[SimplifyLibCalls] Transform printf("%s", str) --> puts(str)/noop

Before this change LLVM cannot simplify printf in following cases:

printf("%s", "") --> noop
printf("%s", str"\n") --> puts(str)

From the other hand GCC can perform such transformations for many years:
https://godbolt.org/z/7nnqbedfe

Differential Revision: https://reviews.llvm.org/D100724

diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
index 4a817f9..e9f777f 100644 (file)
--- a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
@@ -2377,14 +2377,24 @@ Value *LibCallSimplifier::optimizePrintFString(CallInst *CI, IRBuilderBase &B) {
   if (FormatStr.size() == 1 || FormatStr == "%%")
     return emitPutChar(B.getInt32(FormatStr[0]), B, TLI);
 
-  // printf("%s", "a") --> putchar('a')
+  // Try to remove call or emit putchar/puts.
   if (FormatStr == "%s" && CI->getNumArgOperands() > 1) {
-    StringRef ChrStr;
-    if (!getConstantStringInfo(CI->getOperand(1), ChrStr))
+    StringRef OperandStr;
+    if (!getConstantStringInfo(CI->getOperand(1), OperandStr))
       return nullptr;
-    if (ChrStr.size() != 1)
-      return nullptr;
-    return emitPutChar(B.getInt32(ChrStr[0]), B, TLI);
+    // printf("%s", "") --> NOP
+    if (OperandStr.empty())
+      return (Value *)CI;
+    // printf("%s", "a") --> putchar('a')
+    if (OperandStr.size() == 1)
+      return emitPutChar(B.getInt32(OperandStr[0]), B, TLI);
+    // printf("%s", str"\n") --> puts(str)
+    if (OperandStr.back() == '\n') {
+      OperandStr = OperandStr.drop_back();
+      Value *GV = B.CreateGlobalString(OperandStr, "str");
+      return emitPutS(GV, B, TLI);
+    }
+    return nullptr;
   }
 
   // printf("foo\n") --> puts("foo")

diff --git a/llvm/test/Transforms/InstCombine/printf-2.ll b/llvm/test/Transforms/InstCombine/printf-2.ll
index 5bbcb14..760fb42 100644 (file)
--- a/llvm/test/Transforms/InstCombine/printf-2.ll
+++ b/llvm/test/Transforms/InstCombine/printf-2.ll
@@ -24,6 +24,8 @@ declare void @printf(i8*, ...)
 ; CHECK: @[[CHARSTR:[a-zA-Z0-9_$"\\.-]+]] = constant [2 x i8] c"a\00"
 ; CHECK: @[[EMPTY:[a-zA-Z0-9_$"\\.-]+]] = constant [1 x i8] zeroinitializer
 ; CHECK: @[[STR:[a-zA-Z0-9_$"\\.-]+]] = private unnamed_addr constant [12 x i8] c"hello world\00", align 1
+; CHECK: @[[STR_1:[a-zA-Z0-9_$"\\.-]+]] = private unnamed_addr constant [12 x i8] c"hello world\00", align 1
+; CHECK: @[[STR_2:[a-zA-Z0-9_$"\\.-]+]] = private unnamed_addr constant [12 x i8] c"hello world\00", align 1
 ;.
 define void @test_simplify1() {
 ; CHECK-LABEL: @test_simplify1(
@@ -67,9 +69,10 @@ define void @test_simplify7() {
   ret void
 }
 
+; printf("%s", "") --> noop
+
 define void @test_simplify8() {
 ; CHECK-LABEL: @test_simplify8(
-; CHECK-NEXT:    call void (i8*, ...) @printf(i8* noundef nonnull dereferenceable(1) getelementptr inbounds ([3 x i8], [3 x i8]* @format_str, i32 0, i32 0), i8* getelementptr inbounds ([1 x i8], [1 x i8]* @empty, i32 0, i32 0))
 ; CHECK-NEXT:    ret void
 ;
   %fmt = getelementptr [3 x i8], [3 x i8]* @format_str, i32 0, i32 0
@@ -78,9 +81,11 @@ define void @test_simplify8() {
   ret void
 }
 
+; printf("%s", str"\n") --> puts(str)
+
 define void @test_simplify9() {
 ; CHECK-LABEL: @test_simplify9(
-; CHECK-NEXT:    call void (i8*, ...) @printf(i8* noundef nonnull dereferenceable(1) getelementptr inbounds ([3 x i8], [3 x i8]* @format_str, i32 0, i32 0), i8* getelementptr inbounds ([13 x i8], [13 x i8]* @hello_world, i32 0, i32 0))
+; CHECK-NEXT:    [[PUTS:%.*]] = call i32 @puts(i8* nonnull dereferenceable(1) getelementptr inbounds ([12 x i8], [12 x i8]* @str.1, i32 0, i32 0))
 ; CHECK-NEXT:    ret void
 ;
   %fmt = getelementptr [3 x i8], [3 x i8]* @format_str, i32 0, i32 0
@@ -89,11 +94,14 @@ define void @test_simplify9() {
   ret void
 }
 
+; printf("%s", "", ...) --> noop
+; printf("%s", "a", ...) --> putchar('a')
+; printf("%s", str"\n", ...) --> puts(str)
+
 define void @test_simplify10() {
 ; CHECK-LABEL: @test_simplify10(
-; CHECK-NEXT:    call void (i8*, ...) @printf(i8* noundef nonnull dereferenceable(1) getelementptr inbounds ([3 x i8], [3 x i8]* @format_str, i32 0, i32 0), i8* getelementptr inbounds ([1 x i8], [1 x i8]* @empty, i32 0, i32 0), i32 42, double 0x40091EB860000000)
 ; CHECK-NEXT:    [[PUTCHAR:%.*]] = call i32 @putchar(i32 97)
-; CHECK-NEXT:    call void (i8*, ...) @printf(i8* noundef nonnull dereferenceable(1) getelementptr inbounds ([3 x i8], [3 x i8]* @format_str, i32 0, i32 0), i8* getelementptr inbounds ([13 x i8], [13 x i8]* @hello_world, i32 0, i32 0), i32 42, double 0x40091EB860000000)
+; CHECK-NEXT:    [[PUTS:%.*]] = call i32 @puts(i8* nonnull dereferenceable(1) getelementptr inbounds ([12 x i8], [12 x i8]* @str.2, i32 0, i32 0))
 ; CHECK-NEXT:    ret void
 ;
   %fmt = getelementptr [3 x i8], [3 x i8]* @format_str, i32 0, i32 0