reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s

define arm_aapcs_vfpcc <4 x i32> @test_vldrwq_gather_base_wb_s32(<4 x i32>* %addr) {
; CHECK-LABEL: test_vldrwq_gather_base_wb_s32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vldrw.u32 q0, [r0]
; CHECK-NEXT:    vldrw.u32 q1, [q0, #80]!
; CHECK-NEXT:    vstrw.32 q1, [r0]
; CHECK-NEXT:    bx lr
entry:
  %0 = load <4 x i32>, <4 x i32>* %addr, align 8
  %1 = tail call { <4 x i32>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.v4i32.v4i32(<4 x i32> %0, i32 80)
  %2 = extractvalue { <4 x i32>, <4 x i32> } %1, 1
  store <4 x i32> %2, <4 x i32>* %addr, align 8
  %3 = extractvalue { <4 x i32>, <4 x i32> } %1, 0
  ret <4 x i32> %3
}

declare { <4 x i32>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.v4i32.v4i32(<4 x i32>, i32)

define arm_aapcs_vfpcc <4 x float> @test_vldrwq_gather_base_wb_f32(<4 x i32>* %addr) {
; CHECK-LABEL: test_vldrwq_gather_base_wb_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vldrw.u32 q0, [r0]
; CHECK-NEXT:    vldrw.u32 q1, [q0, #64]!
; CHECK-NEXT:    vstrw.32 q1, [r0]
; CHECK-NEXT:    bx lr
entry:
  %0 = load <4 x i32>, <4 x i32>* %addr, align 8
  %1 = tail call { <4 x float>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.v4f32.v4i32(<4 x i32> %0, i32 64)
  %2 = extractvalue { <4 x float>, <4 x i32> } %1, 1
  store <4 x i32> %2, <4 x i32>* %addr, align 8
  %3 = extractvalue { <4 x float>, <4 x i32> } %1, 0
  ret <4 x float> %3
}

declare { <4 x float>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.v4f32.v4i32(<4 x i32>, i32)

define arm_aapcs_vfpcc <2 x i64> @test_vldrdq_gather_base_wb_z_u64(<2 x i64>* %addr, i16 zeroext %p) {
; CHECK-LABEL: test_vldrdq_gather_base_wb_z_u64:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r1
; CHECK-NEXT:    vldrw.u32 q0, [r0]
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vldrdt.u64 q1, [q0, #656]!
; CHECK-NEXT:    vstrw.32 q1, [r0]
; CHECK-NEXT:    bx lr
entry:
  %0 = load <2 x i64>, <2 x i64>* %addr, align 8
  %1 = zext i16 %p to i32
  %2 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %1)
  %3 = tail call { <2 x i64>, <2 x i64> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v2i64.v2i64.v4i1(<2 x i64> %0, i32 656, <4 x i1> %2)
  %4 = extractvalue { <2 x i64>, <2 x i64> } %3, 1
  store <2 x i64> %4, <2 x i64>* %addr, align 8
  %5 = extractvalue { <2 x i64>, <2 x i64> } %3, 0
  ret <2 x i64> %5
}

declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32)

declare { <2 x i64>, <2 x i64> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v2i64.v2i64.v4i1(<2 x i64>, i32, <4 x i1>)