Google Git
Sign in
llvm / llvm-project / libclc / refs/heads/master
commit23845e3ebed4eb2bec486372123dcd2fc560f01b[log] [tgz]
authorWenju He <wenju.he@intel.com>Fri Dec 19 14:36:03 2025 +0800
committerCopybara-Service <copybara-worker@google.com>Thu Dec 18 22:40:48 2025 -0800
treeb527956ca222eb46d9dd2a3d456e9ce625d2708f
parentb653edcb027eb392c3e6bf8e125d4f4c65d51769 [diff]
[libclc] Improve __clc_min/max/clamp implementation (#172599)

Replace __clc_max/min with __clc_fmax/fmin in __clc_clamp. FP
__clc_min/max/clamp now lowers to @llvm.minimumnum/@llvm.maximumnum, and
integer clamp lowers to @llvm.umin/@llvm.umax. This reduce fcmp+select
chains and improving codegen. Example change to amdgcn--amdhsa.bc:
```
in function _Z5clamphhh:
    >   %4 = icmp ugt i8 %0, %2
        %4 = tail call noundef i8 @llvm.umax.i8(i8 %0, i8 %1)
    >   %6 = select i1 %4, i8 %2, i8 %5
    >   ret i8 %6
    <   %5 = tail call noundef i8 @llvm.umin.i8(i8 %2, i8 %4)
    <   ret i8 %5
in function _Z5clampddd:
  in block %3 / %3:
    >   %4 = fcmp ogt double %0, %2
    >   %5 = fcmp olt double %0, %1
    >   %6 = select i1 %5, double %1, double %0
    >   %7 = select i1 %4, double %2, double %6
    >   ret double %7
    <   %4 = tail call noundef double @llvm.maximumnum.f64(double %0, double %1)
    <   %5 = tail call noundef double @llvm.minimumnum.f64(double %4, double %2)
    <   ret double %5
```

GitOrigin-RevId: d5326411fe866e010aadd3af3155b656a5aeaae3
6 files changed
tree: b527956ca222eb46d9dd2a3d456e9ce625d2708f
  1. clc/
  2. cmake/
  3. opencl/
  4. test/
  5. utils/
  6. www/
  7. check_external_funcs.sh
  8. CMakeLists.txt
  9. compile-test.sh
  10. CREDITS.TXT
  11. libclc.pc.in
  12. LICENSE.TXT
  13. Maintainers.md
  14. README.md
README.md

libclc

libclc is an open source implementation of the library requirements of the OpenCL C programming language, as specified by the OpenCL 1.1 Specification. The following sections of the specification impose library requirements:

  • 6.1: Supported Data Types
  • 6.2.3: Explicit Conversions
  • 6.2.4.2: Reinterpreting Types Using as_type() and as_typen()
  • 6.9: Preprocessor Directives and Macros
  • 6.11: Built-in Functions
  • 9.3: Double Precision Floating-Point
  • 9.4: 64-bit Atomics
  • 9.5: Writing to 3D image memory objects
  • 9.6: Half Precision Floating-Point

libclc is intended to be used with the Clang compiler's OpenCL frontend.

libclc is designed to be portable and extensible. To this end, it provides generic implementations of most library requirements, allowing the target to override the generic implementation at the granularity of individual functions.

libclc currently supports PTX, AMDGPU, SPIRV and CLSPV targets, but support for more targets is welcome.

Compiling and installing

(in the following instructions you can use make or ninja)

For an in-tree build, Clang must also be built at the same time:

$ cmake <path-to>/llvm-project/llvm/CMakeLists.txt -DLLVM_ENABLE_PROJECTS="clang" \
    -DLLVM_ENABLE_RUNTIMES="libclc" -DCMAKE_BUILD_TYPE=Release -G Ninja
$ ninja

Then install:

$ ninja install

Note you can use the DESTDIR Makefile variable to do staged installs.

$ DESTDIR=/path/for/staged/install ninja install

To build out of tree, or in other words, against an existing LLVM build or install:

$ cmake <path-to>/llvm-project/libclc/CMakeLists.txt -DCMAKE_BUILD_TYPE=Release \
  -G Ninja -DLLVM_DIR=$(<path-to>/llvm-config --cmakedir)
$ ninja

Then install as before.

In both cases this will include all supported targets. You can choose which targets are enabled by passing -DLIBCLC_TARGETS_TO_BUILD to CMake. The default is all.

In both cases, the LLVM used must include the targets you want libclc support for (AMDGPU and NVPTX are enabled in LLVM by default). Apart from SPIRV where you do not need an LLVM target but you do need the llvm-spirv tool available. Either build this in-tree, or place it in the directory pointed to by LLVM_TOOLS_BINARY_DIR.

Website

https://libclc.llvm.org/