Skip to content

cmake : fix compile assumptions for power9/etc #2777

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 5, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 15 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
- Plain C/C++ implementation without dependencies
- Apple Silicon first-class citizen - optimized via ARM NEON, Accelerate framework, Metal and [Core ML](#core-ml-support)
- AVX intrinsics support for x86 architectures
- VSX intrinsics support for POWER architectures
- [VSX intrinsics support for POWER architectures](#power-vsx-intrinsics)
- Mixed F16 / F32 precision
- [Integer quantization support](#quantization)
- Zero memory allocations at runtime
Expand Down Expand Up @@ -139,6 +139,20 @@ make -j large-v3-turbo
| medium | 1.5 GiB | ~2.1 GB |
| large | 2.9 GiB | ~3.9 GB |

## POWER VSX Intrinsics

`whisper.cpp` supports POWER architectures and includes code which
significantly speeds operation on Linux running on POWER9/10, making it
capable of faster-than-realtime transcription on underclocked Raptor
Talos II. Ensure you have a BLAS package installed, and replace the
standard cmake setup with:

```bash
# build with GGML_BLAS defined
cmake -B build -DGGML_BLAS=1
cmake --build build --config Release
./build/bin/whisper-cli [ .. etc .. ]

## Quantization

`whisper.cpp` supports integer quantization of the Whisper `ggml` models.
Expand Down
18 changes: 7 additions & 11 deletions ggml/src/ggml-cpu/CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -279,19 +279,15 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
endif()
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "ppc64")
message(STATUS "PowerPC detected")
execute_process(COMMAND bash -c "grep POWER10 /proc/cpuinfo | head -n 1" OUTPUT_VARIABLE POWER10_M)
string(FIND "${POWER10_M}" "POWER10" substring_index)
if (NOT DEFINED substring_index OR "${substring_index}" STREQUAL "")
set(substring_index -1)
endif()

if (${substring_index} GREATER_EQUAL 0)
list(APPEND ARCH_FLAGS -mcpu=power10)
execute_process(COMMAND bash -c "grep POWER /proc/cpuinfo | head -n 1" OUTPUT_VARIABLE POWER_M)
if (${POWER_M} MATCHES "POWER10")
list(APPEND ARCH_FLAGS -mcpu=power10)
elseif (${POWER_M} MATCHES "POWER9")
list(APPEND ARCH_FLAGS -mcpu=power9)
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "ppc64le")
list(APPEND ARCH_FLAGS -mcpu=powerpc64le)
list(APPEND ARCH_FLAGS -mcpu=powerpc64le -mtune=native)
else()
list(APPEND ARCH_FLAGS -mcpu=native -mtune=native)
# TODO: Add targets for Power8/Power9 (Altivec/VSX) and Power10(MMA) and query for big endian systems (ppc64/le/be)
list(APPEND ARCH_FLAGS -mcpu=powerpc64 -mtune=native)
endif()
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
message(STATUS "loongarch64 detected")
Expand Down
Loading