19dc9c9780
Move the code which adjusts the immediate/predicate on a G_ICMP to AArch64PostLegalizerLowering. This - Reduces the number of places we need to test for optimized compares in the selector. We know that the compare should have been simplified by the time it hits the selector, so we can avoid testing this in selects, brconds, etc. - Allows us to potentially fold more compares (previously, this optimization was only done after calling `tryFoldCompare`, this may allow us to hit some more TST cases) - Simplifies the selection code in `emitIntegerCompare` significantly; we can just use an emitSUBS function. - Allows us to avoid checking that the predicate has been updated after `emitIntegerCompare`. Also add a utility header file for things that may be useful in the selector and various combiners. No need for an implementation file at this point, since it's just one constexpr function for now. I've run into a couple cases where having one of these would be handy, so might as well add it here. There are a couple functions in the selector that can probably be factored out into here. Differential Revision: https://reviews.llvm.org/D89823
95 lines
2.8 KiB
YAML
95 lines
2.8 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -O0 -mtriple=aarch64 -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s
|
|
#
|
|
# Verify that we can fold compares into integer selects.
|
|
#
|
|
# This is an integer version of fold-fp-select.mir.
|
|
#
|
|
|
|
...
|
|
---
|
|
name: eq
|
|
alignment: 4
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $w0, $w1
|
|
|
|
; CHECK-LABEL: name: eq
|
|
; CHECK: liveins: $w0, $w1
|
|
; CHECK: [[COPY:%[0-9]+]]:gpr32sp = COPY $w0
|
|
; CHECK: [[COPY1:%[0-9]+]]:gpr32 = COPY $w1
|
|
; CHECK: [[COPY2:%[0-9]+]]:gpr32 = COPY $wzr
|
|
; CHECK: [[SUBSWri:%[0-9]+]]:gpr32 = SUBSWri [[COPY]], 0, 0, implicit-def $nzcv
|
|
; CHECK: [[CSELWr:%[0-9]+]]:gpr32 = CSELWr [[COPY2]], [[COPY1]], 0, implicit $nzcv
|
|
; CHECK: $w0 = COPY [[CSELWr]]
|
|
; CHECK: RET_ReallyLR implicit $w0
|
|
%0:gpr(s32) = COPY $w0
|
|
%1:gpr(s32) = COPY $w1
|
|
%2:gpr(s32) = G_CONSTANT i32 0
|
|
%5:gpr(s32) = G_ICMP intpred(eq), %0(s32), %2
|
|
%3:gpr(s1) = G_TRUNC %5(s32)
|
|
%4:gpr(s32) = G_SELECT %3(s1), %2, %1
|
|
$w0 = COPY %4(s32)
|
|
RET_ReallyLR implicit $w0
|
|
|
|
...
|
|
---
|
|
name: using_fcmp
|
|
alignment: 4
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $s0, $w0, $w1
|
|
|
|
; CHECK-LABEL: name: using_fcmp
|
|
; CHECK: liveins: $s0, $w0, $w1
|
|
; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w1
|
|
; CHECK: [[COPY1:%[0-9]+]]:fpr32 = COPY $s0
|
|
; CHECK: [[COPY2:%[0-9]+]]:gpr32 = COPY $wzr
|
|
; CHECK: FCMPSri [[COPY1]], implicit-def $nzcv
|
|
; CHECK: [[CSELWr:%[0-9]+]]:gpr32 = CSELWr [[COPY2]], [[COPY]], 0, implicit $nzcv
|
|
; CHECK: $w0 = COPY [[CSELWr]]
|
|
; CHECK: RET_ReallyLR implicit $w0
|
|
%1:gpr(s32) = COPY $w1
|
|
%2:fpr(s32) = COPY $s0
|
|
%3:fpr(s32) = G_FCONSTANT float 0.000000e+00
|
|
%6:gpr(s32) = G_CONSTANT i32 0
|
|
%7:gpr(s32) = G_FCMP floatpred(oeq), %2(s32), %3
|
|
%4:gpr(s1) = G_TRUNC %7(s32)
|
|
%5:gpr(s32) = G_SELECT %4(s1), %6, %1
|
|
$w0 = COPY %5(s32)
|
|
RET_ReallyLR implicit $w0
|
|
|
|
...
|
|
---
|
|
name: csinc
|
|
alignment: 4
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $w0, $w1
|
|
|
|
; CHECK-LABEL: name: csinc
|
|
; CHECK: liveins: $w0, $w1
|
|
; CHECK: [[COPY:%[0-9]+]]:gpr32common = COPY $w0
|
|
; CHECK: [[SUBSWri:%[0-9]+]]:gpr32 = SUBSWri [[COPY]], 1, 0, implicit-def $nzcv
|
|
; CHECK: [[CSINCWr:%[0-9]+]]:gpr32 = CSINCWr [[COPY]], $wzr, 0, implicit $nzcv
|
|
; CHECK: $w0 = COPY [[CSINCWr]]
|
|
; CHECK: RET_ReallyLR implicit $w0
|
|
%0:gpr(s32) = COPY $w0
|
|
%1:gpr(s32) = COPY $w1
|
|
%2:gpr(s32) = G_CONSTANT i32 1
|
|
%5:gpr(s32) = G_ICMP intpred(eq), %0(s32), %2
|
|
%3:gpr(s1) = G_TRUNC %5(s32)
|
|
%4:gpr(s32) = G_SELECT %3(s1), %0, %2
|
|
$w0 = COPY %4(s32)
|
|
RET_ReallyLR implicit $w0
|
|
...
|