK-NEXT: vmov.8 q2[12], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[5]
|
|
; CHECK-NEXT: vmov.8 q2[13], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[6]
|
|
; CHECK-NEXT: vmov r0, s4
|
|
; CHECK-NEXT: vmov.8 q2[14], r1
|
|
; CHECK-NEXT: vmov.u16 r1, q0[7]
|
|
; CHECK-NEXT: vmov.16 q0[0], r0
|
|
; CHECK-NEXT: vmov r0, s5
|
|
; CHECK-NEXT: vcmp.u32 hi, q7, q3
|
|
; CHECK-NEXT: vmov.16 q0[1], r0
|
|
; CHECK-NEXT: vmov r0, s6
|
|
; CHECK-NEXT: vmov.16 q0[2], r0
|
|
; CHECK-NEXT: vmov r0, s7
|
|
; CHECK-NEXT: vpsel q1, q4, q5
|
|
; CHECK-NEXT: vmov.16 q0[3], r0
|
|
; CHECK-NEXT: vmov r0, s4
|
|
; CHECK-NEXT: vmov.8 q2[15], r1
|
|
; CHECK-NEXT: vmov.16 q0[4], r0
|
|
; CHECK-NEXT: vmov r0, s5
|
|
; CHECK-NEXT: vmov.16 q0[5], r0
|
|
; CHECK-NEXT: vmov r0, s6
|
|
; CHECK-NEXT: vmov.16 q0[6], r0
|
|
; CHECK-NEXT: vmov r0, s7
|
|
; CHECK-NEXT: vmov.16 q0[7], r0
|
|
; CHECK-NEXT: vcmp.i16 ne, q0, zr
|
|
; CHECK-NEXT: vpsel q0, q4, q5
|
|
; CHECK-NEXT: vmov.u16 r0, q0[0]
|
|
; CHECK-NEXT: vmov.8 q3[0], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[1]
|
|
; CHECK-NEXT: vmov.8 q3[1], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[2]
|
|
; CHECK-NEXT: vmov.8 q3[2], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[3]
|
|
; CHECK-NEXT: vmov.8 q3[3], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[4]
|
|
; CHECK-NEXT: vmov.8 q3[4], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
|
; CHECK-NEXT: vmov.8 q3[5], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[6]
|
|
; CHECK-NEXT: vmov.8 q3[6], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[7]
|
|
; CHECK-NEXT: vldrw.u32 q0, [sp] @ 16-byte Reload
|
|
; CHECK-NEXT: vmov.8 q3[7], r0
|
|
; CHECK-NEXT: vcmp.u32 hi, q7, q0
|
|
; CHECK-NEXT: vpsel q1, q4, q5
|
|
; CHECK-NEXT: vcmp.u32 hi, q7, q6
|
|
; CHECK-NEXT: vmov r0, s4
|
|
; CHECK-NEXT: vmov.16 q0[0], r0
|
|
; CHECK-NEXT: vmov r0, s5
|
|
; CHECK-NEXT: vmov.16 q0[1], r0
|
|
; CHECK-NEXT: vmov r0, s6
|
|
; CHECK-NEXT: vmov.16 q0[2], r0
|
|
; CHECK-NEXT: vmov r0, s7
|
|
; CHECK-NEXT: vpsel q1, q4, q5
|
|
; CHECK-NEXT: vmov.16 q0[3], r0
|
|
; CHECK-NEXT: vmov r0, s4
|
|
; CHECK-NEXT: vmov.16 q0[4], r0
|
|
; CHECK-NEXT: vmov r0, s5
|
|
; CHECK-NEXT: vmov.16 q0[5], r0
|
|
; CHECK-NEXT: vmov r0, s6
|
|
; CHECK-NEXT: vmov.16 q0[6], r0
|
|
; CHECK-NEXT: vmov r0, s7
|
|
; CHECK-NEXT: vmov.16 q0[7], r0
|
|
; CHECK-NEXT: vcmp.i16 ne, q0, zr
|
|
; CHECK-NEXT: vpsel q0, q4, q5
|
|
; CHECK-NEXT: vmov.u16 r0, q0[0]
|
|
; CHECK-NEXT: vmov.8 q3[8], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[1]
|
|
; CHECK-NEXT: vmov.8 q3[9], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[2]
|
|
; CHECK-NEXT: vmov.8 q3[10], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[3]
|
|
; CHECK-NEXT: vmov.8 q3[11], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[4]
|
|
; CHECK-NEXT: vmov.8 q3[12], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
|
; CHECK-NEXT: vmov.8 q3[13], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[6]
|
|
; CHECK-NEXT: vmov.8 q3[14], r0
|
|
; CHECK-NEXT: vmov.u16 r0, q0[7]
|
|
; CHECK-NEXT: vmov.8 q3[15], r0
|
|
; CHECK-NEXT: vmov d0, r2, r3
|
|
; CHECK-NEXT: add r0, sp, #88
|
|
; CHECK-NEXT: vcmp.i8 ne, q3, zr
|
|
; CHECK-NEXT: vldr d1, [sp, #80]
|
|
; CHECK-NEXT: vldrw.u32 q1, [r0]
|
|
; CHECK-NEXT: vpnot
|
|
; CHECK-NEXT: vpst
|
|
; CHECK-NEXT: vcmpt.i8 ne, q2, zr
|
|
; CHECK-NEXT: vpsel q0, q0, q1
|
|
; CHECK-NEXT: vmov r0, r1, d0
|
|
; CHECK-NEXT: vmov r2, r3, d1
|
|
; CHECK-NEXT: add sp, #16
|
|
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13, d14, d15}
|
|
; CHECK-NEXT: bx lr
|
|
; CHECK-NEXT: .p2align 4
|
|
; CHECK-NEXT: @ %bb.1:
|
|
; CHECK-NEXT: .LCPI2_0:
|
|
; CHECK-NEXT: .long 0 @ 0x0
|
|
; CHECK-NEXT: .long 1 @ 0x1
|
|
; CHECK-NEXT: .long 2 @ 0x2
|
|
; CHECK-NEXT: .long 3 @ 0x3
|
|
; CHECK-NEXT: .LCPI2_1:
|
|
; CHECK-NEXT: .long 4 @ 0x4
|
|
; CHECK-NEXT: .long 5 @ 0x5
|
|
; CHECK-NEXT: .long 6 @ 0x6
|
|
; CHECK-NEXT: .long 7 @ 0x7
|
|
; CHECK-NEXT: .LCPI2_2:
|
|
; CHECK-NEXT: .long 8 @ 0x8
|
|
; CHECK-NEXT: .long 9 @ 0x9
|
|
; CHECK-NEXT: .long 10 @ 0xa
|
|
; CHECK-NEXT: .long 11 @ 0xb
|
|
; CHECK-NEXT: .LCPI2_3:
|
|
; CHECK-NEXT: .long 12 @ 0xc
|
|
; CHECK-NEXT: .long 13 @ 0xd
|
|
; CHECK-NEXT: .long 14 @ 0xe
|
|
; CHECK-NEXT: .long 15 @ 0xf
|
|
%active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %BTC)
|
|
%select = select <16 x i1> %active.lane.mask, <16 x i8> %V1, <16 x i8> %V2
|
|
ret <16 x i8> %select
|
|
}
|
|
|
|
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
|
|
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)
|
|
declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32, i32)
|