Related
I have the following code:
#.str_specifier = constant [4 x i8] c"%s\0A\00"
#.int_specifier = constant [4 x i8] c"%d\0A\00"
#.string_var1 = constant [2 x i8] c"f\00"
#.string_var2 = constant [6 x i8] c"Error\00"
; >>> Start Program
declare i32 #printf(i8*, ...)
declare void #exit(i32)
define void #print(i8*) {
call i32 (i8*, ...) #printf(i8* getelementptr ([4 x i8], [4 x i8]* #.str_specifier, i32 0, i32 0), i8* %0)
ret void
}
define void #printi(i32) {
call i32 (i8*, ...) #printf(i8* getelementptr ([4 x i8], [4 x i8]* #.int_specifier, i32 0, i32 0), i32 %0)
ret void
}
declare i8* #malloc(i32)
declare void #free(i8*)
declare void #llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i1)
define void #main()
{ ; >>> Adding function scope
%funcArgs1 = alloca [50 x i32]
; >>> Adding function arguments allocation
; >>> Function body of main
call void #print(i8* getelementptr ([2 x i8], [2 x i8]* #.string_var1, i32 0, i32 0))
%register1 = call i8* #malloc(i32 48)
%register2 = bitcast i8* %register1 to i32*
%register3 = getelementptr inbounds [50 x i32], [50 x i32]* %funcArgs1, i32 0, i32 0
%register4 = ptrtoint i32* %register2 to i32
store i32 %register4, i32* %register3
%register5 = getelementptr inbounds i32, i32* %register2, i32 0
%register6 = add i32 0, 12
store i32 %register6, i32* %register5
%register7 = getelementptr inbounds i32, i32* %register2, i32 1
%register8 = add i32 0, 2
store i32 %register8, i32* %register7
%register9 = getelementptr inbounds i32, i32* %register2, i32 2
store i32 0, i32* %register9
%register10 = getelementptr inbounds i32, i32* %register2, i32 3
store i32 0, i32* %register10
%register11 = getelementptr inbounds i32, i32* %register2, i32 4
store i32 0, i32* %register11
%register12 = getelementptr inbounds i32, i32* %register2, i32 5
store i32 0, i32* %register12
%register13 = getelementptr inbounds i32, i32* %register2, i32 6
store i32 0, i32* %register13
%register14 = getelementptr inbounds i32, i32* %register2, i32 7
store i32 0, i32* %register14
%register15 = getelementptr inbounds i32, i32* %register2, i32 8
store i32 0, i32* %register15
%register16 = getelementptr inbounds i32, i32* %register2, i32 9
store i32 0, i32* %register16
%register17 = getelementptr inbounds i32, i32* %register2, i32 10
store i32 0, i32* %register17
%register18 = getelementptr inbounds i32, i32* %register2, i32 11
store i32 0, i32* %register18
%register19 = load i32, i32* %register3 ; Get variable x
%register20 = add i32 0, 2
%register21 = inttoptr i32 %register20 to i32*
%register22 = getelementptr inbounds i32, i32* %register21, i32 1
%register23 = load i32, i32* %register22
%register24 = getelementptr inbounds i32, i32* %register21, i32 0
%register25 = load i32, i32* %register24
%register26 = add i32 %register23, %register25
%register27 = sub i32 %register26, 4
%register28 = icmp sgt i32 %register20, %register27
br i1 %register28, label %label1, label %label_cont1
label_cont1:
br label %label2
label1:
call void #print(i8* getelementptr ([6 x i8], [6 x i8]* #.string_var2, i32 0, i32 0))
call void #exit(i32 1)
%register200 = add i32 0, 2
br label %label2
label2:
ret void
} ; >>> Closing function scope
For some reason when I run it, it fails with Segmentation fault (core dumped) without printing an understandable error. The strange thing is if I comment the commands in label1 and keep it:
;call void #print(i8* getelementptr ([6 x i8], [6 x i8]* #.string_var2, i32 0, i32 0))
;call void #exit(i32 1)
;%register200 = add i32 0, 2
br label %label2
It does not result with Segmentation fault. If I comment out at least one of those commands (for example print or the sum), it will fail. Why does it happen?
EDIT: I think I'm getting the same result here. (Here with comments)
I understand that "Segmentation fault" means that I tried to access memory that
I do not have access to. but why can't I even create an new register with some value?
EDIT2: It looks like br i1 %register28, label %label1, label %label_cont1 is the real reason.
Edit3: The actual full code I'm trying to figure can be found here. The problem is that changing it to alloca i32 will result with Error (instead of printing 1). It also contains the C code I'm trying to copy to LLVM.
The segfault originates from this line
%register21 = inttoptr i32 %register20 to i32*
After the cast, register21 supposedly points to some memory location. But what memory location ?? It's value is a non existent address that wasn't gotten through a an alloca instr or malloc call.
Therefore all the other registers that try to dereference this pointer get disappointed.
I've altered the inttptr line
I have been trying to create a function using the module pass in LLVM. What I am trying to do is create a variable argument function and then add the logic to manipulate the variable arguments.
For example:
/\*can do this\*/
int foo(int a, ...)
{
double var1;
//can't figure out how to add any of this using llvm
va_list ap;
va_start(ap, a);
va_arg(var1,double);
va_end(ap);
}
Creating the function type is easy because I just set the vararg boolean to true. What do I do after that?
I always use clang to check what it needs to convert for c/c++ lang.
Use llvm instruction va_arg and intinsics llvm.va_start, llvm.va_end, llvm.va_copy to use llvm variable argument support.
you also need target-specific value type “va_list” for functions that operates on arguments that use this.
; This struct is different for every platform. For most platforms,
; it is merely an i8*.
%struct.va_list = type { i8* }
; For Unix x86_64 platforms, va_list is the following struct:
; %struct.va_list = type { i32, i32, i8*, i8* }
ref http://llvm.org/docs/LangRef.html#variable-argument-handling-intrinsics
for your listed code,
; ModuleID = 'test.c'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
%struct.__va_list_tag = type { i32, i32, i8*, i8* }
; Function Attrs: nounwind uwtable
define i32 #foo(i32 %a, ...) #0 {
%1 = alloca i32, align 4
%2 = alloca i32, align 4
%var1 = alloca double, align 8
%ap = alloca [1 x %struct.__va_list_tag], align 16
store i32 %a, i32* %2, align 4
%3 = getelementptr inbounds [1 x %struct.__va_list_tag]* %ap, i32 0, i32 0
%4 = bitcast %struct.__va_list_tag* %3 to i8*
call void #llvm.va_start(i8* %4)
%5 = getelementptr inbounds [1 x %struct.__va_list_tag]* %ap, i32 0, i32 0
%6 = getelementptr inbounds %struct.__va_list_tag* %5, i32 0, i32 1
%7 = load i32* %6
%8 = icmp ule i32 %7, 160
br i1 %8, label %9, label %15
; <label>:9 ; preds = %0
%10 = getelementptr inbounds %struct.__va_list_tag* %5, i32 0, i32 3
%11 = load i8** %10
%12 = getelementptr i8* %11, i32 %7
%13 = bitcast i8* %12 to double*
%14 = add i32 %7, 16
store i32 %14, i32* %6
br label %20
; <label>:15 ; preds = %0
%16 = getelementptr inbounds %struct.__va_list_tag* %5, i32 0, i32 2
%17 = load i8** %16
%18 = bitcast i8* %17 to double*
%19 = getelementptr i8* %17, i32 8
store i8* %19, i8** %16
br label %20
; <label>:20 ; preds = %15, %9
%21 = phi double* [ %13, %9 ], [ %18, %15 ]
%22 = load double* %21
%23 = getelementptr inbounds [1 x %struct.__va_list_tag]* %ap, i32 0, i32 0
%24 = bitcast %struct.__va_list_tag* %23 to i8*
call void #llvm.va_end(i8* %24)
%25 = load i32* %1
ret i32 %25
}
; Function Attrs: nounwind
declare void #llvm.va_start(i8*) #1
; Function Attrs: nounwind
declare void #llvm.va_end(i8*) #1
; Function Attrs: nounwind uwtable
define i32 #main() #0 {
ret i32 0
}
When building a project with LLVM, some function calls will be replaced by intrinsic functions. Is the replacement completed by the front-end (e.g. clang) or the LLVM back-end?
Discussions through the Internet indicate that the intrinsic functions replacement is related to optimization options. So does it mean if there is no optimization option, then no intrinsic replacement will happen? Or in fact, there are some default intrinsic functions replacement that cannot be disabled?
If there is any method to disable all the intrinsic functions, how should I do that?
It depends. Intrinsics written in code are emitted through the front-end directly. Intrinsics like llvm.memset are introduced to the code during optimization at IR level (eigther the front-end nor the back-end perform this optimizations).
Here is a (quite stupid) example:
int main(int argc, char** argv)
{
int a[8];
for (int i = 0; i != 8; ++i)
a[i] = 0;
for (int i = 7; i >= 0; --i)
a[i] = a[i+1] + argc;
return a[0];
}
Compiled with clang 3.5 (clang -S -emit-llvm) you will get the following IR without any intrinsics:
; Function Attrs: nounwind uwtable
define i32 #main(i32 %argc, i8** %argv) #0 {
%1 = alloca i32, align 4
%2 = alloca i32, align 4
%3 = alloca i8**, align 8
%a = alloca [8 x i32], align 16
%i = alloca i32, align 4
%i1 = alloca i32, align 4
store i32 0, i32* %1
store i32 %argc, i32* %2, align 4
store i8** %argv, i8*** %3, align 8
store i32 0, i32* %i, align 4
br label %4
; <label>:4 ; preds = %11, %0
%5 = load i32* %i, align 4
%6 = icmp ne i32 %5, 8
br i1 %6, label %7, label %14
; <label>:7 ; preds = %4
%8 = load i32* %i, align 4
%9 = sext i32 %8 to i64
%10 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 %9
store i32 0, i32* %10, align 4
br label %11
; <label>:11 ; preds = %7
%12 = load i32* %i, align 4
%13 = add nsw i32 %12, 1
store i32 %13, i32* %i, align 4
br label %4
; <label>:14 ; preds = %4
store i32 7, i32* %i1, align 4
br label %15
; <label>:15 ; preds = %29, %14
%16 = load i32* %i1, align 4
%17 = icmp sge i32 %16, 0
br i1 %17, label %18, label %32
; <label>:18 ; preds = %15
%19 = load i32* %i1, align 4
%20 = add nsw i32 %19, 1
%21 = sext i32 %20 to i64
%22 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 %21
%23 = load i32* %22, align 4
%24 = load i32* %2, align 4
%25 = add nsw i32 %23, %24
%26 = load i32* %i1, align 4
%27 = sext i32 %26 to i64
%28 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 %27
store i32 %25, i32* %28, align 4
br label %29
; <label>:29 ; preds = %18
%30 = load i32* %i1, align 4
%31 = add nsw i32 %30, -1
store i32 %31, i32* %i1, align 4
br label %15
; <label>:32 ; preds = %15
%33 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 0
%34 = load i32* %33, align 4
ret i32 %34
}
Compiled again with clang -emit-llvm -O1 you will see this:
; Function Attrs: nounwind readnone uwtable
define i32 #main(i32 %argc, i8** nocapture readnone %argv) #0 {
.preheader:
%a = alloca [8 x i32], align 16
%a6 = bitcast [8 x i32]* %a to i8*
call void #llvm.memset.p0i8.i64(i8* %a6, i8 0, i64 32, i32 4, i1 false)
br label %0
; <label>:0 ; preds = %.preheader, %0
%indvars.iv = phi i64 [ 7, %.preheader ], [ %indvars.iv.next, %0 ]
%1 = add nsw i64 %indvars.iv, 1
%2 = getelementptr inbounds [8 x i32]* %a, i64 0, i64 %1
%3 = load i32* %2, align 4, !tbaa !1
%4 = add nsw i32 %3, %argc
%5 = getelementptr inbounds [8 x i32]* %a, i64 0, i64 %indvars.iv
store i32 %4, i32* %5, align 4, !tbaa !1
%indvars.iv.next = add nsw i64 %indvars.iv, -1
%6 = trunc i64 %indvars.iv to i32
%7 = icmp sgt i32 %6, 0
br i1 %7, label %0, label %8
; <label>:8 ; preds = %0
%9 = getelementptr inbounds [8 x i32]* %a, i64 0, i64 0
%10 = load i32* %9, align 16, !tbaa !1
ret i32 %10
}
The initialization loop was replaced by the llvm.memset intrinsic. The back-end is free to handle the intrinsic as it want's but commonly llvm.memset is lowered to a libc library call.
To answer your first question: Yes, if you don't optimize your code, then you will not get intrinsics in your IR.
To prevent intrinsics being introduced in your code all you have to do is find the optimization pass on your IR and don't run it. Here is a related question how to find out what passes are done on the IR: Where to find the optimization sequence for clang -OX?
for -O1 we get:
prune-eh -inline-cost -always-inline -functionattrs -sroa -domtree
-early-cse -lazy-value-info -jump-threading -correlated-propagation -simplifycfg -instcombine -tailcallelim -simplifycfg -reassociate -domtree -loops -loop-simplify -lcssa -loop-rotate -licm -loop-unswitch -instcombine -scalar-evolution -lcssa -indvars -loop-idiom -loop-deletion -loop-unroll -memdep -memcpyopt -sccp -instcombine -lazy-value-info -jump-threading -correlated-propagation -domtree -memdep -dse -adce -simplifycfg -instcombine -barrier -domtree -loops -loop-simplify -lcssa -branch-prob -block-freq -scalar-evolution -loop-vectorize -instcombine -simplifycfg -strip-dead-prototypes -verify
A wild guess: instcombine is introducing the llvm.memset. I run the passes without instcombine and opt on the unoptimized IR and get this:
; Function Attrs: nounwind readnone uwtable
define i32 #main(i32 %argc, i8** %argv) #0 {
%a = alloca [8 x i32], align 16
%1 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 8
%2 = load i32* %1, align 4
%3 = add nsw i32 %2, %argc
%4 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 7
store i32 %3, i32* %4, align 4
%5 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 7
%6 = load i32* %5, align 4
%7 = add nsw i32 %6, %argc
%8 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 6
store i32 %7, i32* %8, align 4
%9 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 6
%10 = load i32* %9, align 4
%11 = add nsw i32 %10, %argc
%12 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 5
store i32 %11, i32* %12, align 4
%13 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 5
%14 = load i32* %13, align 4
%15 = add nsw i32 %14, %argc
%16 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 4
store i32 %15, i32* %16, align 4
%17 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 4
%18 = load i32* %17, align 4
%19 = add nsw i32 %18, %argc
%20 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 3
store i32 %19, i32* %20, align 4
%21 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 3
%22 = load i32* %21, align 4
%23 = add nsw i32 %22, %argc
%24 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 2
store i32 %23, i32* %24, align 4
%25 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 2
%26 = load i32* %25, align 4
%27 = add nsw i32 %26, %argc
%28 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 1
store i32 %27, i32* %28, align 4
%29 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 1
%30 = load i32* %29, align 4
%31 = add nsw i32 %30, %argc
%32 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 0
store i32 %31, i32* %32, align 4
%33 = getelementptr inbounds [8 x i32]* %a, i32 0, i64 0
%34 = load i32* %33, align 4
ret i32 %34
}
No instructions. So to prevent (at least the memset) intrinsics in your code don't run instcombine on your IR. However, instcombine is a mighty opt pass that realy shortens the code.
Now you have two options:
don't use opt passes that introduce intrinsics
write your own llvm
opt pass that transforms intrinsics back to whatever they could be
replaced with an run it after optimization and before the back-end
starts working
I hope this helps you somehow. Cheers!
I have the following rust code.
$ cat hello.rs
fn main() {
println!("Hello world!");
}
$ rustc hello.rs; ./hello
Hello world!
And I'm producing llvm byte code with the --emit=ir option.
$ rustc --emit=ir hello.rs
$ cat hello.ll
; ModuleID = 'hello.rs'
target datalayout = "e-i64:64-f80:128-n8:16:32:64"
target triple = "x86_64-apple-darwin"
%str_slice = type { i8*, i64 }
%"struct.core::fmt::Argument<[]>[#3]" = type { %"enum.core::result::Result<[(), core::fmt::FormatError]>[#3]" (%"enum.core::fmt::Void<[]>[#3]"*, %"struct.core::fmt::Formatter<[]>[#3]"*)*, %"enum.core::fmt::Void<[]>[#3]"* }
%"enum.core::result::Result<[(), core::fmt::FormatError]>[#3]" = type { i8, [0 x i8], [1 x i8] }
%"struct.core::fmt::Formatter<[]>[#3]" = type { i64, i32, i8, %"enum.core::option::Option<[uint]>[#3]", %"enum.core::option::Option<[uint]>[#3]", { void (i8*)**, i8* }, %"struct.core::slice::Items<[core::fmt::Argument]>[#3]", { %"struct.core::fmt::Argument<[]>[#3]"*, i64 } }
%"enum.core::option::Option<[uint]>[#3]" = type { i8, [7 x i8], [1 x i64] }
%"struct.core::slice::Items<[core::fmt::Argument]>[#3]" = type { %"struct.core::fmt::Argument<[]>[#3]"*, %"struct.core::fmt::Argument<[]>[#3]"*, %"struct.core::kinds::marker::ContravariantLifetime<[]>[#3]" }
%"struct.core::kinds::marker::ContravariantLifetime<[]>[#3]" = type {}
%"enum.core::fmt::Void<[]>[#3]" = type {}
%"struct.core::fmt::Arguments<[]>[#3]" = type { { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }, { %"struct.core::fmt::Argument<[]>[#3]"*, i64 } }
%"enum.core::fmt::rt::Piece<[]>[#3]" = type { i8, [7 x i8], [8 x i64] }
#str1364 = internal constant [12 x i8] c"Hello world!"
#_ZN4main15__STATIC_FMTSTR20h3b67a4ad8efbb398oaaE = internal unnamed_addr constant { { i8, %str_slice, [48 x i8] } } { { i8, %str_slice, [48 x i8] } { i8 0, %str_slice { i8* getelementptr inbounds ([12 x i8]* #str1364, i32 0, i32 0), i64 12 }, [48 x i8] undef } }
; Function Attrs: uwtable
define internal void #_ZN4main20he3565cca0bc2f101eaaE() unnamed_addr #0 {
entry-block:
%match = alloca {}
%__args_vec = alloca { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }
%0 = alloca %"struct.core::fmt::Argument<[]>[#3]", i64 0
%__args = alloca %"struct.core::fmt::Arguments<[]>[#3]"
%__adjust = alloca { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }
%__adjust1 = alloca { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }
br label %case_body
case_body: ; preds = %entry-block
%1 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__args_vec, i32 0, i32 0
store %"struct.core::fmt::Argument<[]>[#3]"* %0, %"struct.core::fmt::Argument<[]>[#3]"** %1
%2 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__args_vec, i32 0, i32 1
store i64 0, i64* %2
%3 = getelementptr inbounds { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }* %__adjust, i32 0, i32 0
store %"enum.core::fmt::rt::Piece<[]>[#3]"* getelementptr inbounds ([1 x %"enum.core::fmt::rt::Piece<[]>[#3]"]* bitcast ({ { i8, %str_slice, [48 x i8] } }* #_ZN4main15__STATIC_FMTSTR20h3b67a4ad8efbb398oaaE to [1 x %"enum.core::fmt::rt::Piece<[]>[#3]"]*), i32 0, i32 0), %"enum.core::fmt::rt::Piece<[]>[#3]"** %3
%4 = getelementptr inbounds { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }* %__adjust, i32 0, i32 1
store i64 1, i64* %4
%5 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__args_vec, i32 0, i32 0
%6 = load %"struct.core::fmt::Argument<[]>[#3]"** %5
%7 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__args_vec, i32 0, i32 1
%8 = load i64* %7
%9 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__adjust1, i32 0, i32 0
store %"struct.core::fmt::Argument<[]>[#3]"* %6, %"struct.core::fmt::Argument<[]>[#3]"** %9
%10 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__adjust1, i32 0, i32 1
store i64 %8, i64* %10
call void #"_ZN3fmt22Arguments$LT$$x27a$GT$3new20h30af698883d0f4c86aaE"(%"struct.core::fmt::Arguments<[]>[#3]"* noalias nocapture sret dereferenceable(32) %__args, { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }* noalias nocapture dereferenceable(16) %__adjust, { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* noalias nocapture dereferenceable(16) %__adjust1)
call void #_ZN2io5stdio12println_args20hecac3fc58fb73442EvmE(%"struct.core::fmt::Arguments<[]>[#3]"* noalias nocapture dereferenceable(32) %__args)
br label %join
join: ; preds = %case_body
ret void
}
define i64 #main(i64, i8**) unnamed_addr #1 {
top:
%2 = call i64 #_ZN10lang_start20h7823875e69d425d0BueE(i8* bitcast (void ()* #_ZN4main20he3565cca0bc2f101eaaE to i8*), i64 %0, i8** %1)
ret i64 %2
}
declare i64 #_ZN10lang_start20h7823875e69d425d0BueE(i8*, i64, i8**) unnamed_addr #1
; Function Attrs: inlinehint uwtable
define internal void #"_ZN3fmt22Arguments$LT$$x27a$GT$3new20h30af698883d0f4c86aaE"(%"struct.core::fmt::Arguments<[]>[#3]"* noalias nocapture sret dereferenceable(32), { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }* noalias nocapture dereferenceable(16), { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* noalias nocapture dereferenceable(16)) unnamed_addr #2 {
entry-block:
%__adjust = alloca { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }
%3 = getelementptr inbounds %"struct.core::fmt::Arguments<[]>[#3]"* %0, i32 0, i32 0
%4 = bitcast { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }* %1 to i8*
%5 = bitcast { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }* %3 to i8*
call void #llvm.memcpy.p0i8.p0i8.i64(i8* %5, i8* %4, i64 16, i32 8, i1 false)
%6 = getelementptr inbounds %"struct.core::fmt::Arguments<[]>[#3]"* %0, i32 0, i32 1
%7 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %2, i32 0, i32 0
%8 = load %"struct.core::fmt::Argument<[]>[#3]"** %7
%9 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %2, i32 0, i32 1
%10 = load i64* %9
%11 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__adjust, i32 0, i32 0
store %"struct.core::fmt::Argument<[]>[#3]"* %8, %"struct.core::fmt::Argument<[]>[#3]"** %11
%12 = getelementptr inbounds { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__adjust, i32 0, i32 1
store i64 %10, i64* %12
%13 = bitcast { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %__adjust to i8*
%14 = bitcast { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* %6 to i8*
call void #llvm.memcpy.p0i8.p0i8.i64(i8* %14, i8* %13, i64 16, i32 8, i1 false)
ret void
}
; Function Attrs: nounwind
declare void #llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) unnamed_addr #3
declare void #_ZN2io5stdio12println_args20hecac3fc58fb73442EvmE(%"struct.core::fmt::Arguments<[]>[#3]"* noalias nocapture dereferenceable(32)) unnamed_addr #1
attributes #0 = { uwtable "split-stack" }
attributes #1 = { "split-stack" }
attributes #2 = { inlinehint uwtable "split-stack" }
attributes #3 = { nounwind "split-stack" }
However, lli won't accept this bytecode.
$ lli hello.ll
lli: hello.ll:47:138: error: expected value token
call void #"_ZN3fmt22Arguments$LT$$x27a$GT$3new20h30af698883d0f4c86aaE"(%"struct.core::fmt::Arguments<[]>[#3]"* noalias nocapture sret dereferenceable(32) %__args, { %"enum.core::fmt::rt::Piece<[]>[#3]"*, i64 }* noalias nocapture dereferenceable(16) %__adjust, { %"struct.core::fmt::Argument<[]>[#3]"*, i64 }* noalias nocapture dereferenceable(16) %__adjust1)
^
Any ideas why?
The dereferenceable attribute was added to LLVM just last month (July 2014). I'm assuming the rustc you are using is based on brand new LLVM code while your lli is slightly older. To fix this, update your code and rebuild.
The dereferenceable attribute was added in a commit one month before the OP, so if you are using a released LLVM package, you may not be using a recent enough package.
Try using an LLVM package built from top of trunk.
I have a c code that calculates the factorial of an int "factorial.c". I compile it to llvm readable code "factorial.ll" and I modify in the compiled llvm code.
The objective is to execute the modified llvm code and to see its output, How can I do this?
It will depend on how your outputted LLVM is assembled and what libraries it links against, but for example executing the following factorial.ll with the shell command lli
$ lli factorial.ll
Factorial of 10 = 3628800
Will execute the main function with the JIT and use the standard printf to output the result to stdout.
#.str = private unnamed_addr constant [22 x i8] c"Factorial of %d = %d\0A\00", align 1
declare i32 #printf(i8*, ...)
define i32 #factorial(i32 %n) nounwind uwtable {
entry:
%n.addr = alloca i32, align 4
store i32 %n, i32* %n.addr, align 4
%0 = load i32* %n.addr, align 4
%cmp = icmp sle i32 %0, 1
br i1 %cmp, label %cond.true, label %cond.false
cond.true: ; preds = %entry
br label %cond.end
cond.false: ; preds = %entry
%1 = load i32* %n.addr, align 4
%2 = load i32* %n.addr, align 4
%sub = sub nsw i32 %2, 1
%call = call i32 #factorial(i32 %sub)
%mul = mul nsw i32 %1, %call
br label %cond.end
cond.end: ; preds = %cond.false, %cond.true
%cond = phi i32 [ 1, %cond.true ], [ %mul, %cond.false ]
ret i32 %cond
}
define i32 #main(i32 %argc, i8** %argv) nounwind uwtable {
entry:
%retval = alloca i32, align 4
%argc.addr = alloca i32, align 4
%argv.addr = alloca i8**, align 8
store i32 0, i32* %retval
store i32 %argc, i32* %argc.addr, align 4
store i8** %argv, i8*** %argv.addr, align 8
%call = call i32 #factorial(i32 10)
%call1 = call i32 (i8*, ...)* #printf(i8* getelementptr inbounds ([22 x i8]* #.str, i32 0, i32 0), i32 10, i32 %call)
ret i32 0
}