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-toolchain-features.hip

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

82 lines
3.8 KiB
Plaintext
Raw Normal View History

[HIP] Handle compile -m options and propagate into LLC Allow the compile options for -m such as -mxnack/-mno-xnack, -msram-ecc/-mno-sram-ecc, -mcode-object-v3/-mno-code-object-v3 to propagate into LLC args. Fix an issue where -mattr was pushed even when it was empty. Also add lit tests to verify features are properly passed. Differential Revision: https://reviews.llvm.org/D57977 Reviewers: yaxunl, kzhuravl llvm-svn: 353952
2019-02-14 00:12:16 +08:00
// REQUIRES: clang-driver
// REQUIRES: x86-registered-target
// REQUIRES: amdgpu-registered-target
[HIP] Add missing options for lto Add -mcpu, -mattr, -mllvm, and -save-temps options for lto when necessary. Differential Revision: https://reviews.llvm.org/D82506
2020-06-25 05:34:21 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
[HIP] Support target id by --offload-arch This patch introduces support of target id by -offload-arch. Differential Revision: https://reviews.llvm.org/D60620
2020-05-05 11:22:06 +08:00
// RUN: --cuda-gpu-arch=gfx906:xnack+ --cuda-gpu-arch=gfx900:xnack+ %s \
// RUN: 2>&1 | FileCheck %s -check-prefix=XNACK
[HIP] Add missing options for lto Add -mcpu, -mattr, -mllvm, and -save-temps options for lto when necessary. Differential Revision: https://reviews.llvm.org/D82506
2020-06-25 05:34:21 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
[HIP] Support target id by --offload-arch This patch introduces support of target id by -offload-arch. Differential Revision: https://reviews.llvm.org/D60620
2020-05-05 11:22:06 +08:00
// RUN: --cuda-gpu-arch=gfx906:xnack- --cuda-gpu-arch=gfx900:xnack- %s \
// RUN: 2>&1 | FileCheck %s -check-prefix=NOXNACK
[HIP] Handle compile -m options and propagate into LLC Allow the compile options for -m such as -mxnack/-mno-xnack, -msram-ecc/-mno-sram-ecc, -mcode-object-v3/-mno-code-object-v3 to propagate into LLC args. Fix an issue where -mattr was pushed even when it was empty. Also add lit tests to verify features are properly passed. Differential Revision: https://reviews.llvm.org/D57977 Reviewers: yaxunl, kzhuravl llvm-svn: 353952
2019-02-14 00:12:16 +08:00
// XNACK: {{.*}}clang{{.*}}"-target-feature" "+xnack"
// NOXNACK: {{.*}}clang{{.*}}"-target-feature" "-xnack"
[AMDGPU] Extend hip-toolchin-features.hip test - Extend hip-toolchin-features.hip to also check the lld attributes are passed correctly. - Add check for cumode attributes. Differential Revision: https://reviews.llvm.org/D89636
2020-10-18 06:38:04 +08:00
// XNACK: {{.*}}lld{{.*}} "-plugin-opt=-mattr=+xnack"
// NOXNACK: {{.*}}lld{{.*}} "-plugin-opt=-mattr=-xnack"
[HIP] Handle compile -m options and propagate into LLC Allow the compile options for -m such as -mxnack/-mno-xnack, -msram-ecc/-mno-sram-ecc, -mcode-object-v3/-mno-code-object-v3 to propagate into LLC args. Fix an issue where -mattr was pushed even when it was empty. Also add lit tests to verify features are properly passed. Differential Revision: https://reviews.llvm.org/D57977 Reviewers: yaxunl, kzhuravl llvm-svn: 353952
2019-02-14 00:12:16 +08:00
[HIP] Add missing options for lto Add -mcpu, -mattr, -mllvm, and -save-temps options for lto when necessary. Differential Revision: https://reviews.llvm.org/D82506
2020-06-25 05:34:21 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
[clang][AMDGPU] rename sram-ecc as sramecc As backend renamed sram-ecc to sramecc, this patch makes corresponding change in clang. Differential Revision: https://reviews.llvm.org/D86217
2020-12-08 06:31:28 +08:00
// RUN: --cuda-gpu-arch=gfx908:sramecc+ %s \
[HIP] Support target id by --offload-arch This patch introduces support of target id by -offload-arch. Differential Revision: https://reviews.llvm.org/D60620
2020-05-05 11:22:06 +08:00
// RUN: 2>&1 | FileCheck %s -check-prefix=SRAM
[HIP] Add missing options for lto Add -mcpu, -mattr, -mllvm, and -save-temps options for lto when necessary. Differential Revision: https://reviews.llvm.org/D82506
2020-06-25 05:34:21 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
[clang][AMDGPU] rename sram-ecc as sramecc As backend renamed sram-ecc to sramecc, this patch makes corresponding change in clang. Differential Revision: https://reviews.llvm.org/D86217
2020-12-08 06:31:28 +08:00
// RUN: --cuda-gpu-arch=gfx908:sramecc- %s \
[HIP] Support target id by --offload-arch This patch introduces support of target id by -offload-arch. Differential Revision: https://reviews.llvm.org/D60620
2020-05-05 11:22:06 +08:00
// RUN: 2>&1 | FileCheck %s -check-prefix=NOSRAM
[HIP] Handle compile -m options and propagate into LLC Allow the compile options for -m such as -mxnack/-mno-xnack, -msram-ecc/-mno-sram-ecc, -mcode-object-v3/-mno-code-object-v3 to propagate into LLC args. Fix an issue where -mattr was pushed even when it was empty. Also add lit tests to verify features are properly passed. Differential Revision: https://reviews.llvm.org/D57977 Reviewers: yaxunl, kzhuravl llvm-svn: 353952
2019-02-14 00:12:16 +08:00
[clang][AMDGPU] rename sram-ecc as sramecc As backend renamed sram-ecc to sramecc, this patch makes corresponding change in clang. Differential Revision: https://reviews.llvm.org/D86217
2020-12-08 06:31:28 +08:00
// SRAM: {{.*}}clang{{.*}}"-target-feature" "+sramecc"
// NOSRAM: {{.*}}clang{{.*}}"-target-feature" "-sramecc"
// SRAM: {{.*}}lld{{.*}} "-plugin-opt=-mattr=+sramecc"
// NOTSRAM: {{.*}}lld{{.*}} "-plugin-opt=-mattr=-sramecc"
[AMDGPU] Extend hip-toolchin-features.hip test - Extend hip-toolchin-features.hip to also check the lld attributes are passed correctly. - Add check for cumode attributes. Differential Revision: https://reviews.llvm.org/D89636
2020-10-18 06:38:04 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
// RUN: --cuda-gpu-arch=gfx1010 %s \
// RUN: -mcumode 2>&1 | FileCheck %s -check-prefix=CUMODE
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
// RUN: --cuda-gpu-arch=gfx1010 %s \
// RUN: -mno-cumode 2>&1 | FileCheck %s -check-prefix=NOTCUMODE
// CUMODE: {{.*}}clang{{.*}}"-target-feature" "+cumode"
// NOTCUMODE: {{.*}}clang{{.*}}"-target-feature" "-cumode"
// CUMODE: {{.*}}lld{{.*}} "-plugin-opt=-mattr=+cumode"
// NOTCUMODE: {{.*}}lld{{.*}} "-plugin-opt=-mattr=-cumode"
[HIP] Handle compile -m options and propagate into LLC Allow the compile options for -m such as -mxnack/-mno-xnack, -msram-ecc/-mno-sram-ecc, -mcode-object-v3/-mno-code-object-v3 to propagate into LLC args. Fix an issue where -mattr was pushed even when it was empty. Also add lit tests to verify features are properly passed. Differential Revision: https://reviews.llvm.org/D57977 Reviewers: yaxunl, kzhuravl llvm-svn: 353952
2019-02-14 00:12:16 +08:00
[HIP] Add missing options for lto Add -mcpu, -mattr, -mllvm, and -save-temps options for lto when necessary. Differential Revision: https://reviews.llvm.org/D82506
2020-06-25 05:34:21 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
[clang][AMDGPU] rename sram-ecc as sramecc As backend renamed sram-ecc to sramecc, this patch makes corresponding change in clang. Differential Revision: https://reviews.llvm.org/D86217
2020-12-08 06:31:28 +08:00
// RUN: --cuda-gpu-arch=gfx908:xnack+:sramecc+ %s \
[HIP] Handle compile -m options and propagate into LLC Allow the compile options for -m such as -mxnack/-mno-xnack, -msram-ecc/-mno-sram-ecc, -mcode-object-v3/-mno-code-object-v3 to propagate into LLC args. Fix an issue where -mattr was pushed even when it was empty. Also add lit tests to verify features are properly passed. Differential Revision: https://reviews.llvm.org/D57977 Reviewers: yaxunl, kzhuravl llvm-svn: 353952
2019-02-14 00:12:16 +08:00
// RUN: 2>&1 | FileCheck %s -check-prefix=ALL3
[HIP] Add missing options for lto Add -mcpu, -mattr, -mllvm, and -save-temps options for lto when necessary. Differential Revision: https://reviews.llvm.org/D82506
2020-06-25 05:34:21 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
[clang][AMDGPU] rename sram-ecc as sramecc As backend renamed sram-ecc to sramecc, this patch makes corresponding change in clang. Differential Revision: https://reviews.llvm.org/D86217
2020-12-08 06:31:28 +08:00
// RUN: --cuda-gpu-arch=gfx908:xnack-:sramecc- %s \
[HIP] Handle compile -m options and propagate into LLC Allow the compile options for -m such as -mxnack/-mno-xnack, -msram-ecc/-mno-sram-ecc, -mcode-object-v3/-mno-code-object-v3 to propagate into LLC args. Fix an issue where -mattr was pushed even when it was empty. Also add lit tests to verify features are properly passed. Differential Revision: https://reviews.llvm.org/D57977 Reviewers: yaxunl, kzhuravl llvm-svn: 353952
2019-02-14 00:12:16 +08:00
// RUN: 2>&1 | FileCheck %s -check-prefix=NOALL3
[clang][AMDGPU] rename sram-ecc as sramecc As backend renamed sram-ecc to sramecc, this patch makes corresponding change in clang. Differential Revision: https://reviews.llvm.org/D86217
2020-12-08 06:31:28 +08:00
// ALL3: {{.*}}clang{{.*}}"-target-feature" "+sramecc" "-target-feature" "+xnack"
// NOALL3: {{.*}}clang{{.*}}"-target-feature" "-sramecc" "-target-feature" "-xnack"
[NFC] Extract unifyTargetFeatures Differential Revision: https://reviews.llvm.org/D82579
2020-06-25 22:03:31 +08:00
[AMDGPU] gfx90a support Differential Revision: https://reviews.llvm.org/D96906
2021-02-18 05:37:46 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
// RUN: --cuda-gpu-arch=gfx1010 %s \
// RUN: -mtgsplit 2>&1 | FileCheck %s -check-prefix=TGSPLIT
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
// RUN: --cuda-gpu-arch=gfx1010 %s \
// RUN: -mno-tgsplit 2>&1 | FileCheck %s -check-prefix=NOTTGSPLIT
// TGSPLIT: {{.*}}clang{{.*}}"-target-feature" "+tgsplit"
// NOTTGSPLIT: {{.*}}clang{{.*}}"-target-feature" "-tgsplit"
// TGSPLIT: {{.*}}lld{{.*}} "-plugin-opt=-mattr=+tgsplit"
// NOTTGSPLIT: {{.*}}lld{{.*}} "-plugin-opt=-mattr=-tgsplit"
[NFC] Extract unifyTargetFeatures Differential Revision: https://reviews.llvm.org/D82579
2020-06-25 22:03:31 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
// RUN: --cuda-gpu-arch=gfx1010 %s \
// RUN: -mcumode -mcumode -mno-cumode -mwavefrontsize64 -mcumode \
// RUN: -mwavefrontsize64 -mno-wavefrontsize64 2>&1 \
// RUN: | FileCheck %s -check-prefix=DUP
Emit predefined macro for wavefront size for amdgcn Also fix the issue of multiple -m[no-]wavefrontsize64 options to make the last one wins. Differential Revision: https://reviews.llvm.org/D88370
2020-09-27 10:28:04 +08:00
// DUP: {{.*}}clang{{.*}} "-target-feature" "+cumode"
// DUP-NOT: "-target-feature" "{{.*}}wavefrontsize16"
// DUP-NOT: "-target-feature" "{{.*}}wavefrontsize32"
// DUP-NOT: "-target-feature" "{{.*}}wavefrontsize64"
// DUP: {{.*}}lld{{.*}} "-plugin-opt=-mattr=+cumode"
// RUN: %clang -### -target x86_64-linux-gnu -fgpu-rdc -nogpulib \
// RUN: --cuda-gpu-arch=gfx1010 %s \
// RUN: -mno-wavefrontsize64 -mwavefrontsize64 2>&1 \
// RUN: | FileCheck %s -check-prefix=WAVE64
// WAVE64: {{.*}}clang{{.*}} "-target-feature" "+wavefrontsize64"
// WAVE64-NOT: "-target-feature" "{{.*}}wavefrontsize16"
// WAVE64-NOT: "-target-feature" "{{.*}}wavefrontsize32"
// WAVE64: {{.*}}lld{{.*}} "-plugin-opt=-mattr=+wavefrontsize64"