kleidiai: Add SME vs SME2 distinction in kernel dispatch (#25478)

The current integration treats SME as a single capability (CPU_FEATURE_SME)
with no distinction between SME(v1) and SME2. The kernels dispatched under
CPU_FEATURE_SME use SME2-specific instructions, making dispatch incorrect
on SME(v1)-only hardware.

We introduce build-time and runtime distinction between SME and SME2, and
wire SME(v1) and SME2 kernels based on actual hardware support.
This commit is contained in:
Rajendra Matcha
2026-07-16 08:57:04 -07:00
committed by GitHub
parent b15ca938ad
commit f15bd60901
8 changed files with 178 additions and 13 deletions
+16 -2
View File
@@ -678,7 +678,18 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
endif()
if (NOT SME_ENABLED MATCHES -1)
list(APPEND GGML_KLEIDIAI_SOURCES
list(APPEND GGML_KLEIDIAI_SME_SOURCES
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_qai8dxp_qsi8cxp/kai_matmul_clamp_f32_qai8dxp1vlx4_qsi8cxp4vlx4_1vlx4vl_sme_mopa.c
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_qai8dxp_qsi8cxp/kai_matmul_clamp_f32_qai8dxp1vlx4_qsi8cxp4vlx4_1vlx4vl_sme_mopa_asm.S
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_qai8dxp_qsi8cxp/kai_matmul_clamp_f32_qai8dxp1x4_qsi8cxp4vlx4_1x4vl_sme_dot.c
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_qai8dxp_qsi8cxp/kai_matmul_clamp_f32_qai8dxp1x4_qsi8cxp4vlx4_1x4vl_sme_dot_asm.S
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_f32p_f32p/kai_matmul_clamp_f32_f32p2vlx1_f32p2vlx1b_2vlx2vl_sme_mopa.c
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_f32p_f32p/kai_matmul_clamp_f32_f32p2vlx1_f32p2vlx1b_2vlx2vl_sme_mopa_asm.S)
set_source_files_properties(${GGML_KLEIDIAI_SME_SOURCES}
PROPERTIES COMPILE_OPTIONS "-fno-tree-vectorize;${ARCH_FLAGS_TEMP}+sve+sve2+sme")
list(APPEND GGML_CPU_SOURCES ${GGML_KLEIDIAI_SME_SOURCES})
list(APPEND GGML_KLEIDIAI_SME2_SOURCES
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p1x4_qsi4c32p4vlx4_1x4vl_sme2_sdot.c
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_qai8dxp_qsi8cxp/kai_matmul_clamp_f32_qai8dxp1vlx4_qsi8cxp4vlx4_1vlx4vl_sme2_mopa.c
${KLEIDIAI_SRC}/kai/ukernels/matmul/matmul_clamp_f32_qai8dxp_qsi8cxp/kai_matmul_clamp_f32_qai8dxp1vlx4_qsi8cxp4vlx4_1vlx4vl_sme2_mopa_asm.S
@@ -698,7 +709,10 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_f32p2vlx1biasf32_f32_f32_sme.c
${KLEIDIAI_SRC}/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_f32p2vlx1biasf32_f32_f32_sme_asm.S
${KLEIDIAI_SRC}/kai/kai_common_sme_asm.S)
set(PRIVATE_ARCH_FLAGS "-fno-tree-vectorize;${PRIVATE_ARCH_FLAGS}+sve+sve2+sme2+fp16")
set_source_files_properties(${GGML_KLEIDIAI_SME2_SOURCES}
PROPERTIES COMPILE_OPTIONS "-fno-tree-vectorize;${ARCH_FLAGS_TEMP}+sve+sve2+sme2+fp16")
list(APPEND GGML_CPU_SOURCES ${GGML_KLEIDIAI_SME2_SOURCES})
set(PRIVATE_ARCH_FLAGS "-fno-tree-vectorize;${PRIVATE_ARCH_FLAGS}")
endif()
if (NOT SVE_ENABLED MATCHES -1)