This is an archive of the discontinued LLVM Phabricator instance.

Differential D65277

[ARM][LowOverheadLoops] Enable by default
ClosedPublic

Authored by samparker on Jul 25 2019, 5:47 AM.

Details

Reviewers
SjoerdMeijer
dmgreen
Commits
rGe3a4a13fcc0d: [ARM][LowOverheadLoops] Enable by default
rL367297: [ARM][LowOverheadLoops] Enable by default
Summary

The code is now in a good enough state to pass the bunch of tests that I have run (after fixing the bugs), so let's enable it by default.

Diff Detail

Repository
rL LLVM

Event Timeline

samparker created this revision.Jul 25 2019, 5:47 AM
Herald added subscribers: kristof.beyls, javed.absar. · View Herald TranscriptJul 25 2019, 5:47 AM
samparker added parent revisions: D65268: [ARM][LowOverheadLoops] Revert non-header LE target, D65275: [ARM][LowOverheadLoops] Add CPSR defs.Jul 25 2019, 5:47 AM
SjoerdMeijer accepted this revision.Jul 26 2019, 12:17 AM

Yep, sounds good, let's go for it.

This revision is now accepted and ready to land.Jul 26 2019, 12:17 AM
Closed by commit rL367297: [ARM][LowOverheadLoops] Enable by default (authored by sam_parker). · Explain WhyJul 30 2019, 1:16 AM
This revision was automatically updated to reflect the committed changes.
Herald added a project: Restricted Project. · View Herald TranscriptJul 30 2019, 1:16 AM

Revision Contents

PathSize
llvm/
trunk/
lib/
Target/
ARM/
2 lines
test/
Transforms/
HardwareLoops/
ARM/
5 lines
13 lines
2 lines
2 lines
4 lines
5 lines
6 lines

Diff 212289

llvm/trunk/lib/Target/ARM/ARMTargetTransformInfo.cpp

Show All 31 Lines
#include <cstdint> #include <cstdint>
#include <utility> #include <utility>
using namespace llvm; using namespace llvm;
#define DEBUG_TYPE "armtti" #define DEBUG_TYPE "armtti"
static cl::opt<bool> DisableLowOverheadLoops( static cl::opt<bool> DisableLowOverheadLoops(
"disable-arm-loloops", cl::Hidden, cl::init(true), "disable-arm-loloops", cl::Hidden, cl::init(false),
cl::desc("Disable the generation of low-overhead loops")); cl::desc("Disable the generation of low-overhead loops"));
bool ARMTTIImpl::areInlineCompatible(const Function *Caller, bool ARMTTIImpl::areInlineCompatible(const Function *Caller,
const Function *Callee) const { const Function *Callee) const {
const TargetMachine &TM = getTLI()->getTargetMachine(); const TargetMachine &TM = getTLI()->getTargetMachine();
const FeatureBitset &CallerBits = const FeatureBitset &CallerBits =
TM.getSubtargetImpl(*Caller)->getFeatureBits(); TM.getSubtargetImpl(*Caller)->getFeatureBits();
const FeatureBitset &CalleeBits = const FeatureBitset &CalleeBits =
▲ Show 20 Lines • Show All 868 Lines • Show Last 20 Lines

llvm/trunk/test/Transforms/HardwareLoops/ARM/calls-codegen.ll

; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+lob,+mve.fp -disable-arm-loloops=false %s -o - | FileCheck %s ; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+lob,+mve.fp -disable-arm-loloops=true %s -o - | FileCheck %s --check-prefix=DISABLED
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+lob,+mve.fp %s -o - | FileCheck %s
; DISABLED-NOT: dls lr,
; CHECK-LABEL: test_target_specific: ; CHECK-LABEL: test_target_specific:
; CHECK: mov.w lr, #50 ; CHECK: mov.w lr, #50
; CHECK: dls lr, lr ; CHECK: dls lr, lr
; CHECK-NOT: mov lr, ; CHECK-NOT: mov lr,
; CHECK: [[LOOP_HEADER:\.LBB[0-9_]+]]: ; CHECK: [[LOOP_HEADER:\.LBB[0-9_]+]]:
; CHECK: le lr, [[LOOP_HEADER]] ; CHECK: le lr, [[LOOP_HEADER]]
; CHECK-NOT: b . ; CHECK-NOT: b .
▲ Show 20 Lines • Show All 49 Lines • Show Last 20 Lines

llvm/trunk/test/Transforms/HardwareLoops/ARM/calls.ll

; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MAIN ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MAIN
; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+fullfp16 -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+fullfp16 -hardware-loops %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP
; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+fp-armv8,+fullfp16 -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP64 ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+fp-armv8,+fullfp16 -hardware-loops %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP64
; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVE ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve -hardware-loops %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVE
; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVEFP ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp -hardware-loops %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVEFP
; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops -disable-arm-loloops=true %s -S -o - | FileCheck %s --check-prefix=DISABLED
; DISABLED-NOT: call i32 @llvm.loop.decrement
; CHECK-LABEL: skip_call ; CHECK-LABEL: skip_call
; CHECK-NOT: call void @llvm.set.loop.iterations ; CHECK-NOT: call void @llvm.set.loop.iterations
; CHECK-NOT: call i32 @llvm.loop.decrement ; CHECK-NOT: call i32 @llvm.loop.decrement
define i32 @skip_call(i32 %n) { define i32 @skip_call(i32 %n) {
entry: entry:
%cmp6 = icmp eq i32 %n, 0 %cmp6 = icmp eq i32 %n, 0
▲ Show 20 Lines • Show All 391 Lines • Show Last 20 Lines

llvm/trunk/test/Transforms/HardwareLoops/ARM/counter.ll

; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops -disable-arm-loloops=false %s -o - | FileCheck %s ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops %s -o - | FileCheck %s
@g = common local_unnamed_addr global i32* null, align 4 @g = common local_unnamed_addr global i32* null, align 4
; CHECK-LABEL: counter_too_large ; CHECK-LABEL: counter_too_large
; CHECK-NOT: call void @llvm.set.loop.iterations ; CHECK-NOT: call void @llvm.set.loop.iterations
; CHECK-NOT: call i32 @llvm.loop.decrement ; CHECK-NOT: call i32 @llvm.loop.decrement
define i32 @counter_too_large(i64 %n) { define i32 @counter_too_large(i64 %n) {
Show All 26 Lines

llvm/trunk/test/Transforms/HardwareLoops/ARM/do-rem.ll

; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops %s -S -o - | FileCheck %s
@g = common local_unnamed_addr global i32* null, align 4 @g = common local_unnamed_addr global i32* null, align 4
; CHECK-LABEL: do_with_i32_urem ; CHECK-LABEL: do_with_i32_urem
; CHECK: entry: ; CHECK: entry:
; CHECK: [[TEST:%[^ ]+]] = call i1 @llvm.test.set.loop.iterations.i32(i32 %n) ; CHECK: [[TEST:%[^ ]+]] = call i1 @llvm.test.set.loop.iterations.i32(i32 %n)
; CHECK: br i1 [[TEST]], label %while.body.preheader, label %while.end ; CHECK: br i1 [[TEST]], label %while.body.preheader, label %while.end
▲ Show 20 Lines • Show All 266 Lines • Show Last 20 Lines

llvm/trunk/test/Transforms/HardwareLoops/ARM/fp-emulation.ll

; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+fp-armv8 -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+fp-armv8 -hardware-loops %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP
; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+soft-float -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-SOFT ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+soft-float -hardware-loops %s -S -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-SOFT
; CHECK-LABEL: test_fptosi ; CHECK-LABEL: test_fptosi
; CHECK-SOFT-NOT: call void @llvm.set.loop.iterations ; CHECK-SOFT-NOT: call void @llvm.set.loop.iterations
; CHECK: entry: ; CHECK: entry:
; CHECK-FP: [[CMP:%[^ ]+]] = icmp ugt i32 %n, 1 ; CHECK-FP: [[CMP:%[^ ]+]] = icmp ugt i32 %n, 1
; CHECK-FP: [[COUNT:%[^ ]+]] = select i1 [[CMP]], i32 %n, i32 1 ; CHECK-FP: [[COUNT:%[^ ]+]] = select i1 [[CMP]], i32 %n, i32 1
▲ Show 20 Lines • Show All 200 Lines • Show Last 20 Lines

llvm/trunk/test/Transforms/HardwareLoops/ARM/simple-do.ll

; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops %s -S -o - | FileCheck %s
; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops -disable-arm-loloops=true %s -S -o - | FileCheck %s --check-prefix=DISABLED ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops -disable-arm-loloops=true %s -S -o - | FileCheck %s --check-prefix=DISABLED
; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=-lob -hardware-loops %s -S -o - | FileCheck %s --check-prefix=DISABLED ; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi %s -o - | FileCheck %s --check-prefix=CHECK-LLC
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -disable-arm-loloops=false %s -o - | FileCheck %s --check-prefix=CHECK-LLC
; DISABLED-NOT: llvm.{{.*}}.loop.iterations ; DISABLED-NOT: llvm.{{.*}}.loop.iterations
; DISABLED-NOT: llvm.loop.decrement ; DISABLED-NOT: llvm.loop.decrement
@g = common local_unnamed_addr global i32* null, align 4 @g = common local_unnamed_addr global i32* null, align 4
; CHECK-LABEL: do_copy ; CHECK-LABEL: do_copy
; CHECK: call void @llvm.set.loop.iterations.i32(i32 %n) ; CHECK: call void @llvm.set.loop.iterations.i32(i32 %n)
▲ Show 20 Lines • Show All 184 Lines • Show Last 20 Lines

llvm/trunk/test/Transforms/HardwareLoops/ARM/structure.ll

; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops -disable-arm-loloops=false %s -S -o - | FileCheck %s ; RUN: opt -mtriple=thumbv8.1m.main-arm-none-eabi -hardware-loops %s -S -o - | FileCheck %s
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -disable-arm-loloops=false %s -o - | FileCheck %s --check-prefix=CHECK-LLC ; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi %s -o - | FileCheck %s --check-prefix=CHECK-LLC
; RUN: opt -mtriple=thumbv8.1m.main -loop-unroll -unroll-remainder=false -S < %s | llc -mtriple=thumbv8.1m.main -disable-arm-loloops=false | FileCheck %s --check-prefix=CHECK-UNROLL ; RUN: opt -mtriple=thumbv8.1m.main -loop-unroll -unroll-remainder=false -S < %s | llc -mtriple=thumbv8.1m.main | FileCheck %s --check-prefix=CHECK-UNROLL
; CHECK-LABEL: early_exit ; CHECK-LABEL: early_exit
; CHECK-NOT: llvm.set.loop.iterations ; CHECK-NOT: llvm.set.loop.iterations
; CHECK-NOT: llvm.loop.decrement ; CHECK-NOT: llvm.loop.decrement
define i32 @early_exit(i32* nocapture readonly %a, i32 %max, i32 %n) { define i32 @early_exit(i32* nocapture readonly %a, i32 %max, i32 %n) {
entry: entry:
br label %do.body br label %do.body
▲ Show 20 Lines • Show All 423 Lines • Show Last 20 Lines