[AMDGPU][SplitModule] Allow non-kernels to be treated as roots

llvm/test/tools/llvm-split/AMDGPU/address-taken-externalize-with-call.ll

@@ -1,4 +1,4 @@
-; RUN: llvm-split -o %t %s -j 3 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-kernel-threshold=0
+; RUN: llvm-split -o %t %s -j 3 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-function-threshold=0
 ; RUN: llvm-dis -o - %t0 | FileCheck --check-prefix=CHECK0 %s
 ; RUN: llvm-dis -o - %t1 | FileCheck --check-prefix=CHECK1 %s
 ; RUN: llvm-dis -o - %t2 | FileCheck --check-prefix=CHECK2 %s

llvm/test/tools/llvm-split/AMDGPU/address-taken-externalize.ll

@@ -1,4 +1,4 @@
-; RUN: llvm-split -o %t %s -j 2 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-kernel-threshold=0
+; RUN: llvm-split -o %t %s -j 2 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-function-threshold=0
 ; RUN: llvm-dis -o - %t0 | FileCheck --check-prefix=CHECK0 %s
 ; RUN: llvm-dis -o - %t1 | FileCheck --check-prefix=CHECK1 %s
 

llvm/test/tools/llvm-split/AMDGPU/debug-non-kernel-root.ll

@@ -0,0 +1,36 @@
+; RUN: llvm-split -o %t %s -j 2 -mtriple amdgcn-amd-amdhsa -debug 2>&1 | FileCheck %s --implicit-check-not="[root]"
+; REQUIRES: asserts
+
+; func_3 is never directly called, it needs to be considered
+; as a root to handle this module correctly.
+
+; CHECK:      [root] kernel_1
+; CHECK-NEXT:   [dependency] func_1
+; CHECK-NEXT:   [dependency] func_2
+; CHECK-NEXT: [root] func_3
+; CHECK-NEXT:   [dependency] func_2
+
+define amdgpu_kernel void @kernel_1() {
+entry:
+  call void @func_1()
+  ret void
+}
+
+define linkonce_odr hidden void @func_1() {
+entry:
+  %call = call i32 @func_2()
+  ret void
+}
+
+define linkonce_odr hidden i32 @func_2() #0 {
+entry:
+  ret i32 0
+}
+
+define void @func_3() {
+entry:
+  %call = call i32 @func_2()
+  ret void
+}
+
+attributes #0 = { noinline optnone }

llvm/test/tools/llvm-split/AMDGPU/large-kernels-merging.ll

@@ -1,9 +1,9 @@
-; RUN: llvm-split -o %t %s -j 3 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-kernel-threshold=1.2 -amdgpu-module-splitting-large-kernel-merge-overlap=0.5
+; RUN: llvm-split -o %t %s -j 3 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-function-threshold=1.2 -amdgpu-module-splitting-large-function-merge-overlap=0.5
 ; RUN: llvm-dis -o - %t0 | FileCheck --check-prefix=CHECK0 %s
 ; RUN: llvm-dis -o - %t1 | FileCheck --check-prefix=CHECK1 %s
 ; RUN: llvm-dis -o - %t2 | FileCheck --check-prefix=CHECK2 %s
 
-; RUN: llvm-split -o %t.nolarge %s -j 3 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-kernel-threshold=0
+; RUN: llvm-split -o %t.nolarge %s -j 3 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-function-threshold=0
 ; RUN: llvm-dis -o - %t.nolarge0 | FileCheck --check-prefix=NOLARGEKERNELS-CHECK0 %s
 ; RUN: llvm-dis -o - %t.nolarge1 | FileCheck --check-prefix=NOLARGEKERNELS-CHECK1 %s
 ; RUN: llvm-dis -o - %t.nolarge2 | FileCheck --check-prefix=NOLARGEKERNELS-CHECK2 %s

llvm/test/tools/llvm-split/AMDGPU/non-kernels-dependencies.ll

@@ -0,0 +1,44 @@
+; RUN: llvm-split -o %t %s -j 3 -mtriple amdgcn-amd-amdhsa
+; RUN: llvm-dis -o - %t0 | FileCheck --check-prefix=CHECK0 --implicit-check-not=DEFINE %s
+; RUN: llvm-dis -o - %t1 | FileCheck --check-prefix=CHECK1 --implicit-check-not=DEFINE %s
+; RUN: llvm-dis -o - %t2 | FileCheck --check-prefix=CHECK2 --implicit-check-not=DEFINE %s
+
+; 3 functions with each their own dependencies should go into 3
+; distinct partitions.
+
+; CHECK0: define void @C
+; CHECK0: define internal void @HelperC
+
+; CHECK1: define void @B
+; CHECK1: define internal void @HelperB
+
+; CHECK2: define void @A
+; CHECK2: define internal void @HelperA
+
+
+define void @A() {
+  call void @HelperA()
+  ret void
+}
+
+define internal void @HelperA() {
+  ret void
+}
+
+define void @B() {
+  call void @HelperB()
+  ret void
+}
+
+define internal void @HelperB() {
+  ret void
+}
+
+define void @C() {
+  call void @HelperC()
+  ret void
+}
+
+define internal void @HelperC() {
+  ret void
+}

llvm/test/tools/llvm-split/AMDGPU/non-kernels-dependency-indirect.ll

@@ -0,0 +1,72 @@
+; RUN: llvm-split -o %t %s -j 3 -mtriple amdgcn-amd-amdhsa
+; RUN: llvm-dis -o - %t0 | FileCheck --check-prefix=CHECK0 --implicit-check-not=DEFINE %s
+; RUN: llvm-dis -o - %t1 | FileCheck --check-prefix=CHECK1 --implicit-check-not=DEFINE %s
+; RUN: llvm-dis -o - %t2 | FileCheck --check-prefix=CHECK2 --implicit-check-not=DEFINE %s
+
+; We have 4 function:
+;   - Each function has an internal helper
+;   - @A and @B's helpers does an indirect call.
+;
+; For non-kernels, indirect calls shouldn't matter, so
+; @CallCandidate doesn't have to be in A/B's partition, unlike
+; in the corresponding tests for kernels where it has to.
+
+; CHECK0: define hidden void @HelperA
+; CHECK0: define hidden void @HelperB
+; CHECK0: define internal void @HelperC
+; CHECK0: define internal void @HelperD
+; CHECK0: define void @A
+; CHECK0: define void @B
+
+; CHECK1: define internal void @HelperD
+; CHECK1: define void @D
+
+; CHECK2: define hidden void @CallCandidate
+; CHECK2: define internal void @HelperC
+; CHECK2: define void @C
+
+@addrthief = global [3 x ptr] [ptr @HelperA, ptr @HelperB, ptr @CallCandidate]
+
+define internal void @HelperA(ptr %call) {
+  call void %call()
+  ret void
+}
+
+define internal void @HelperB(ptr %call) {
+  call void @HelperC()
+  call void %call()
+  call void @HelperD()
+  ret void
+}
+
+define internal void @CallCandidate() {
+  ret void
+}
+
+define internal void @HelperC() {
+  ret void
+}
+
+define internal void @HelperD() {
+  ret void
+}
+
+define void @A(ptr %call) {
+  call void @HelperA(ptr %call)
+  ret void
+}
+
+define void @B(ptr %call) {
+  call void @HelperB(ptr %call)
+  ret void
+}
+
+define void @C() {
+  call void @HelperC()
+  ret void
+}
+
+define void @D() {
+  call void @HelperD()
+  ret void
+}