maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AVR/select-must-add-uncondition...

59 lines
1.9 KiB
LLVM
Raw Normal View History

[CodeGenPrep] Skip merging empty case blocks This is recommit of r287553 after fixing the invalid loop info after eliminating an empty block and unit test failures in AVR and WebAssembly : Summary: Merging an empty case block into the header block of switch could cause ISel to add COPY instructions in the header of switch, instead of the case block, if the case block is used as an incoming block of a PHI. This could potentially increase dynamic instructions, especially when the switch is in a loop. I added a test case which was reduced from the benchmark I was targetting. Reviewers: t.p.northover, mcrosier, manmanren, wmi, joerg, davidxl Subscribers: joerg, qcolombet, danielcdh, hfinkel, mcrosier, llvm-commits Differential Revision: https://reviews.llvm.org/D22696 llvm-svn: 289988
2016-12-17 04:38:39 +08:00
; RUN: llc -march=avr -print-after=expand-isel-pseudos -cgp-freq-ratio-to-skip-merge=10 < %s 2>&1 | FileCheck %s
[AVR] Add a selection of CodeGen tests Summary: This adds all of the CodeGen tests which currently pass. Reviewers: arsenm, kparzysz Subscribers: japaric, wdng Differential Revision: https://reviews.llvm.org/D26388 llvm-svn: 286418
2016-11-10 07:46:52 +08:00
; Because `switch` seems to trigger Machine Basic Blocks to be ordered
; in a different order than they were constructed, this exposes an
; error in the `expand-isel-pseudos` pass. Specifically, it thought we
; could always fallthrough to a newly-constructed MBB. However,
; there's no guarantee that either of the constructed MBBs need to
; occur immediately after the currently-focused one!
;
; This issue manifests in a CFG that looks something like this:
;
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; %bb.2: derived from LLVM BB %finish
; Predecessors according to CFG: %bb.0 %bb.1
; %0<def> = PHI %3, <%bb.0>, %5, <%bb.1>
[CodeGen] Print "%vreg0" as "%0" in both MIR and debug output As part of the unification of the debug format and the MIR format, avoid printing "vreg" for virtual registers (which is one of the current MIR possibilities). Basically: * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E "s/%vreg([0-9]+)/%\1/g" * grep -nr '%vreg' . and fix if needed * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E "s/ vreg([0-9]+)/ %\1/g" * grep -nr 'vreg[0-9]\+' . and fix if needed Differential Revision: https://reviews.llvm.org/D40420 llvm-svn: 319427
2017-11-30 20:12:19 +08:00
; %7<def> = LDIRdK 2
; %8<def> = LDIRdK 1
; CPRdRr %2, %0, %SREG<imp-def>
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; BREQk <%bb.6>, %SREG<imp-use>
; Successors according to CFG: %bb.5(?%) %bb.6(?%)
[AVR] Add a selection of CodeGen tests Summary: This adds all of the CodeGen tests which currently pass. Reviewers: arsenm, kparzysz Subscribers: japaric, wdng Differential Revision: https://reviews.llvm.org/D26388 llvm-svn: 286418
2016-11-10 07:46:52 +08:00
;
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; The code assumes it the fallthrough block after this is %bb.5, but
; it's actually %bb.3! To be proper, there should be an unconditional
; jump tying this block to %bb.5.
[AVR] Add a selection of CodeGen tests Summary: This adds all of the CodeGen tests which currently pass. Reviewers: arsenm, kparzysz Subscribers: japaric, wdng Differential Revision: https://reviews.llvm.org/D26388 llvm-svn: 286418
2016-11-10 07:46:52 +08:00
define i8 @select_must_add_unconditional_jump(i8 %arg0, i8 %arg1) unnamed_addr {
entry-block:
switch i8 %arg0, label %dead [
i8 0, label %zero
i8 1, label %one
]
zero:
br label %finish
one:
br label %finish
finish:
%predicate = phi i8 [ 50, %zero ], [ 100, %one ]
%is_eq = icmp eq i8 %arg1, %predicate
%result = select i1 %is_eq, i8 1, i8 2
ret i8 %result
dead:
ret i8 0
}
; This check may be a bit brittle, but the important thing is that the
; basic block containing `select` needs to contain explicit jumps to
; both successors.
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: %bb.2: derived from LLVM BB %finish
; CHECK: BREQk <[[BRANCHED:%bb.[0-9]+]]>
; CHECK: RJMPk <[[DIRECT:%bb.[0-9]+]]>
[AVR] Add a selection of CodeGen tests Summary: This adds all of the CodeGen tests which currently pass. Reviewers: arsenm, kparzysz Subscribers: japaric, wdng Differential Revision: https://reviews.llvm.org/D26388 llvm-svn: 286418
2016-11-10 07:46:52 +08:00
; CHECK: Successors according to CFG
; CHECK-SAME-DAG: {{.*}}[[BRANCHED]]
; CHECK-SAME-DAG: {{.*}}[[DIRECT]]
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: %bb.3: derived from LLVM BB