maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/Driver/hip-binding.hip

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

44 lines
2.7 KiB
Plaintext
Raw Normal View History

[HIP] Fix unbundling HIP uses clang-offload-bundler to bundle intermediate files for host and different gpu archs together. When a file is unbundled, clang-offload-bundler should be called only once, and the objects for host and different gpu archs should be passed to the next jobs. This is because Driver maintains CachedResults which maps triple-arch string to output files for each job. This patch fixes a bug in Driver::BuildJobsForActionNoCache which uses incorrect key for CachedResults for HIP which causes clang-offload-bundler being called mutiple times and incorrect output files being used. It only affects HIP. Differential Revision: https://reviews.llvm.org/D47555 llvm-svn: 334128
2018-06-07 03:44:10 +08:00
// REQUIRES: clang-driver
// REQUIRES: x86-registered-target
// REQUIRES: amdgpu-registered-target
[HIP] Do not call opt/llc for -fno-gpu-rdc Currently HIP toolchain calls clang to emit bitcode then calls opt/llc for device compilation for the default -fno-gpu-rdc case, which is unnecessary since clang is able to compile a single source file to ISA. This patch fixes the HIP action builder and toolchain so that the default -fno-gpu-rdc can be done like a canonical toolchain, i.e. one clang -cc1 invocation to compile source code to ISA. This can avoid unnecessary processes to speed up the compilation, and avoid redundant LLVM passes which are performed in clang -cc1 and opt. Differential Revision: https://reviews.llvm.org/D81627
2020-06-10 03:02:53 +08:00
// RUN: %clang -ccc-print-bindings -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
// RUN: -c 2>&1 | FileCheck -check-prefix=NRDCS %s
// NRDCS: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[IN:.*hip-binding.hip]]"], output: "[[OBJ1:.*o]]"
// NRDCS: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ1]]"], output: "[[IMG1:.*]]"
// NRDCS: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[IN:.*hip-binding.hip]]"], output: "[[OBJ2:.*o]]"
// NRDCS: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ2]]"], output: "[[IMG2:.*]]"
// NRDCS: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[IMG1]]", "[[IMG2]]"], output: "[[FATBIN:.*]]"
// NRDCS: # "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[IN]]", "[[FATBIN]]"], output: "{{.*}}"
// RUN: %clang -ccc-print-bindings -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
// RUN: -c -fgpu-rdc 2>&1 | FileCheck -check-prefix=RDCS %s
// RDCS: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[IN:.*hip-binding.hip]]"], output: "[[BC1:.*bc]]"
// RDCS: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[IN:.*hip-binding.hip]]"], output: "[[BC2:.*bc]]"
// RDCS: # "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[IN]]"], output: "[[HOSTOBJ:.*o]]"
// RDCS: # "x86_64-unknown-linux-gnu" - "offload bundler", inputs: ["[[BC1]]", "[[BC2]]", "[[HOSTOBJ]]"], output: "{{.*}}"
[HIP] Fix unbundling HIP uses clang-offload-bundler to bundle intermediate files for host and different gpu archs together. When a file is unbundled, clang-offload-bundler should be called only once, and the objects for host and different gpu archs should be passed to the next jobs. This is because Driver maintains CachedResults which maps triple-arch string to output files for each job. This patch fixes a bug in Driver::BuildJobsForActionNoCache which uses incorrect key for CachedResults for HIP which causes clang-offload-bundler being called mutiple times and incorrect output files being used. It only affects HIP. Differential Revision: https://reviews.llvm.org/D47555 llvm-svn: 334128
2018-06-07 03:44:10 +08:00
// RUN: touch %t.o
// RUN: %clang --hip-link -ccc-print-bindings -target x86_64-linux-gnu \
[HIP] Do not unbundle object files for -fno-gpu-rdc When -fno-gpu-rdc is set, device code is compiled, linked, and assembled into fat binary and embedded as string in object files. The object files are normal object files which can be linked by host linker. In the linking stage, the object files should not be unbundled when -fno-gpu-rdc is set since they are normal object files, not bundles. The object files only need to be unbundled when -fgpu-rdc is set. Currently clang always unbundles object files, disregarding -fgpu-rdc option. This patch fixes that. Differential Revision: https://reviews.llvm.org/D58917 llvm-svn: 355410
2019-03-06 00:07:56 +08:00
// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 -fgpu-rdc %t.o\
[HIP] Fix unbundling HIP uses clang-offload-bundler to bundle intermediate files for host and different gpu archs together. When a file is unbundled, clang-offload-bundler should be called only once, and the objects for host and different gpu archs should be passed to the next jobs. This is because Driver maintains CachedResults which maps triple-arch string to output files for each job. This patch fixes a bug in Driver::BuildJobsForActionNoCache which uses incorrect key for CachedResults for HIP which causes clang-offload-bundler being called mutiple times and incorrect output files being used. It only affects HIP. Differential Revision: https://reviews.llvm.org/D47555 llvm-svn: 334128
2018-06-07 03:44:10 +08:00
// RUN: 2>&1 | FileCheck %s
[HIP] Move HIP Linking Logic into HIP ToolChain This patch is a follow up on https://reviews.llvm.org/D78759. Extract the HIP Linker script from generic GNU linker, and move it into HIP ToolChain. Update OffloadActionBuilder Link actions feature to apply device linking and host linking actions separately. Using MC Directives, embed the device images and define symbols. Reviewers: JonChesterfield, yaxunl Subscribers: tra, echristo, jdoerfert, msearles, scchan Differential Revision: https://reviews.llvm.org/D81963
2020-06-12 02:36:10 +08:00
// CHECK: # "x86_64-unknown-linux-gnu" - "offload bundler", inputs: ["[[IN:.*o]]"], outputs: ["[[HOSTOBJ:.*o]]", "{{.*o}}", "{{.*o}}"]
// CHECK: # "amdgcn-amd-amdhsa" - "offload bundler", inputs: ["[[IN]]"], outputs: ["{{.*o}}", "[[DOBJ1:.*o]]", "[[DOBJ2:.*o]]"]
// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[DOBJ1]]"], output: "[[IMG1:.*out]]"
[HIP] Fix unbundling HIP uses clang-offload-bundler to bundle intermediate files for host and different gpu archs together. When a file is unbundled, clang-offload-bundler should be called only once, and the objects for host and different gpu archs should be passed to the next jobs. This is because Driver maintains CachedResults which maps triple-arch string to output files for each job. This patch fixes a bug in Driver::BuildJobsForActionNoCache which uses incorrect key for CachedResults for HIP which causes clang-offload-bundler being called mutiple times and incorrect output files being used. It only affects HIP. Differential Revision: https://reviews.llvm.org/D47555 llvm-svn: 334128
2018-06-07 03:44:10 +08:00
// CHECK-NOT: offload bundler
[HIP] Move HIP Linking Logic into HIP ToolChain This patch is a follow up on https://reviews.llvm.org/D78759. Extract the HIP Linker script from generic GNU linker, and move it into HIP ToolChain. Update OffloadActionBuilder Link actions feature to apply device linking and host linking actions separately. Using MC Directives, embed the device images and define symbols. Reviewers: JonChesterfield, yaxunl Subscribers: tra, echristo, jdoerfert, msearles, scchan Differential Revision: https://reviews.llvm.org/D81963
2020-06-12 02:36:10 +08:00
// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[DOBJ2]]"], output: "[[IMG2:.*out]]"
[HIP] Fix unbundling HIP uses clang-offload-bundler to bundle intermediate files for host and different gpu archs together. When a file is unbundled, clang-offload-bundler should be called only once, and the objects for host and different gpu archs should be passed to the next jobs. This is because Driver maintains CachedResults which maps triple-arch string to output files for each job. This patch fixes a bug in Driver::BuildJobsForActionNoCache which uses incorrect key for CachedResults for HIP which causes clang-offload-bundler being called mutiple times and incorrect output files being used. It only affects HIP. Differential Revision: https://reviews.llvm.org/D47555 llvm-svn: 334128
2018-06-07 03:44:10 +08:00
// CHECK-NOT: offload bundler
[HIP] Move HIP Linking Logic into HIP ToolChain This patch is a follow up on https://reviews.llvm.org/D78759. Extract the HIP Linker script from generic GNU linker, and move it into HIP ToolChain. Update OffloadActionBuilder Link actions feature to apply device linking and host linking actions separately. Using MC Directives, embed the device images and define symbols. Reviewers: JonChesterfield, yaxunl Subscribers: tra, echristo, jdoerfert, msearles, scchan Differential Revision: https://reviews.llvm.org/D81963
2020-06-12 02:36:10 +08:00
// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[IMG1]]", "[[IMG2]]"], output: "[[FATBINOBJ:.*o]]"
// CHECK-NOT: offload bundler
// CHECK: # "x86_64-unknown-linux-gnu" - "GNU::Linker", inputs: ["[[HOSTOBJ]]", "[[FATBINOBJ]]"], output: "a.out"
[HIP] Do not unbundle object files for -fno-gpu-rdc When -fno-gpu-rdc is set, device code is compiled, linked, and assembled into fat binary and embedded as string in object files. The object files are normal object files which can be linked by host linker. In the linking stage, the object files should not be unbundled when -fno-gpu-rdc is set since they are normal object files, not bundles. The object files only need to be unbundled when -fgpu-rdc is set. Currently clang always unbundles object files, disregarding -fgpu-rdc option. This patch fixes that. Differential Revision: https://reviews.llvm.org/D58917 llvm-svn: 355410
2019-03-06 00:07:56 +08:00
// RUN: %clang --hip-link -ccc-print-bindings -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t.o\
// RUN: 2>&1 | FileCheck -check-prefix=NORDC %s
// NORDC-NOT: offload bundler
// NORDC: # "x86_64-unknown-linux-gnu" - "GNU::Linker", inputs: ["{{.*o}}"], output: "a.out"