HaoyuZhang created this revision.
Herald added a subscriber: wenlei.
Herald added a project: All.
HaoyuZhang requested review of this revision.
Herald added subscribers: cfe-commits, MaskRay.
Herald added a project: clang.
This patch enable -sample-profile-use-profi in Clang frontend as user-facing
feature. By using this patch, we can use the cflag of
"-fsample-profile-use-profi"
instead of "-mllvm -sample-profile-use-profi".
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D136846
Files:
clang/include/clang/Driver/Options.td
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/CodeGen/Inputs/pgo-sample-use-profi.prof
clang/test/CodeGen/pgo-sample-use-profi.cpp
Index: clang/test/CodeGen/pgo-sample-use-profi.cpp
===================================================================
--- /dev/null
+++ clang/test/CodeGen/pgo-sample-use-profi.cpp
@@ -0,0 +1,38 @@
+//Test if profi flat is enabled in frontend as user-facing feature.
+//
+//RUN: %clang++ -c -O2 -g
-fprofile-sample-use=%S/Inputs/pgo-sample-use-profi.prof %s -emit-llvm -o - |
opt -passes='print<branch-prob>' -disable-output 2>&1 | FileCheck %s
--check-prefix=CHECK1
+//RUN: %clang++ -c -O2 -g
-fprofile-sample-use=%S/Inputs/pgo-sample-use-profi.prof -mllvm
-sample-profile-use-profi %s -emit-llvm -o - | opt -passes='print<branch-prob>'
-disable-output 2>&1 | FileCheck %s --check-prefix=CHECK2
+//RUN: %clang++ -c -O2 -g
-fprofile-sample-use=%S/Inputs/pgo-sample-use-profi.prof
-fsample-profile-use-profi %s -emit-llvm -o - | opt
-passes='print<branch-prob>' -disable-output 2>&1 | FileCheck %s
--check-prefix=CHECK2
+
+// Check the profi algorithm can fix the block and with using the user-facing
feature can achieve the same result of using "-mllvm"
+// CHECK1: for.body.preheader.preheader probability is 0x7ffe64db / 0x80000000
= 100.00% [HOT edge]
+// CHECK2: for.body.preheader.preheader probability is 0x7ffe64d6 / 0x80000000
= 100.00% [HOT edge]
+
+const int N = 30000;
+
+__attribute__ ((noinline)) void bubble_sort (int *a, int n) {
+ int i, t, s = 1;
+ while (s) {
+ s = 0;
+ for (i = 1; i < n; i++) {
+ if (a[i] < a[i - 1]) {
+ t = a[i];
+ a[i] = a[i - 1];
+ a[i - 1] = t;
+ s = 1;
+ }
+ }
+ }
+}
+
+int main() {
+ int data[N];
+ for (int i = 0; i < N; i ++) {
+ if (i%2 == 0)
+ data[i] = i;
+ else
+ data[i] = -i;
+ }
+ bubble_sort(data, N);
+ return 0;
+}
\ No newline at end of file
Index: clang/test/CodeGen/Inputs/pgo-sample-use-profi.prof
===================================================================
--- /dev/null
+++ clang/test/CodeGen/Inputs/pgo-sample-use-profi.prof
@@ -0,0 +1,8 @@
+_Z11bubble_sortPii:965211:0
+ 0: 0
+ 2: 4
+ 4: 19852
+ 5: 20401
+ 7: 4556
+ 8: 4556
+ 13: 0
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -5760,6 +5760,12 @@
Args.AddLastArg(CmdArgs, options::OPT_fclang_abi_compat_EQ);
+ // Enable profi in frontend and forward to LLVM invocation
+ if (Args.hasArg(options::OPT_fsample_profile_use_profi)) {
+ CmdArgs.push_back("-mllvm");
+ CmdArgs.push_back("-sample-profile-use-profi");
+ }
+
// Add runtime flag for PS4/PS5 when PGO, coverage, or sanitizers are
enabled.
if (RawTriple.isPS() &&
!Args.hasArg(options::OPT_nostdlib, options::OPT_nodefaultlibs)) {
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -1248,6 +1248,9 @@
as cold. Otherwise, treat callsites without profile samples as
if
we have no profile}]>,
MarshallingInfoFlag<CodeGenOpts<"ProfileSampleAccurate">>;
+def fsample_profile_use_profi : Flag<["-"], "fsample-profile-use-profi">,
+ Flags<[NoXarchOption, CC1Option]>, Group<f_Group>,
+ HelpText<"Use profi to infer block and edge counts.">;
def fno_profile_sample_accurate : Flag<["-"], "fno-profile-sample-accurate">,
Group<f_Group>, Flags<[NoXarchOption]>;
def fauto_profile : Flag<["-"], "fauto-profile">, Group<f_Group>,
Index: clang/test/CodeGen/pgo-sample-use-profi.cpp
===================================================================
--- /dev/null
+++ clang/test/CodeGen/pgo-sample-use-profi.cpp
@@ -0,0 +1,38 @@
+//Test if profi flat is enabled in frontend as user-facing feature.
+//
+//RUN: %clang++ -c -O2 -g -fprofile-sample-use=%S/Inputs/pgo-sample-use-profi.prof %s -emit-llvm -o - | opt -passes='print<branch-prob>' -disable-output 2>&1 | FileCheck %s --check-prefix=CHECK1
+//RUN: %clang++ -c -O2 -g -fprofile-sample-use=%S/Inputs/pgo-sample-use-profi.prof -mllvm -sample-profile-use-profi %s -emit-llvm -o - | opt -passes='print<branch-prob>' -disable-output 2>&1 | FileCheck %s --check-prefix=CHECK2
+//RUN: %clang++ -c -O2 -g -fprofile-sample-use=%S/Inputs/pgo-sample-use-profi.prof -fsample-profile-use-profi %s -emit-llvm -o - | opt -passes='print<branch-prob>' -disable-output 2>&1 | FileCheck %s --check-prefix=CHECK2
+
+// Check the profi algorithm can fix the block and with using the user-facing feature can achieve the same result of using "-mllvm"
+// CHECK1: for.body.preheader.preheader probability is 0x7ffe64db / 0x80000000 = 100.00% [HOT edge]
+// CHECK2: for.body.preheader.preheader probability is 0x7ffe64d6 / 0x80000000 = 100.00% [HOT edge]
+
+const int N = 30000;
+
+__attribute__ ((noinline)) void bubble_sort (int *a, int n) {
+ int i, t, s = 1;
+ while (s) {
+ s = 0;
+ for (i = 1; i < n; i++) {
+ if (a[i] < a[i - 1]) {
+ t = a[i];
+ a[i] = a[i - 1];
+ a[i - 1] = t;
+ s = 1;
+ }
+ }
+ }
+}
+
+int main() {
+ int data[N];
+ for (int i = 0; i < N; i ++) {
+ if (i%2 == 0)
+ data[i] = i;
+ else
+ data[i] = -i;
+ }
+ bubble_sort(data, N);
+ return 0;
+}
\ No newline at end of file
Index: clang/test/CodeGen/Inputs/pgo-sample-use-profi.prof
===================================================================
--- /dev/null
+++ clang/test/CodeGen/Inputs/pgo-sample-use-profi.prof
@@ -0,0 +1,8 @@
+_Z11bubble_sortPii:965211:0
+ 0: 0
+ 2: 4
+ 4: 19852
+ 5: 20401
+ 7: 4556
+ 8: 4556
+ 13: 0
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -5760,6 +5760,12 @@
Args.AddLastArg(CmdArgs, options::OPT_fclang_abi_compat_EQ);
+ // Enable profi in frontend and forward to LLVM invocation
+ if (Args.hasArg(options::OPT_fsample_profile_use_profi)) {
+ CmdArgs.push_back("-mllvm");
+ CmdArgs.push_back("-sample-profile-use-profi");
+ }
+
// Add runtime flag for PS4/PS5 when PGO, coverage, or sanitizers are enabled.
if (RawTriple.isPS() &&
!Args.hasArg(options::OPT_nostdlib, options::OPT_nodefaultlibs)) {
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -1248,6 +1248,9 @@
as cold. Otherwise, treat callsites without profile samples as if
we have no profile}]>,
MarshallingInfoFlag<CodeGenOpts<"ProfileSampleAccurate">>;
+def fsample_profile_use_profi : Flag<["-"], "fsample-profile-use-profi">,
+ Flags<[NoXarchOption, CC1Option]>, Group<f_Group>,
+ HelpText<"Use profi to infer block and edge counts.">;
def fno_profile_sample_accurate : Flag<["-"], "fno-profile-sample-accurate">,
Group<f_Group>, Flags<[NoXarchOption]>;
def fauto_profile : Flag<["-"], "fauto-profile">, Group<f_Group>,
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
