regcoal-invalid-subrange-update.mir 3.46 KB
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc %s -start-before simple-register-coalescing -mtriple=arm-apple-ios -stop-after machine-scheduler -o - -arm-enable-subreg-liveness -verify-machineinstrs | FileCheck %s

# Check that when we merge live-ranges that imply offseting
# the definition of a subregister by some other subreg index,
# we take that new index into account while updating the subrange.
#
# For this specific test case, the coalescer is going to get rid
# of `%5.dsub_1:dtriple = COPY %4.dsub_3` by aligning
# %5.dsub_1:<3 x s64> with %4.dsub_3:<4 x s64>.
# This is done by moving to a bigger register class <5 x s64>
# and offseting %5 definitions with a new subregidx:
# NewVar: <5 x s64> dsub_0 dsub_1 dsub_2 dsub_3 dsub_4
# %4:     <4 x s64> dsub_0 dsub_1 dsub_2 dsub_3
# %5:     <3 x s64> <==offset===> dsub_0 dsub_1 dsub_2
#
# In other %5.dsub_0 needs to be mapped to NewVar.dsub_2, %5.dsub_1
# to NewVar.dsub_3 and so on. So essentially we are offseting %5 by
# dsub_2.
#
# When updating the live-ranges, the register coalescer actually
# has not rewritten the original code, so we need to fake the
# rewrite to do that update.
# This used to be wrong and this test was failling with a machine
# verifier error: No live segment at def.
#
# The test case runs through the coalescer *and* the scheduler, just
# to force the live intervals to be carried around so that the verifier
# gets a chance to verify those. If we were to just run the coalescer,
# the live intervals would be dropped before running the verifier since
# no other pass would need that analysis around.
#
# Note: The test case looks slightly more complicated than just the
#       offseting part. That's because the bug needs three things to
#       trigger:
#       1. Overlapping subreg lanes: here, dsub0 == <ssub0, ssub1>
#       2. Tuple registers with a possibility to coalesce the subreg index:
#          here, what we explain with %5.dsub_1 == %4.dsub_3
#       3. Subreg liveness enabled.
# #1 is required to trigger the splitting of subranges that implies
# looking at the IR to decide what is alive and what is not.
# #2 is what produces the IR to be out-of-synce with what the reg coalescer
# maintains for the live-ranges information.
# #3 is, well, the problem has to do with subranges updates!
#
# In the end, the expected result is to have all the variables
# being coalesced in one big (qqqq) variable.
---
name:            main
alignment:       1
tracksRegLiveness: true
frameInfo:
  maxAlignment:    1
machineFunctionInfo: {}
body:             |
  bb.0:
    liveins: $d2, $s1, $d4


    ; CHECK-LABEL: name: main
    ; CHECK: liveins: $d2, $s1, $d4
    ; CHECK: undef %4.dsub_0:qqqqpr_with_ssub_4 = COPY $d4
    ; CHECK: %4.ssub_4:qqqqpr_with_ssub_4 = COPY $s1
    ; CHECK: %4.dsub_1:qqqqpr_with_ssub_4 = COPY $d2
    ; CHECK: %4.dsub_3:qqqqpr_with_ssub_4 = COPY %4.dsub_1
    ; CHECK: KILL implicit-def %4.dsub_2, implicit %4.qqsub_0
    ; CHECK: %4.dsub_4:qqqqpr_with_ssub_4 = COPY %4.dsub_1
    ; CHECK: tBX_RET 14 /* CC::al */, $noreg, implicit %4.ssub_4_ssub_5_ssub_6_ssub_7_ssub_8_ssub_9
    %3:dpr_vfp2 = COPY $d4
    undef %0.ssub_0:dpr_vfp2 = COPY $s1
    %1:dpr_vfp2 = COPY $d2
    undef %4.dsub_0:dquad = COPY %3
    %4.dsub_1:dquad = COPY %1
    %4.dsub_2:dquad = COPY %0
    %4.dsub_3:dquad = COPY %1
    KILL implicit-def undef %5.dsub_0:dtriple, implicit %4
    %5.dsub_1:dtriple = COPY %4.dsub_3
    %5.dsub_2:dtriple = COPY %1
    tBX_RET 14, $noreg, implicit %5

...