Added test case for multiple launch

llvm/test/VISC/unitTests/twoLaunch.ll

+; RUN: opt -load LLVMBuildDFG.so -load LLVMDFG2LLVM_X86.so -load LLVMClearDFG.so -dfg2llvm-x86 -clearDFG -o %t.ll -S < %s
+; RUN: llvm-link %t.ll ~/current-src/projects/visc-rt/visc-rt.ll -S -o %t.linked.ll
+; RUN: clang++ -O3 %t.linked.ll -lpthread -lOpenCL -o %t.bin
+; RUN: %t.bin 5
+; ModuleID = '/home/psrivas2/current-test/unitTests/singleNode.ll'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+%rtype = type <{i32}>
+%struct.arg = type <{ %rtype }>
+
+@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1
+
+; Function Attrs: nounwind
+declare i8* @llvm.visc.createNode(i8*) #0
+
+; Function Attrs: nounwind
+declare i8* @llvm.visc.createEdge(i8*, i8*, i1, i32, i32) #0
+
+; Function Attrs: nounwind
+declare i8* @llvm.visc.launch(i8*, i8*) #0
+
+; Function Attrs: nounwind
+declare void @llvm.visc.wait(i8*) #0
+
+; Function Attrs: nounwind
+declare void @llvm.visc.bind.input(i8*, i32, i32)
+
+; Function Attrs: nounwind
+declare void @llvm.visc.bind.output(i8*, i32, i32)
+
+; Function Attrs: nounwind uwtable
+define i32 @main(i32 %argc, i8** nocapture %argv) #1 {
+entry:
+  %in.addr_1 = alloca %struct.arg
+  %in.addr_2= alloca %struct.arg
+  %arrayidx = getelementptr inbounds i8** %argv, i64 1
+  %0 = load i8** %arrayidx, align 8, !tbaa !0
+  %call.i = tail call i64 @strtol(i8* nocapture %0, i8** null, i32 10) #0
+  %conv.i = trunc i64 %call.i to i32
+  %args_1 = bitcast %struct.arg* %in.addr_1 to i8*
+  %args_2 = bitcast %struct.arg* %in.addr_2 to i8*
+  %graphID_1 = call i8* @llvm.visc.launch(i8* bitcast (%rtype ()* @Root_1 to i8*), i8* %args_1)
+  %call1 = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 x i8]* @.str, i64 0, i64 0), i32 %conv.i) #0
+  call void @llvm.visc.wait(i8* %graphID_1)
+  %graphID_2 = call i8* @llvm.visc.launch(i8* bitcast (%rtype ()* @Root_2 to i8*), i8* %args_2)
+  call void @llvm.visc.wait(i8* %graphID_2)
+
+  ret i32 0
+}
+
+define %rtype @foo_1() {
+  %sum = add i32 4, 10 
+  %output = insertvalue %rtype undef, i32 %sum, 0
+  ret %rtype %output
+}
+
+define %rtype @foo_2() {
+  %sum = add i32 4, 10 
+  %output = insertvalue %rtype undef, i32 %sum, 0
+  ret %rtype %output
+}
+
+define %rtype @Root_1() {
+  %node = call i8* @llvm.visc.createNode(i8* bitcast (%rtype ()* @foo_1 to i8*))
+  call void @llvm.visc.bind.output(i8* %node, i32 0, i32 0)
+  ret %rtype zeroinitializer
+}
+
+define %rtype @Root_2() {
+  %node = call i8* @llvm.visc.createNode(i8* bitcast (%rtype ()* @foo_2 to i8*))
+  call void @llvm.visc.bind.output(i8* %node, i32 0, i32 0)
+  ret %rtype zeroinitializer
+}
+
+; Function Attrs: nounwind
+declare i32 @printf(i8* nocapture, ...) #2
+
+; Function Attrs: nounwind
+declare i64 @strtol(i8*, i8** nocapture, i32) #2
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #2 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!0 = metadata !{metadata !"any pointer", metadata !1}
+!1 = metadata !{metadata !"omnipotent char", metadata !2}
+!2 = metadata !{metadata !"Simple C/C++ TBAA"}