jrbyrnes updated this revision to Diff 534725.
jrbyrnes marked an inline comment as done.
jrbyrnes added a comment.
Fix tests + add tests. Add phase test for -fgpu-rdc --no-gpu-link-output (these
are not intended to be used together)
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D153667/new/
https://reviews.llvm.org/D153667
Files:
clang/include/clang/Driver/Options.td
clang/lib/Driver/Driver.cpp
clang/test/Driver/hip-device-compile.hip
clang/test/Driver/hip-phases.hip
clang/test/Driver/hip-rdc-device-only.hip
Index: clang/test/Driver/hip-rdc-device-only.hip
===================================================================
--- clang/test/Driver/hip-rdc-device-only.hip
+++ clang/test/Driver/hip-rdc-device-only.hip
@@ -5,7 +5,7 @@
// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
// RUN: -c -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
-// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output --gpu-link-output \
// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITBC %s
// With `-emit-llvm`, the output should be the same as the aforementioned line
@@ -15,14 +15,14 @@
// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
// RUN: -c -emit-llvm -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
-// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output --gpu-link-output \
// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITBC %s
// RUN: %clang -### --target=x86_64-linux-gnu \
// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
// RUN: -S -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
-// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output --gpu-link-output \
// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITLL %s
// With `-emit-llvm`, the output should be the same as the aforementioned line
@@ -32,7 +32,7 @@
// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
// RUN: -S -emit-llvm -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
-// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output --gpu-link-output \
// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITLL %s
// With `-save-temps`, commane lines for each steps are dumped. For assembly
@@ -43,7 +43,7 @@
// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
// RUN: -S -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
-// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output --gpu-link-output \
// RUN: 2>&1 | FileCheck -check-prefix=SAVETEMP %s
// Check output one file without bundling cause error.
@@ -54,6 +54,12 @@
// RUN: %S/Inputs/hip_multiple_inputs/a.cu -o %t.s --no-gpu-bundle-output \
// RUN: 2>&1 | FileCheck -check-prefix=FAIL %s
+// RUN: %clang -### --target=x86_64-linux-gnu \
+// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN: -S -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
+// RUN: %S/Inputs/hip_multiple_inputs/a.cu -o %t.s --no-gpu-link-output \
+// RUN: 2>&1 | FileCheck -check-prefix=FAIL %s
+
// COMMON: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
// COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
// EMITBC-SAME: "-emit-llvm-bc"
Index: clang/test/Driver/hip-phases.hip
===================================================================
--- clang/test/Driver/hip-phases.hip
+++ clang/test/Driver/hip-phases.hip
@@ -244,6 +244,53 @@
// DASM-NOT: clang-offload-bundler
// DASM-NOT: host
+//
+// Test single gpu architecture with compile to relocatable in device-only
+// compilation mode.
+//
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 %s --cuda-device-only --no-gpu-link-output 2>&1 \
+// RUN: | FileCheck -check-prefixes=RELOC %s
+// RELOC-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
+// RELOC-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
+// RELOC-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
+// RELOC-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
+// RELOC-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
+// RELOC-NOT: linker
+// RELOC-DAG: [[P5:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P4]]}, object
+
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 %s --cuda-device-only --no-gpu-link-output -fgpu-rdc 2>&1 \
+// RUN: | FileCheck -check-prefixes=RELOC3 %s
+// RELOC3-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
+// RELOC3-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
+// RELOC3-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
+// RELOC3-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, ir, (device-[[T]], [[ARCH]])
+// RELOC3-NOT: linker
+// RELOC3-DAG: [[P4:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P3]]}, ir
+
+//
+// Test two gpu architectures with compile to relocatable in device-only
+// compilation mode.
+//
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s --cuda-device-only --no-gpu-link-output 2>&1 \
+// RUN: | FileCheck -check-prefixes=RELOC2 %s
+// RELOC2-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
+// RELOC2-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
+// RELOC2-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
+// RELOC2-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
+// RELOC2-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
+// RELOC2-NOT: [[P5:[0-9]+]]: linker, {[[P4]]}, image, (device-[[T]], [[ARCH]])
+// RELOC2-DAG: [[P5:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P4]]}, object
+// RELOC2-DAG: [[P6:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH2:gfx900]])
+// RELOC2-DAG: [[P7:[0-9]+]]: preprocessor, {[[P6]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH2]])
+// RELOC2-DAG: [[P8:[0-9]+]]: compiler, {[[P7]]}, ir, (device-[[T]], [[ARCH2]])
+// RELOC2-DAG: [[P9:[0-9]+]]: backend, {[[P8]]}, assembler, (device-[[T]], [[ARCH2]])
+// RELOC2-DAG: [[P10:[0-9]+]]: assembler, {[[P9]]}, object, (device-[[T]], [[ARCH2]])
+// RELOC2-NOT: linker
+// RELOC2-DAG: [[P11:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH2]])" {[[P10]]}, object
+
//
// Test two gpu architectures with complete compilation in device-only
// compilation mode.
Index: clang/test/Driver/hip-device-compile.hip
===================================================================
--- clang/test/Driver/hip-device-compile.hip
+++ clang/test/Driver/hip-device-compile.hip
@@ -45,6 +45,14 @@
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
// RUN: 2>&1 | FileCheck -check-prefixes=CHECK,ASM,NBUN %s
+// Output relocatable.
+// RUN: %clang -c --cuda-device-only -### --target=x86_64-linux-gnu \
+// RUN: -o a.o -x hip --cuda-gpu-arch=gfx900 --no-gpu-link-output \
+// RUN: --hip-device-lib=lib1.bc \
+// RUN: --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/lib1 \
+// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN: 2>&1 | FileCheck -check-prefixes=CHECK,NBUN,RELOC %s
+
// Output bundled assembly.
// RUN: %clang -c -S --cuda-device-only -### --target=x86_64-linux-gnu \
// RUN: -o a.s -x hip --cuda-gpu-arch=gfx900 --no-gpu-bundle-output \
@@ -68,6 +76,7 @@
// LLBUN-SAME: "-o" "{{.*}}.ll"
// ASM-SAME: "-o" "a.s"
// ASMBUN-SAME: "-o" "{{.*}}.s"
+// RELOC-SAME: "-o" "a.o"
// CHECK-SAME: {{".*a.cu"}}
// CHECK-NOT: {{"*.llvm-link"}}
Index: clang/lib/Driver/Driver.cpp
===================================================================
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -3322,16 +3322,23 @@
// only compilation. Bundle other type of output files only if
// --gpu-bundle-output is specified for device only compilation.
std::optional<bool> BundleOutput;
+ std::optional<bool> LinkOutput;
public:
HIPActionBuilder(Compilation &C, DerivedArgList &Args,
const Driver::InputList &Inputs)
: CudaActionBuilderBase(C, Args, Inputs, Action::OFK_HIP) {
DefaultCudaArch = CudaArch::GFX906;
+ if (Args.hasArg(options::OPT_gpu_link_output,
+ options::OPT_no_gpu_link_output))
+ LinkOutput = Args.hasFlag(options::OPT_gpu_link_output,
+ options::OPT_no_gpu_link_output, true);
+
if (Args.hasArg(options::OPT_gpu_bundle_output,
options::OPT_no_gpu_bundle_output))
BundleOutput = Args.hasFlag(options::OPT_gpu_bundle_output,
- options::OPT_no_gpu_bundle_output, true);
+ options::OPT_no_gpu_bundle_output, true) &&
+ (!LinkOutput || *LinkOutput);
}
bool canUseBundlerUnbundler() const override { return true; }
@@ -3378,8 +3385,10 @@
assert(!CompileHostOnly &&
"Not expecting HIP actions in host-only compilation.");
+ bool ShouldLink = !LinkOutput || *LinkOutput;
+
if (!Relocatable && CurPhase == phases::Backend && !EmitLLVM &&
- !EmitAsm) {
+ !EmitAsm && ShouldLink) {
// If we are in backend phase, we attempt to generate the fat binary.
// We compile each arch to IR and use a link action to generate code
// object containing ISA. Then we use a special "link" action to create
@@ -3455,6 +3464,8 @@
return CompileDeviceOnly ? ABRT_Ignore_Host : ABRT_Success;
} else if (CurPhase == phases::Link) {
+ if (!ShouldLink)
+ return ABRT_Success;
// Save CudaDeviceActions to DeviceLinkerInputs for each GPU subarch.
// This happens to each device action originated from each input file.
// Later on, device actions in DeviceLinkerInputs are used to create
@@ -3492,8 +3503,11 @@
CudaDeviceActions.clear();
}
- return (CompileDeviceOnly && CurPhase == FinalPhase) ? ABRT_Ignore_Host
- : ABRT_Success;
+ return (CompileDeviceOnly &&
+ (CurPhase == FinalPhase ||
+ (!ShouldLink && CurPhase == phases::Assemble)))
+ ? ABRT_Ignore_Host
+ : ABRT_Success;
}
void appendLinkDeviceActions(ActionList &AL) override {
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -1124,6 +1124,10 @@
Group<f_Group>, HelpText<"Bundle output files of HIP device compilation">;
def no_gpu_bundle_output : Flag<["--"], "no-gpu-bundle-output">,
Group<f_Group>, HelpText<"Do not bundle output files of HIP device compilation">;
+def gpu_link_output : Flag<["--"], "gpu-link-output">,
+ Group<f_Group>, HelpText<"Link output files of HIP device compilation">;
+def no_gpu_link_output : Flag<["--"], "no-gpu-link-output">,
+ Group<f_Group>, HelpText<"Do not link output files of HIP device compilation">;
def cuid_EQ : Joined<["-"], "cuid=">, Flags<[CC1Option]>,
HelpText<"An ID for compilation unit, which should be the same for the same "
"compilation unit but different for different compilation units. "
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
