[clang-offload-bundler] Make Bundle Entry ID backward compatible

[saiislam]

Summary

Earlier BundleEntryID used to be <OffloadKind>-<Triple>-<GPUArch>.
This used to work because the clang-offload-bundler didn't need
GPUArch explicitly for any bundling/unbundling action. With
unbundleArchive it needs GPUArch to ensure compatibility between
device specific code objects. D93525 enforced triples to have
separators for all 4 components irrespective of number of
components, like "amdgcn-amd-amdhsa--". It was required to
to correctly parse a possible 4th environment component or a GPU.
But, this condition is breaking backward compatibility with
archive libraries compiled with compilers older than D93525.

This patch allows triples to have any number of components with
and without extra separator for empty environment field. Thus,
both the following bundle entry IDs are same:
openmp-amdgcn-amd-amdhsa--gfx906
openmp-amdgcn-amd-amdhsa-gfx906

[saiislam]

Ping.

[grokos]

LG. One possible suggestion is that you leave the double dash (--) variant in some tests so that we can make sure both variants (e.g. both openmp-amdgcn-amd-amdhsa--gfx906 and openmp-amdgcn-amd-amdhsa-gfx906) are correctly parsed.

[saiislam]

Added test cases for compatibility old and new formats of bundle entry id.

[yaxunl]

clang/tools/clang-offload-bundler/ClangOffloadBundler.cpp

148

This is rather fragile to determine whether a bundle ID contains GPU arch. Is there better way?

At least for HIP offload kind, GPU arch should always be there.

1297

need a test

[saiislam]

1. Added tests for empty and incompatible archives.
2. Improved identification of GPUArch in Bundle Entry ID using CudaArch.

[yaxunl]

Ideally, we probably need something like isValidOffloadArch(Triple, OffloadArch) or getTargetTriple(OffloadArch). However, I think the current patch is good enough for its own purpose.

[grokos]

LGTM as well.

[RKSimon]

clang/test/Driver/clang-offload-bundler.c

405

@saiislam This is causing an issue on a thinlto buildbot: https://lab.llvm.org/buildbot/#/builders/67/builds/4148

[kwk]

@saiislam please have a look into why this happens. Is the -debug-only=CodeObjectCompatibility maybe a left-over of some sort?

clang/test/Driver/clang-offload-bundler.c

405

@saiislam We're seeing the same issue in one of our downstream builders:

: 'RUN: at line 405';   clang-offload-bundler -unbundle -type=a -targets=openmp-amdgcn-amd-amdhsa--gfx906,openmp-amdgcn-amd-amdhsa-gfx908 -inputs=/builddir/build/BUILD/clang-14.0.0.src/redhat-linux-build/test/Driver/Output/clang-offload-bundler.c.tmp.input-archive.a -outputs=/builddir/build/BUILD/clang-14.0.0.src/redhat-linux-build/test/Driver/Output/clang-offload-bundler.c.tmp-archive-gfx906-simple.a,/builddir/build/BUILD/clang-14.0.0.src/redhat-linux-build/test/Driver/Output/clang-offload-bundler.c.tmp-archive-gfx908-simple.a -debug-only=CodeObjectCompatibility 2>&1 | /usr/bin/FileCheck /builddir/build/BUILD/clang-14.0.0.src/test/Driver/clang-offload-bundler.c -check-prefix=BUNDLECOMPATIBILITY
--
Exit Code: 1

Command Output (stderr):
--
/builddir/build/BUILD/clang-14.0.0.src/test/Driver/clang-offload-bundler.c:406:25: error: BUNDLECOMPATIBILITY: expected string not found in input
// BUNDLECOMPATIBILITY: Compatible: Exact match: [CodeObject: openmp-amdgcn-amd-amdhsa-gfx906] : [Target: openmp-amdgcn-amd-amdhsa--gfx906]
                        ^
<stdin>:1:1: note: scanning from here
clang-offload-bundler: Unknown command line argument '-debug-only=CodeObjectCompatibility'. Try: 'clang-offload-bundler --help'
^

Input file: <stdin>
Check file: /builddir/build/BUILD/clang-14.0.0.src/test/Driver/clang-offload-bundler.c

-dump-input=help explains the following input dump.

Input was:
<<<<<<
           1: clang-offload-bundler: Unknown command line argument '-debug-only=CodeObjectCompatibility'. Try: 'clang-offload-bundler --help' 
check:406     X~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ error: no match found
           2: clang-offload-bundler: Did you mean '--unbundle=CodeObjectCompatibility'? 
check:406     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>>>>>>

--

[saiislam]

In D106809#2993666, @kwk wrote:

@saiislam please have a look into why this happens. Is the -debug-only=CodeObjectCompatibility maybe a left-over of some sort?

No, it is not a left-over. I was using this debug output to show that new and old bundle entry ID formats are compatible with each other.

I am taking a look on how to fix this. Thanks for pointing it out @RKSimon and @kwk .

[dyung]

In D106809#2994067, @saiislam wrote:

In D106809#2993666, @kwk wrote:

@saiislam please have a look into why this happens. Is the -debug-only=CodeObjectCompatibility maybe a left-over of some sort?

No, it is not a left-over. I was using this debug output to show that new and old bundle entry ID formats are compatible with each other.

I am taking a look on how to fix this. Thanks for pointing it out @RKSimon and @kwk .

We are also seeing this issue on our internal build bot that builds a "release" configuration.

If you must use "-debug-only" in your test, a fix could be to add "REQUIRES: asserts" to the test, but that would mean the test would then be completely skipped in release builds. A better solution might be to break out the run line with "-debug-only" to a separate test file which does have a "REQUIRES: asserts" line so that we still run everything else that we can.

[saiislam]

In D106809#2994169, @dyung wrote:

In D106809#2994067, @saiislam wrote:

In D106809#2993666, @kwk wrote:

@saiislam please have a look into why this happens. Is the -debug-only=CodeObjectCompatibility maybe a left-over of some sort?

No, it is not a left-over. I was using this debug output to show that new and old bundle entry ID formats are compatible with each other.

I am taking a look on how to fix this. Thanks for pointing it out @RKSimon and @kwk .

We are also seeing this issue on our internal build bot that builds a "release" configuration.

If you must use "-debug-only" in your test, a fix could be to add "REQUIRES: asserts" to the test, but that would mean the test would then be completely skipped in release builds. A better solution might be to break out the run line with "-debug-only" to a separate test file which does have a "REQUIRES: asserts" line so that we still run everything else that we can.

Thanks for the suggestion. I am going to remove the -debug-only test because the same can be tested by changing bundler entry ID format in one of the tests above.

Please have a look at D109592.

clang/docs/ClangOffloadBundler.rst

.. table:: Bundled Code Object Offload Kind
                     to be loaded by the HIP runtime. The fat binary can be
                     loaded directly from a file, or be embedded in the host code
                     object as a data section with the name ``.hip_fatbin``.
 
       openmp        Offload code object for the OpenMP language extension.
       ============= ==============================================================
 
 **target-triple**
-    The target triple of the code object:
-
-.. code::
-
-  <Architecture>-<Vendor>-<OS>-<Environment>
-
-It is required to have all four components present, if target-id is present.
-Components are hyphen separated. If a component is not specified then the
-empty string must be used in its place.
+    The target triple of the code object.
 
 **target-id**
   The canonical target ID of the code object. Present only if the target
   supports a target ID. See :ref:`clang-target-id`.
 
 Each entry of a bundled code object must have a different bundle entry ID. There
 can be multiple entries for the same processor provided they differ in target
 feature settings. If there is an entry with a target feature specified as *Any*,

clang/lib/Driver/ToolChains/Clang.cpp

if (const auto *OA = dyn_cast<OffloadAction>(CurDep)) {
       CurTC = nullptr;
       OA->doOnEachDependence([&](Action *A, const ToolChain *TC, const char *) {
         assert(CurTC == nullptr && "Expected one dependence!");
         CurKind = A->getOffloadingDeviceKind();
         CurTC = TC;
       });
     }
     Triples += Action::GetOffloadKindName(CurKind);
-    Triples += "-";
-    std::string NormalizedTriple = CurTC->getTriple().normalize();
-    Triples += NormalizedTriple;
-
-    if (CurDep->getOffloadingArch() != nullptr) {
-      // If OffloadArch is present it can only appear as the 6th hypen
-      // sepearated field of Bundle Entry ID. So, pad required number of
-      // hyphens in Triple.
-      for (int i = 4 - StringRef(NormalizedTriple).count("-"); i > 0; i--)
-        Triples += "-";
+    Triples += '-';
+    Triples += CurTC->getTriple().normalize();
+    if ((CurKind == Action::OFK_HIP || CurKind == Action::OFK_OpenMP ||
+         CurKind == Action::OFK_Cuda) &&
+        CurDep->getOffloadingArch()) {
+      Triples += '-';
       Triples += CurDep->getOffloadingArch();
     }
   }
   CmdArgs.push_back(TCArgs.MakeArgString(Triples));
 
   // Get bundled file command.
   CmdArgs.push_back(
       TCArgs.MakeArgString(Twine("-outputs=") + Output.getFilename()));
void OffloadBundler::ConstructJobMultipleOutputs(
   Triples += "-targets=";
   auto DepInfo = UA.getDependentActionsInfo();
   for (unsigned I = 0; I < DepInfo.size(); ++I) {
     if (I)
       Triples += ',';
 
     auto &Dep = DepInfo[I];
     Triples += Action::GetOffloadKindName(Dep.DependentOffloadKind);
-    Triples += "-";
-    std::string NormalizedTriple =
-        Dep.DependentToolChain->getTriple().normalize();
-    Triples += NormalizedTriple;
-
-    if (!Dep.DependentBoundArch.empty()) {
-      // If OffloadArch is present it can only appear as the 6th hypen
-      // sepearated field of Bundle Entry ID. So, pad required number of
-      // hyphens in Triple.
-      for (int i = 4 - StringRef(NormalizedTriple).count("-"); i > 0; i--)
-        Triples += "-";
+    Triples += '-';
+    Triples += Dep.DependentToolChain->getTriple().normalize();
+    if ((Dep.DependentOffloadKind == Action::OFK_HIP ||
+         Dep.DependentOffloadKind == Action::OFK_OpenMP ||
+         Dep.DependentOffloadKind == Action::OFK_Cuda) &&
+        !Dep.DependentBoundArch.empty()) {
+      Triples += '-';
       Triples += Dep.DependentBoundArch;
     }
   }
 
   CmdArgs.push_back(TCArgs.MakeArgString(Triples));
 
   // Get bundled file command.
   CmdArgs.push_back(

clang/test/Driver/clang-offload-bundler.c

 // NOHOST-DAG: hip-amdgcn-amd-amdhsa--gfx906
 // Check archive unbundling
 //
 // Create few code object bundles and archive them to create an input archive
 // RUN: clang-offload-bundler -type=o -targets=host-%itanium_abi_triple,openmp-amdgcn-amd-amdhsa--gfx906,openmp-amdgcn-amd-amdhsa--gfx908 -inputs=%t.o,%t.tgt1,%t.tgt2 -outputs=%t.simple.bundle
 // RUN: clang-offload-bundler -type=o -targets=host-%itanium_abi_triple,openmp-amdgcn-amd-amdhsa--gfx903 -inputs=%t.o,%t.tgt1 -outputs=%t.simple1.bundle
 // RUN: llvm-ar cr %t.input-archive.a %t.simple.bundle %t.simple1.bundle
 
-// RUN: clang-offload-bundler -unbundle -type=a -targets=openmp-amdgcn-amd-amdhsa--gfx906,openmp-amdgcn-amd-amdhsa--gfx908 -inputs=%t.input-archive.a -outputs=%t-archive-gfx906-simple.a,%t-archive-gfx908-simple.a
+// RUN: clang-offload-bundler -unbundle -type=a -targets=openmp-amdgcn-amd-amdhsa-gfx906,openmp-amdgcn-amd-amdhsa-gfx908 -inputs=%t.input-archive.a -outputs=%t-archive-gfx906-simple.a,%t-archive-gfx908-simple.a
 // RUN: llvm-ar t %t-archive-gfx906-simple.a | FileCheck %s -check-prefix=GFX906
 // GFX906: simple-openmp-amdgcn-amd-amdhsa--gfx906
 // RUN: llvm-ar t %t-archive-gfx908-simple.a | FileCheck %s -check-prefix=GFX908
 // GFX908-NOT: {{gfx906}}
 
 // Some code so that we can create a binary out of this file.
 int A = 0;
 void test_func(void) {
   ++A;
 }

clang/test/Driver/hip-rdc-device-only.hip

 // COMMON-SAME: "-fapply-global-visibility-to-externs"
 // COMMON-SAME: "-target-cpu" "gfx900"
 // COMMON-SAME: "-fgpu-rdc"
 // EMITBC-SAME: {{.*}} "-o" {{".*a.*bc"}} "-x" "hip"
 // EMITLL-SAME: {{.*}} "-o" {{".*a.*ll"}} "-x" "hip"
 // COMMON-SAME: {{.*}} {{".*a.cu"}}
 
 // COMMON: "{{.*}}clang-offload-bundler" "-type={{(bc|ll)}}"
-// COMMON-SAME: "-targets=hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
+// COMMON-SAME: "-targets=hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // COMMON-SAME: "-outputs=a-hip-amdgcn-amd-amdhsa.{{(bc|ll)}}"
 
 // COMMON: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // EMITBC-SAME: "-emit-llvm-bc"
 // EMITLL-SAME: "-emit-llvm"
 // COMMON-SAME: {{.*}} "-main-file-name" "b.hip"
 // COMMON-SAME: "-fcuda-is-device" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"

 // COMMON-SAME: "-fapply-global-visibility-to-externs"
 // COMMON-SAME: "-target-cpu" "gfx900"
 // COMMON-SAME: "-fgpu-rdc"
 // EMITBC-SAME: {{.*}} "-o" {{".*b.*bc"}} "-x" "hip"
 // EMITLL-SAME: {{.*}} "-o" {{".*b.*ll"}} "-x" "hip"
 // COMMON-SAME: {{.*}} {{".*b.hip"}}
 
 // COMMON: "{{.*}}clang-offload-bundler" "-type={{(bc|ll)}}"
-// COMMON-SAME: "-targets=hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
+// COMMON-SAME: "-targets=hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // COMMON-SAME: "-outputs=b-hip-amdgcn-amd-amdhsa.{{(bc|ll)}}"
 
 // SAVETEMP: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-E"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
 // SAVETEMP-SAME: {{.*}} "-o" [[A_GFX803_CUI:"a.*cui"]] "-x" "hip" {{".*a.cu"}}
 // SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm-bc"

 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" [[A_GFX900_TMP_BC:"a.*tmp.bc"]] "-x" "hip-cpp-output" [[A_GFX900_CUI]]
 // SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" {{"a.*.ll"}} "-x" "ir" [[A_GFX900_TMP_BC]]
 
 // SAVETEMP: "{{.*}}clang-offload-bundler" "-type=ll"
-// SAVETEMP-SAME: "-targets=hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
+// SAVETEMP-SAME: "-targets=hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // SAVETEMP-SAME: "-outputs=a-hip-amdgcn-amd-amdhsa.ll"
 
 // SAVETEMP: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-E"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
 // SAVETEMP-SAME: {{.*}} "-o" [[B_GFX803_CUI:"b.*cui"]] "-x" "hip" {{".*b.hip"}}
 // SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm-bc"

 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" [[B_GFX900_TMP_BC:"b.*tmp.bc"]] "-x" "hip-cpp-output" [[B_GFX900_CUI]]
 // SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
 // SAVETEMP-SAME: "-emit-llvm"
 // SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
 // SAVETEMP-SAME: {{.*}} "-o" {{"b.*.ll"}} "-x" "ir" [[B_GFX900_TMP_BC]]
 
 // SAVETEMP: "{{.*}}clang-offload-bundler" "-type=ll"
-// SAVETEMP-SAME: "-targets=hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
+// SAVETEMP-SAME: "-targets=hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // SAVETEMP-SAME: "-outputs=b-hip-amdgcn-amd-amdhsa.ll"
 
 // FAIL: error: cannot specify -o when generating multiple output files

clang/test/Driver/hip-toolchain-rdc-separate.hip

 // CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
 // CHECK-SAME: "-fgpu-rdc"
 // CHECK-SAME: {{.*}} "-o" "[[A_OBJ_HOST:.*o]]" "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
 // CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
-// CHECK-SAME: "-targets=hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900,host-x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-targets=hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900,host-x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-outputs=[[A_O:.*a.o]]" "-inputs=[[A_BC1]],[[A_BC2]],[[A_OBJ_HOST]]"
 
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
 // CHECK-SAME: "-fcuda-is-device" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"

 // CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-emit-obj"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
 // CHECK-SAME: "-fgpu-rdc"
 // CHECK-SAME: {{.*}} "-o" "[[B_OBJ_HOST:.*o]]" "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]
 
 // CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
-// CHECK-SAME: "-targets=hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900,host-x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-targets=hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900,host-x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-outputs=[[B_O:.*b.o]]" "-inputs=[[B_BC1]],[[B_BC2]],[[B_OBJ_HOST]]"
 
 // RUN: touch %T/a.o
 // RUN: touch %T/b.o
 // RUN: %clang --hip-link -### -target x86_64-linux-gnu \
 // RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
 // RUN:   -fuse-ld=lld -fgpu-rdc -nogpuinc \
 // RUN:   %T/a.o %T/b.o \
 // RUN: 2>&1 | FileCheck -check-prefix=LINK %s
 
 // LINK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
-// LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
+// LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // LINK-SAME: "-inputs=[[A_O:.*a.o]]" "-outputs=[[A_OBJ_HOST:.*o]],{{.*o}},{{.*o}}"
 // LINK: "-unbundle" "-allow-missing-bundles"
 
 // LINK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
-// LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
+// LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // LINK-SAME: "-inputs=[[B_O:.*b.o]]" "-outputs=[[B_OBJ_HOST:.*o]],{{.*o}},{{.*o}}"
 // LINK: "-unbundle" "-allow-missing-bundles"
 
 // LINK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
-// LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
+// LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // LINK-SAME: "-inputs=[[A_O]]" "-outputs={{.*o}},[[A_BC1:.*o]],[[A_BC2:.*o]]"
 // LINK: "-unbundle" "-allow-missing-bundles"
 
 // LINK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
-// LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa--gfx803,hip-amdgcn-amd-amdhsa--gfx900"
+// LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // LINK-SAME: "-inputs=[[B_O]]" "-outputs={{.*o}},[[B_BC1:.*o]],[[B_BC2:.*o]]"
 // LINK: "-unbundle" "-allow-missing-bundles"
 
 // LINK-NOT: "*.llvm-link"
 // LINK-NOT: ".*opt"
 // LINK-NOT: ".*llc"
 // LINK: {{".*lld.*"}} {{.*}} "-plugin-opt=-amdgpu-internalize-symbols"
 // LINK: "-plugin-opt=mcpu=gfx803"

clang/tools/clang-offload-bundler/ClangOffloadBundler.cpp

 static std::string BundlerExecutable;
 
 /// Obtain the offload kind, real machine triple, and an optional GPUArch
 /// out of the target information specified by the user.
 /// Bundle Entry ID (or, Offload Target String) has following components:
 ///  * Offload Kind - Host, OpenMP, or HIP
 ///  * Triple - Standard LLVM Triple
 ///  * GPUArch (Optional) - Processor name, like gfx906 or sm_30
-/// In presence of Proc, the Triple should contain separator "-" for all
-/// standard four components, even if they are empty.
+
 struct OffloadTargetInfo {
   StringRef OffloadKind;
   llvm::Triple Triple;
   StringRef GPUArch;
 
   OffloadTargetInfo(const StringRef Target) {
-    SmallVector<StringRef, 6> Components;
-    Target.split(Components, '-', 5);
-    Components.resize(6);
-    this->OffloadKind = Components[0];
-    this->Triple = llvm::Triple(Components[1], Components[2], Components[3],
-                                Components[4]);
-    this->GPUArch = Components[5];
+    auto TargetFeatures = Target.split(':');
+    auto TripleOrGPU = TargetFeatures.first.rsplit('-');
+
+    // Check if the last option before any colon is a triple field or a GPU name
+    if (TripleOrGPU.second.startswith("gfx") ||
+        TripleOrGPU.second.startswith("sm_")) {
+      auto KindTriple = TripleOrGPU.first.split('-');
+      this->OffloadKind = KindTriple.first;
+      this->Triple = llvm::Triple(KindTriple.second);
+      auto TID = Target.substr(Target.find("gfx"));
+      if (TID.empty())
+        TID = Target.substr(Target.find("sm_"));
+      this->GPUArch = TID;
+    } else {
+      auto KindTriple = TargetFeatures.first.split('-');
+      this->OffloadKind = KindTriple.first;
+      this->Triple = llvm::Triple(KindTriple.second);
+      this->GPUArch = "";
+    }
   }
 
   bool hasHostKind() const { return this->OffloadKind == "host"; }
 
   bool isOffloadKindValid() const {
     return OffloadKind == "host" || OffloadKind == "openmp" ||
            OffloadKind == "hip" || OffloadKind == "hipv4";
   }
if (CurArchiveMembers != OutputArchivesMap.end()) {
                                         true, false, nullptr))
         return WriteErr;
     } else if (!AllowMissingBundles) {
       std::string ErrMsg =
           Twine("no compatible code object found for the target '" + Target +
                 "' in heterogenous archive library: " + IFName)
               .str();
       return createStringError(inconvertibleErrorCode(), ErrMsg);
+    } else { // Create an empty archive file if no compatible code object is
+             // found and "allow-missing-bundles" is enabled. It ensures that
+             // the linker using output of this step doesn't complain about
+             // the missing input file.
+      std::vector<llvm::NewArchiveMember> EmptyArchive;
+      EmptyArchive.clear();
+      if (Error WriteErr = writeArchive(FileName, EmptyArchive, true,
+                                        getDefaultArchiveKindForHost(), true,
+                                        false, nullptr))
+        return WriteErr;
     }
   }
 
   return Error::success();
 }
 
 static void PrintVersion(raw_ostream &OS) {
   OS << clang::getClangToolFullVersion("clang-offload-bundler") << '\n';