[SYCL] Implement per-aspect device code split

llvm/test/tools/sycl-post-link/device-code-split/per-aspect-split-1.ll

@@ -0,0 +1,133 @@
+; This test emulates two translation units with 3 kernels:
+; TU0_kernel0 - 1st translation unit, no aspects used
+; TU0_kernel1 - 1st translation unit, aspect 1 is used
+; TU1_kernel2 - 2nd translation unit, no aspects used
+
+; The test is intended to check that sycl-post-link correctly separates kernels
+; that use aspects from kernels which doesn't use aspects regardless of device
+; code split mode
+
+; RUN: sycl-post-link -split=auto -symbols -S %s -o %t.table
+; RUN: FileCheck %s -input-file=%t_0.ll --check-prefixes CHECK-M0-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_1.ll --check-prefixes CHECK-M1-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_2.ll --check-prefixes CHECK-M2-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_0.sym --check-prefixes CHECK-M0-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_1.sym --check-prefixes CHECK-M1-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_2.sym --check-prefixes CHECK-M2-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+
+; RUN: sycl-post-link -split=source -symbols -S %s -o %t.table
+; RUN: FileCheck %s -input-file=%t_0.ll --check-prefixes CHECK-M0-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_1.ll --check-prefixes CHECK-M1-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_2.ll --check-prefixes CHECK-M2-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_0.sym --check-prefixes CHECK-M0-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_1.sym --check-prefixes CHECK-M1-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_2.sym --check-prefixes CHECK-M2-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+
+; RUN: sycl-post-link -split=kernel -symbols -S %s -o %t.table
+; RUN: FileCheck %s -input-file=%t_0.ll --check-prefixes CHECK-M0-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_1.ll --check-prefixes CHECK-M1-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_2.ll --check-prefixes CHECK-M2-IR \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_0.sym --check-prefixes CHECK-M0-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_1.sym --check-prefixes CHECK-M1-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+; RUN: FileCheck %s -input-file=%t_2.sym --check-prefixes CHECK-M2-SYMS \
+; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1
+
+; Regardless of device code split mode, each kernel should go into a separate
+; device image
+
+; CHECK-M2-IR: define {{.*}} @TU0_kernel0
+; CHECK-M2-SYMS: TU0_kernel0
+
+; CHECK-M1-IR: define {{.*}} @TU0_kernel1
+; CHECK-M1-SYMS: TU0_kernel1
+
+; CHECK-M0-IR: define {{.*}} @TU1_kernel2
+; CHECK-M0-SYMS: TU1_kernel2
+
+target datalayout = "e-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024"
+target triple = "spir64-unknown-linux"
+
+; FIXME: device globals should also be properly distributed across device images
+; if they are of optional type
+@_ZL2GV = internal addrspace(1) constant [1 x i32] [i32 42], align 4
+
+define dso_local spir_kernel void @TU0_kernel0() #0 {
+entry:
+  call spir_func void @foo()
+  ret void
+}
+
+define dso_local spir_func void @foo() {
+entry:
+  %a = alloca i32, align 4
+  %call = call spir_func i32 @bar(i32 1)
+  %add = add nsw i32 2, %call
+  store i32 %add, i32* %a, align 4
+  ret void
+}
+
+; Function Attrs: nounwind
+define linkonce_odr dso_local spir_func i32 @bar(i32 %arg) {
+entry:
+  %arg.addr = alloca i32, align 4
+  store i32 %arg, i32* %arg.addr, align 4
+  %0 = load i32, i32* %arg.addr, align 4
+  ret i32 %0
+}
+
+define dso_local spir_kernel void @TU0_kernel1() #0 !sycl_used_aspects !2 {
+entry:
+  call spir_func void @foo1()
+  ret void
+}
+
+; Function Attrs: nounwind
+define dso_local spir_func void @foo1() {
+entry:
+  %a = alloca i32, align 4
+  store i32 2, i32* %a, align 4
+  ret void
+}
+
+define dso_local spir_kernel void @TU1_kernel2() #1 {
+entry:
+  call spir_func void @foo2()
+  ret void
+}
+
+; Function Attrs: nounwind
+define dso_local spir_func void @foo2() {
+entry:
+  %a = alloca i32, align 4
+  %0 = load i32, i32 addrspace(4)* getelementptr inbounds ([1 x i32], [1 x i32] addrspace(4)* addrspacecast ([1 x i32] addrspace(1)* @_ZL2GV to [1 x i32] addrspace(4)*), i64 0, i64 0), align 4
+  %add = add nsw i32 4, %0
+  store i32 %add, i32* %a, align 4
+  ret void
+}
+
+attributes #0 = { "sycl-module-id"="TU1.cpp" }
+attributes #1 = { "sycl-module-id"="TU2.cpp" }
+
+!opencl.spir.version = !{!0, !0}
+!spirv.Source = !{!1, !1}
+
+!0 = !{i32 1, i32 2}
+!1 = !{i32 4, i32 100000}
+!2 = !{i32 1}

llvm/test/tools/sycl-post-link/device-code-split/per-aspect-split-2.ll

@@ -0,0 +1,59 @@
+; The test is intended to check that sycl-post-link correctly groups kernels
+; by unique sets of aspects used in them
+
+; RUN: sycl-post-link -split=auto -symbols -S %s -o %t.table
+; RUN: FileCheck %s -input-file=%t.table --check-prefix CHECK-TABLE
+;
+; RUN: FileCheck %s -input-file=%t_0.sym --check-prefix CHECK-M0-SYMS \
+; RUN:     --implicit-check-not kernel0 --implicit-check-not kernel1 \
+; RUN:     --implicit-check-not kernel2
+;
+; RUN: FileCheck %s -input-file=%t_1.sym --check-prefix CHECK-M1-SYMS \
+; RUN:     --implicit-check-not kernel3 --implicit-check-not kernel1 \
+; RUN:     --implicit-check-not kernel2
+;
+; RUN: FileCheck %s -input-file=%t_2.sym --check-prefix CHECK-M2-SYMS \
+; RUN:     --implicit-check-not kernel0 --implicit-check-not kernel3
+
+; CHECK-TABLE: Code
+; CHECK-TABLE-NEXT: _0.sym
+; CHECK-TABLE-NEXT: _1.sym
+; CHECK-TABLE-NEXT: _2.sym
+; CHECK-TABLE-EMPTY:
+
+; CHECK-M0-SYMS: kernel3
+
+; CHECK-M1-SYMS: kernel0
+
+; CHECK-M2-SYMS: kernel1
+; CHECK-M2-SYMS: kernel2
+
+target datalayout = "e-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024"
+target triple = "spir64-unknown-linux"
+
+define dso_local spir_kernel void @kernel0() #0 !sycl_used_aspects !1 {
+entry:
+  ret void
+}
+
+define dso_local spir_kernel void @kernel1() #0 !sycl_used_aspects !2 {
+entry:
+  ret void
+}
+
+define dso_local spir_kernel void @kernel2() #0 !sycl_used_aspects !3 {
+entry:
+  ret void
+}
+
+define dso_local spir_kernel void @kernel3() #0 !sycl_used_aspects !4 {
+entry:
+  ret void
+}
+
+attributes #0 = { "sycl-module-id"="TU1.cpp" }
+
+!1 = !{i32 1}
+!2 = !{i32 1, i32 2}
+!3 = !{i32 2, i32 1}
+!4 = !{i32 2, i32 3, i32 4}

llvm/test/tools/sycl-post-link/device-code-split/per-aspect-split-3.ll

@@ -0,0 +1,94 @@
+; This test is intended to check that per-aspect device code split works as
+; expected with SYCL_EXTERNAL functions
+
+; RUN: sycl-post-link -split=auto -symbols -S %s -o %t.table
+; RUN: FileCheck %s -input-file=%t.table --check-prefix CHECK-TABLE
+;
+; RUN: FileCheck %s -input-file=%t_0.sym --check-prefix CHECK-M0-SYMS \
+; RUN:     --implicit-check-not foo --implicit-check-not kernel1
+;
+; RUN: FileCheck %s -input-file=%t_1.sym --check-prefix CHECK-M1-SYMS \
+; RUN:     --implicit-check-not foo --implicit-check-not kernel0
+;
+; RUN: FileCheck %s -input-file=%t_2.sym --check-prefix CHECK-M2-SYMS \
+; RUN:     --implicit-check-not kernel0 --implicit-check-not foo \
+; RUN:     --implicit-check-not bar
+;
+; RUN: FileCheck %s -input-file=%t_2.ll --check-prefix CHECK-M2-IR \
+; RUN:     --implicit-check-not kernel0 --implicit-check-not bar
+
+; We expect to see 3 modules generated:
+;
+; CHECK-TABLE: Code
+; CHECK-TABLE-NEXT: _0.sym
+; CHECK-TABLE-NEXT: _1.sym
+; CHECK-TABLE-NEXT: _2.sym
+; CHECK-TABLE-EMPTY:
+
+; sycl-post-link aims to achieve two goals while doing splitting:
+;   - each kernel must be self-contained, i.e. all functions called from a
+;     kernel must reside in the same device image
+;   - each entry point should be assigned to a correct device image in
+;     accordance with selected device code split mode
+;
+; In this test @bar and @foo are SYCL_EXTERNAL functions and they are treated
+; as entry points.
+;
+; @bar uses the same list of aspects as @kernel0 which calls it and therefore
+; they can be put into the same device image. There also goes @baz, because of
+; the same list of used aspects.
+;
+; CHECK-M0-SYMS: bar
+; CHECK-M0-SYMS: baz
+; CHECK-M0-SYMS: kernel0
+;
+; List of aspects used by @foo is different from the one attached to @kernel1
+; which calls @foo (for example, @kernel1 uses an extra optional feature besides
+; ones used in @foo). As a result, @foo should be both included into the same
+; device image as @kernel1 to make it self contained, but at the same time it
+; should also present in a separate device image, because it is an entry point
+; with unique set of used aspects.
+;
+; CHECK-M1-SYMS: foo
+;
+; CHECK-M2-SYMS: kernel1
+;
+; @kernel1 uses @foo and therefore @foo should be present in the same module as
+; @kernel1 as well
+; CHECK-M2-IR-DAG: define spir_func void @foo
+; CHECK-M2-IR-DAG: define spir_kernel void @kernel1
+
+
+target datalayout = "e-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024"
+target triple = "spir64-unknown-linux"
+
+define spir_func void @foo() #0 !sycl_used_aspects !1 {
+  ret void
+}
+
+define spir_func void @bar() #1 !sycl_used_aspects !2 {
+  ret void
+}
+
+define spir_func void @baz() #1 !sycl_used_aspects !2 {
+  ret void
+}
+
+define spir_kernel void @kernel0() #1 !sycl_used_aspects !2 {
+entry:
+  call void @bar()
+  ret void
+}
+
+define spir_kernel void @kernel1() #0 !sycl_used_aspects !3 {
+entry:
+  call void @foo()
+  ret void
+}
+
+attributes #0 = { "sycl-module-id"="TU1.cpp" }
+attributes #1 = { "sycl-module-id"="TU2.cpp" }
+
+!1 = !{i32 1}
+!2 = !{i32 2}
+!3 = !{i32 3, i32 1}

llvm/test/tools/sycl-post-link/device-code-split/per-aspect-split-4.ll

@@ -0,0 +1,55 @@
+; This test is intended to check that we do not perform per-aspect split if
+; it was disabled through one or another sycl-post-link option
+
+; RUN: sycl-post-link -symbols -S %s -o %t.table
+; RUN: FileCheck %s -input-file=%t.table --check-prefix CHECK-TABLE
+; RUN: FileCheck %s -input-file=%t_0.ll --check-prefix CHECK-IR
+;
+; -lower-esimd is needed so sycl-post-link does not complain about no actions
+; specified
+; RUN: sycl-post-link -lower-esimd -ir-output-only -S %s -o %t.ll
+; RUN: FileCheck %s -input-file=%t.ll --check-prefix CHECK-IR
+
+; We expect to see only one module generated:
+;
+; CHECK-TABLE: Code
+; CHECK-TABLE-NEXT: _0.ll
+; CHECK-TABLE-EMPTY:
+
+; Regardless of used aspects and sycl-module-id metadata, all kernel and
+; functions should still be present.
+
+; CHECK-IR-DAG: define spir_func void @foo
+; CHECK-IR-DAG: define spir_func void @bar
+; CHECK-IR-DAG: define spir_kernel void @kernel0
+; CHECK-IR-DAG: define spir_kernel void @kernel1
+
+target datalayout = "e-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024"
+target triple = "spir64-unknown-linux"
+
+define spir_func void @foo() #0 !sycl_used_aspects !1 {
+  ret void
+}
+
+define spir_func void @bar() #1 !sycl_used_aspects !2 {
+  ret void
+}
+
+define spir_kernel void @kernel0() #1 !sycl_used_aspects !2 {
+entry:
+  ret void
+}
+
+define spir_kernel void @kernel1() #0 !sycl_used_aspects !3 {
+entry:
+  call void @foo()
+  ret void
+}
+
+attributes #0 = { "sycl-module-id"="TU1.cpp" }
+attributes #1 = { "sycl-module-id"="TU2.cpp" }
+
+!1 = !{i32 1}
+!2 = !{i32 2}
+!3 = !{i32 3, i32 1}
+