notbugAs an Amazon Associate I earn from qualifying purchases.
Want a good read? Try FreeBSD Mastery: Jails (IT Mastery Book 15)
Want a good monitor light? See my photosAll times are UTC
Ukraine
2024-11-06 Today brought in a new category: filesystems. Sadly, the website did not process it well. I am working on that. It may take a few days.
2024-11-07 Commit processing is halted. I have a fix for the new category. It is making its way through the system.
UPDATE: the backend is processing the original filesystems commit now. It should take about an hour.
UPDATE: as of 20:30 UTC, the filesystems commit has been processed. Commit processing is now up to date.
Port details
libxsmm Library for dense and sparse matrix operations and deep learning
1.17_1 math on this many watch lists=2 search for ports that depend on this port Find issues related to this port Report an issue related to this port View this port on Repology. pkg-fallout 1.17_1Version of this port present on the latest quarterly branch.
Maintainer: yuri@FreeBSD.org search for ports maintained by this maintainer
Port Added: 2018-09-20 17:45:02
Last Update: 2023-04-23 09:09:58
Commit Hash: 8d3e020
People watching this port, also watch:: jdictionary, py311-Automat, py311-python-gdsii, py39-PyOpenGL, p5-Sane
Also Listed In: science
License: BSD3CLAUSE
WWW:
https://github.com/hfp/libxsmm
Description:
LIBXSMM is a library for specialized dense and sparse matrix operations as well as for deep learning primitives such as small convolutions targeting Intel Architecture. Small matrix multiplication kernels (SMMs) are generated for Intel SSE, Intel AVX, Intel AVX2, IMCI (KNCni) for Intel Xeon Phi coprocessors (KNC), and Intel AVX-512 as found in the Intel Xeon Phi processor family (KNL, KNM) and Intel Xeon processors (SKX). Highly optimized code for small convolutions is targeting Intel AVX2 and Intel AVX-512, whereas other targets can automatically leverage specialized SMMs to perform convolutions. The library supports statically generated code at configuration time (SMMs), uses optimized code paths based on compiler-generated code as well as Intrinsic functions, but mainly utilizes Just-In-Time (JIT) code specialization for compiler-independent performance (matrix multiplications, matrix transpose/copy, sparse functionality, and small convolutions). LIBXSMM is suitable for "build once and deploy everywhere" i.e., no special target flags are needed to exploit the available performance.
Homepage    cgit ¦ Codeberg ¦ GitHub ¦ GitLab ¦ SVNWeb

Manual pages:
FreshPorts has no man page information for this port.
pkg-plist: as obtained via: make generate-plist
Expand this list (335 items)
Collapse this list.
  1. @ldconfig
  2. /usr/local/share/licenses/libxsmm-1.17_1/catalog.mk
  3. /usr/local/share/licenses/libxsmm-1.17_1/LICENSE
  4. /usr/local/share/licenses/libxsmm-1.17_1/BSD3CLAUSE
  5. bin/libxsmm_gemm_generator
  6. include/libxsmm.f
  7. include/libxsmm.h
  8. include/libxsmm.mod
  9. include/libxsmm/generator_common.c
  10. include/libxsmm/generator_common.h
  11. include/libxsmm/generator_gemm.c
  12. include/libxsmm/generator_gemm_avx2_microkernel.c
  13. include/libxsmm/generator_gemm_avx2_microkernel.h
  14. include/libxsmm/generator_gemm_avx512_microkernel.c
  15. include/libxsmm/generator_gemm_avx512_microkernel.h
  16. include/libxsmm/generator_gemm_avx_microkernel.c
  17. include/libxsmm/generator_gemm_avx_microkernel.h
  18. include/libxsmm/generator_gemm_common.c
  19. include/libxsmm/generator_gemm_common.h
  20. include/libxsmm/generator_gemm_noarch.c
  21. include/libxsmm/generator_gemm_noarch.h
  22. include/libxsmm/generator_gemm_sse3_avx_avx2_avx512.c
  23. include/libxsmm/generator_gemm_sse3_avx_avx2_avx512.h
  24. include/libxsmm/generator_gemm_sse3_microkernel.c
  25. include/libxsmm/generator_gemm_sse3_microkernel.h
  26. include/libxsmm/generator_matcopy.c
  27. include/libxsmm/generator_matcopy_avx_avx512.c
  28. include/libxsmm/generator_matcopy_avx_avx512.h
  29. include/libxsmm/generator_mateltwise.c
  30. include/libxsmm/generator_mateltwise_avx_avx512.c
  31. include/libxsmm/generator_mateltwise_avx_avx512.h
  32. include/libxsmm/generator_packed.c
  33. include/libxsmm/generator_packed_aux.h
  34. include/libxsmm/generator_packed_gemm_ac_rm_avx_avx2_avx512.c
  35. include/libxsmm/generator_packed_gemm_ac_rm_avx_avx2_avx512.h
  36. include/libxsmm/generator_packed_gemm_avx_avx512.c
  37. include/libxsmm/generator_packed_gemm_avx_avx512.h
  38. include/libxsmm/generator_packed_gemm_bc_rm_avx_avx2_avx512.c
  39. include/libxsmm/generator_packed_gemm_bc_rm_avx_avx2_avx512.h
  40. include/libxsmm/generator_packed_gemmnn.h
  41. include/libxsmm/generator_packed_getrf_avx_avx512.c
  42. include/libxsmm/generator_packed_getrf_avx_avx512.h
  43. include/libxsmm/generator_packed_trmm_avx_avx512.c
  44. include/libxsmm/generator_packed_trmm_avx_avx512.h
  45. include/libxsmm/generator_packed_trsm_avx_avx512.c
  46. include/libxsmm/generator_packed_trsm_avx_avx512.h
  47. include/libxsmm/generator_packed_trsm_dmacros.h
  48. include/libxsmm/generator_packed_xct_avx2_lln.h
  49. include/libxsmm/generator_spgemm.c
  50. include/libxsmm/generator_spgemm_csc_asparse.c
  51. include/libxsmm/generator_spgemm_csc_asparse.h
  52. include/libxsmm/generator_spgemm_csc_bsparse.c
  53. include/libxsmm/generator_spgemm_csc_bsparse.h
  54. include/libxsmm/generator_spgemm_csc_bsparse_soa.c
  55. include/libxsmm/generator_spgemm_csc_bsparse_soa.h
  56. include/libxsmm/generator_spgemm_csc_csparse_soa.c
  57. include/libxsmm/generator_spgemm_csc_csparse_soa.h
  58. include/libxsmm/generator_spgemm_csc_reader.c
  59. include/libxsmm/generator_spgemm_csc_reader.h
  60. include/libxsmm/generator_spgemm_csr_asparse.c
  61. include/libxsmm/generator_spgemm_csr_asparse.h
  62. include/libxsmm/generator_spgemm_csr_asparse_reg.c
  63. include/libxsmm/generator_spgemm_csr_asparse_reg.h
  64. include/libxsmm/generator_spgemm_csr_asparse_soa.c
  65. include/libxsmm/generator_spgemm_csr_asparse_soa.h
  66. include/libxsmm/generator_spgemm_csr_bsparse_soa.c
  67. include/libxsmm/generator_spgemm_csr_bsparse_soa.h
  68. include/libxsmm/generator_spgemm_csr_reader.c
  69. include/libxsmm/generator_spgemm_csr_reader.h
  70. include/libxsmm/generator_transpose.c
  71. include/libxsmm/generator_transpose_avx_avx512.c
  72. include/libxsmm/generator_transpose_avx_avx512.h
  73. include/libxsmm/generator_x86_instructions.c
  74. include/libxsmm/generator_x86_instructions.h
  75. include/libxsmm/libxsmm_blocked_gemm.c
  76. include/libxsmm/libxsmm_blocked_gemm_types.h
  77. include/libxsmm/libxsmm_cpuid_x86.c
  78. include/libxsmm/libxsmm_diff.h
  79. include/libxsmm/libxsmm_dnn.c
  80. include/libxsmm/libxsmm_dnn_convolution.c
  81. include/libxsmm/libxsmm_dnn_convolution_backward.c
  82. include/libxsmm/libxsmm_dnn_convolution_backward.h
  83. include/libxsmm/libxsmm_dnn_convolution_forward.c
  84. include/libxsmm/libxsmm_dnn_convolution_forward.h
  85. include/libxsmm/libxsmm_dnn_convolution_weight_update.c
  86. include/libxsmm/libxsmm_dnn_convolution_weight_update.h
  87. include/libxsmm/libxsmm_dnn_elementwise.c
  88. include/libxsmm/libxsmm_dnn_elementwise.h
  89. include/libxsmm/libxsmm_dnn_fullyconnected.c
  90. include/libxsmm/libxsmm_dnn_fullyconnected_backward_weight_update.c
  91. include/libxsmm/libxsmm_dnn_fullyconnected_backward_weight_update.h
  92. include/libxsmm/libxsmm_dnn_fullyconnected_forward.c
  93. include/libxsmm/libxsmm_dnn_fullyconnected_forward.h
  94. include/libxsmm/libxsmm_dnn_fusedbatchnorm.c
  95. include/libxsmm/libxsmm_dnn_fusedbatchnorm_backward.c
  96. include/libxsmm/libxsmm_dnn_fusedbatchnorm_backward.h
  97. include/libxsmm/libxsmm_dnn_fusedbatchnorm_forward.c
  98. include/libxsmm/libxsmm_dnn_fusedbatchnorm_forward.h
  99. include/libxsmm/libxsmm_dnn_fusedgroupnorm.c
  100. include/libxsmm/libxsmm_dnn_fusedgroupnorm_backward.c
  101. include/libxsmm/libxsmm_dnn_fusedgroupnorm_backward.h
  102. include/libxsmm/libxsmm_dnn_fusedgroupnorm_forward.c
  103. include/libxsmm/libxsmm_dnn_fusedgroupnorm_forward.h
  104. include/libxsmm/libxsmm_dnn_optimizer.c
  105. include/libxsmm/libxsmm_dnn_optimizer_sgd.c
  106. include/libxsmm/libxsmm_dnn_optimizer_sgd.h
  107. include/libxsmm/libxsmm_dnn_pooling.c
  108. include/libxsmm/libxsmm_dnn_pooling_backward.c
  109. include/libxsmm/libxsmm_dnn_pooling_backward.h
  110. include/libxsmm/libxsmm_dnn_pooling_forward.c
  111. include/libxsmm/libxsmm_dnn_pooling_forward.h
  112. include/libxsmm/libxsmm_dnn_rnncell.c
  113. include/libxsmm/libxsmm_dnn_rnncell_backward_weight_update.c
  114. include/libxsmm/libxsmm_dnn_rnncell_backward_weight_update.h
  115. include/libxsmm/libxsmm_dnn_rnncell_forward.c
  116. include/libxsmm/libxsmm_dnn_rnncell_forward.h
  117. include/libxsmm/libxsmm_dnn_softmaxloss.c
  118. include/libxsmm/libxsmm_dnn_softmaxloss_backward.c
  119. include/libxsmm/libxsmm_dnn_softmaxloss_backward.h
  120. include/libxsmm/libxsmm_dnn_softmaxloss_forward.c
  121. include/libxsmm/libxsmm_dnn_softmaxloss_forward.h
  122. include/libxsmm/libxsmm_dnn_tensor.c
  123. include/libxsmm/libxsmm_ext.c
  124. include/libxsmm/libxsmm_ext.h
  125. include/libxsmm/libxsmm_ext_blocked_gemm.c
  126. include/libxsmm/libxsmm_ext_gemm.c
  127. include/libxsmm/libxsmm_ext_xcopy.c
  128. include/libxsmm/libxsmm_fsspmdm.c
  129. include/libxsmm/libxsmm_gemm.c
  130. include/libxsmm/libxsmm_gemm.h
  131. include/libxsmm/libxsmm_generator.c
  132. include/libxsmm/libxsmm_generator_gemm_driver.c
  133. include/libxsmm/libxsmm_hash.c
  134. include/libxsmm/libxsmm_hash.h
  135. include/libxsmm/libxsmm_main.c
  136. include/libxsmm/libxsmm_main.h
  137. include/libxsmm/libxsmm_malloc.c
  138. include/libxsmm/libxsmm_math.c
  139. include/libxsmm/libxsmm_memory.c
  140. include/libxsmm/libxsmm_mhd.c
  141. include/libxsmm/libxsmm_perf.c
  142. include/libxsmm/libxsmm_perf.h
  143. include/libxsmm/libxsmm_python.c
  144. include/libxsmm/libxsmm_rng.c
  145. include/libxsmm/libxsmm_spmdm.c
  146. include/libxsmm/libxsmm_spmdm_begin.h
  147. include/libxsmm/libxsmm_spmdm_begin_avx2.h
  148. include/libxsmm/libxsmm_spmdm_begin_avx512.h
  149. include/libxsmm/libxsmm_spmdm_end.h
  150. include/libxsmm/libxsmm_sync.c
  151. include/libxsmm/libxsmm_timer.c
  152. include/libxsmm/libxsmm_trace.c
  153. include/libxsmm/libxsmm_trace.h
  154. include/libxsmm/libxsmm_xcopy.c
  155. include/libxsmm/libxsmm_xcopy.h
  156. include/libxsmm/perf_jitdump.h
  157. include/libxsmm/template/libxsmm.f
  158. include/libxsmm/template/libxsmm.h
  159. include/libxsmm/template/libxsmm_blocked_gemm.tpl.c
  160. include/libxsmm/template/libxsmm_blocked_gemm_convert_b_to_a.tpl.c
  161. include/libxsmm/template/libxsmm_blocked_gemm_copyin_a.tpl.c
  162. include/libxsmm/template/libxsmm_blocked_gemm_copyin_b.tpl.c
  163. include/libxsmm/template/libxsmm_blocked_gemm_copyin_c.tpl.c
  164. include/libxsmm/template/libxsmm_blocked_gemm_copyout_c.tpl.c
  165. include/libxsmm/template/libxsmm_blocked_gemm_transpose_b.tpl.c
  166. include/libxsmm/template/libxsmm_config.h
  167. include/libxsmm/template/libxsmm_dnn_bf16_macros_define.tpl.c
  168. include/libxsmm/template/libxsmm_dnn_bf16_macros_undefine.tpl.c
  169. include/libxsmm/template/libxsmm_dnn_convolve_st_bwd_custom_custom_fallback_generic.tpl.c
  170. include/libxsmm/template/libxsmm_dnn_convolve_st_bwd_custom_custom_generic.tpl.c
  171. include/libxsmm/template/libxsmm_dnn_convolve_st_bwd_custom_custom_generic_bf16.tpl.c
  172. include/libxsmm/template/libxsmm_dnn_convolve_st_bwd_nhwc_custom-rsck_fallback_generic.tpl.c
  173. include/libxsmm/template/libxsmm_dnn_convolve_st_bwd_nhwc_custom-rsck_generic.tpl.c
  174. include/libxsmm/template/libxsmm_dnn_convolve_st_fwd_custom_custom_generic.tpl.c
  175. include/libxsmm/template/libxsmm_dnn_convolve_st_fwd_custom_custom_generic_bf16.tpl.c
  176. include/libxsmm/template/libxsmm_dnn_convolve_st_fwd_custom_custom_generic_i8i32.tpl.c
  177. include/libxsmm/template/libxsmm_dnn_convolve_st_fwd_custom_custom_generic_i8i8.tpl.c
  178. include/libxsmm/template/libxsmm_dnn_convolve_st_fwd_nhwc_custom-rsck_generic.tpl.c
  179. include/libxsmm/template/libxsmm_dnn_convolve_st_upd_custom_custom_generic.tpl.c
  180. include/libxsmm/template/libxsmm_dnn_convolve_st_upd_custom_custom_generic_bf16.tpl.c
  181. include/libxsmm/template/libxsmm_dnn_convolve_st_upd_nhwc_custom-rsck_generic.tpl.c
  182. include/libxsmm/template/libxsmm_dnn_fullyconnected_st_bwdupd_custom_generic.tpl.c
  183. include/libxsmm/template/libxsmm_dnn_fullyconnected_st_bwdupd_ncnc_kcck_generic.tpl.c
  184. include/libxsmm/template/libxsmm_dnn_fullyconnected_st_bwdupd_ncnc_kcck_generic_bf16.tpl.c
  185. include/libxsmm/template/libxsmm_dnn_fullyconnected_st_fwd_custom_generic.tpl.c
  186. include/libxsmm/template/libxsmm_dnn_fullyconnected_st_fwd_ncnc_kcck_generic.tpl.c
  187. include/libxsmm/template/libxsmm_dnn_fullyconnected_st_fwd_ncnc_kcck_generic_bf16.tpl.c
  188. include/libxsmm/template/libxsmm_dnn_fusedbatchnorm_st_bwd_custom_f32_bf16_c16_avx512.tpl.c
  189. include/libxsmm/template/libxsmm_dnn_fusedbatchnorm_st_bwd_custom_f32_bf16_c32_avx512.tpl.c
  190. include/libxsmm/template/libxsmm_dnn_fusedbatchnorm_st_bwd_custom_f32_bf16_c64_avx512.tpl.c
  191. include/libxsmm/template/libxsmm_dnn_fusedbatchnorm_st_bwd_custom_generic.tpl.c
  192. include/libxsmm/template/libxsmm_dnn_fusedbatchnorm_st_fwd_custom_f32_bf16_c16_avx512.tpl.c
  193. include/libxsmm/template/libxsmm_dnn_fusedbatchnorm_st_fwd_custom_f32_bf16_c32_avx512.tpl.c
  194. include/libxsmm/template/libxsmm_dnn_fusedbatchnorm_st_fwd_custom_f32_bf16_c64_avx512.tpl.c
  195. include/libxsmm/template/libxsmm_dnn_fusedbatchnorm_st_fwd_custom_generic.tpl.c
  196. include/libxsmm/template/libxsmm_dnn_fusedgroupnorm_st_bwd_custom_f32_bf16_c16_avx512.tpl.c
  197. include/libxsmm/template/libxsmm_dnn_fusedgroupnorm_st_bwd_custom_f32_bf16_c32_avx512.tpl.c
  198. include/libxsmm/template/libxsmm_dnn_fusedgroupnorm_st_bwd_custom_f32_bf16_c64_avx512.tpl.c
  199. include/libxsmm/template/libxsmm_dnn_fusedgroupnorm_st_bwd_custom_generic.tpl.c
  200. include/libxsmm/template/libxsmm_dnn_fusedgroupnorm_st_fwd_custom_f32_bf16_c16_avx512.tpl.c
  201. include/libxsmm/template/libxsmm_dnn_fusedgroupnorm_st_fwd_custom_f32_bf16_c32_avx512.tpl.c
  202. include/libxsmm/template/libxsmm_dnn_fusedgroupnorm_st_fwd_custom_f32_bf16_c64_avx512.tpl.c
  203. include/libxsmm/template/libxsmm_dnn_fusedgroupnorm_st_fwd_custom_generic.tpl.c
  204. include/libxsmm/template/libxsmm_dnn_optimizer_sgd_st_generic.tpl.c
  205. include/libxsmm/template/libxsmm_dnn_pooling_st_bwd_custom_f32_bf16_c16_avx512.tpl.c
  206. include/libxsmm/template/libxsmm_dnn_pooling_st_bwd_custom_f32_bf16_c32_avx512.tpl.c
  207. include/libxsmm/template/libxsmm_dnn_pooling_st_bwd_custom_f32_bf16_c64_avx512.tpl.c
  208. include/libxsmm/template/libxsmm_dnn_pooling_st_bwd_custom_generic.tpl.c
  209. include/libxsmm/template/libxsmm_dnn_pooling_st_fwd_custom_f32_bf16_c16_avx512.tpl.c
  210. include/libxsmm/template/libxsmm_dnn_pooling_st_fwd_custom_f32_bf16_c32_avx512.tpl.c
  211. include/libxsmm/template/libxsmm_dnn_pooling_st_fwd_custom_f32_bf16_c64_avx512.tpl.c
  212. include/libxsmm/template/libxsmm_dnn_pooling_st_fwd_custom_generic.tpl.c
  213. include/libxsmm/template/libxsmm_dnn_rnncell_st_gru_bwdupd_nc_ck_generic.tpl.c
  214. include/libxsmm/template/libxsmm_dnn_rnncell_st_gru_bwdupd_nc_kcck.tpl.c
  215. include/libxsmm/template/libxsmm_dnn_rnncell_st_gru_fwd_nc_ck_generic.tpl.c
  216. include/libxsmm/template/libxsmm_dnn_rnncell_st_gru_fwd_nc_kcck.tpl.c
  217. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_bwdupd_nc_ck_generic.tpl.c
  218. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_bwdupd_nc_ck_generic_bf16.tpl.c
  219. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_bwdupd_nc_kcck.tpl.c
  220. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_bwdupd_nc_kcck_bf16.tpl.c
  221. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_bwdupd_nc_kcck_core.tpl.c
  222. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_bwdupd_nc_kcck_core_bf16.tpl.c
  223. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_fwd_nc_ck_generic.tpl.c
  224. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_fwd_nc_ck_generic_bf16.tpl.c
  225. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_fwd_nc_kcck.tpl.c
  226. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_fwd_nc_kcck_bf16.tpl.c
  227. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_fwd_nc_kcck_diffused.tpl.c
  228. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_fwd_nc_kcck_diffused_bf16.tpl.c
  229. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_fwd_nc_kcck_fused.tpl.c
  230. include/libxsmm/template/libxsmm_dnn_rnncell_st_lstm_fwd_nc_kcck_fused_bf16.tpl.c
  231. include/libxsmm/template/libxsmm_dnn_rnncell_st_rnn_bwdupd_nc_ck_generic.tpl.c
  232. include/libxsmm/template/libxsmm_dnn_rnncell_st_rnn_bwdupd_nc_kcck.tpl.c
  233. include/libxsmm/template/libxsmm_dnn_rnncell_st_rnn_fwd_nc_ck_generic.tpl.c
  234. include/libxsmm/template/libxsmm_dnn_rnncell_st_rnn_fwd_nc_kcck.tpl.c
  235. include/libxsmm/template/libxsmm_dnn_rnncell_st_rnn_fwd_ncnc_kcck.tpl.c
  236. include/libxsmm/template/libxsmm_dnn_softmaxloss_st_bwd_ncnc_generic.tpl.c
  237. include/libxsmm/template/libxsmm_dnn_softmaxloss_st_fwd_ncnc_generic.tpl.c
  238. include/libxsmm/template/libxsmm_dnn_tensor_bias_copy_in_nchw.tpl.c
  239. include/libxsmm/template/libxsmm_dnn_tensor_bias_copy_out_nchw.tpl.c
  240. include/libxsmm/template/libxsmm_dnn_tensor_buffer_copy_in_nchw.tpl.c
  241. include/libxsmm/template/libxsmm_dnn_tensor_buffer_copy_out_nchw.tpl.c
  242. include/libxsmm/template/libxsmm_dnn_tensor_filter_copy_in_kcrs.tpl.c
  243. include/libxsmm/template/libxsmm_dnn_tensor_filter_copy_out_kcrs.tpl.c
  244. include/libxsmm/template/libxsmm_dnn_zero_rim_st_input_custom.tpl.c
  245. include/libxsmm/template/libxsmm_dnn_zero_rim_st_input_nhwc.tpl.c
  246. include/libxsmm/template/libxsmm_internal_gru_bwdupd_fused_eltwise_1.tpl.c
  247. include/libxsmm/template/libxsmm_internal_gru_bwdupd_fused_eltwise_2.tpl.c
  248. include/libxsmm/template/libxsmm_internal_lstm_bwdupd_fused_eltwise.tpl.c
  249. include/libxsmm/template/libxsmm_internal_lstm_bwdupd_fused_eltwise_reformat.tpl.c
  250. include/libxsmm/template/libxsmm_internal_lstm_bwdupd_fused_eltwise_reformat_bf16.tpl.c
  251. include/libxsmm/template/libxsmm_internal_lstm_fwd_fused_eltwise.tpl.c
  252. include/libxsmm/template/libxsmm_internal_lstm_fwd_fused_eltwise_bf16.tpl.c
  253. include/libxsmm/template/libxsmm_matdiff.tpl.c
  254. include/libxsmm/template/libxsmm_spmdm_compute_bfloat16_thread.tpl.c
  255. include/libxsmm/template/libxsmm_spmdm_compute_fp32_thread.tpl.c
  256. include/libxsmm/template/libxsmm_spmdm_createSparseSlice_bfloat16_thread.tpl.c
  257. include/libxsmm/template/libxsmm_spmdm_createSparseSlice_fp32_thread.tpl.c
  258. include/libxsmm/template/libxsmm_version.h
  259. include/libxsmm/template/transpose.tpl.c
  260. include/libxsmm_blocked_gemm.h
  261. include/libxsmm_config.h
  262. include/libxsmm_cpuid.h
  263. include/libxsmm_dnn.h
  264. include/libxsmm_dnn_convolution.h
  265. include/libxsmm_dnn_fullyconnected.h
  266. include/libxsmm_dnn_fusedbatchnorm.h
  267. include/libxsmm_dnn_fusedgroupnorm.h
  268. include/libxsmm_dnn_optimizer.h
  269. include/libxsmm_dnn_pooling.h
  270. include/libxsmm_dnn_rnncell.h
  271. include/libxsmm_dnn_softmaxloss.h
  272. include/libxsmm_dnn_tensor.h
  273. include/libxsmm_frontend.h
  274. include/libxsmm_fsspmdm.h
  275. include/libxsmm_generator.h
  276. include/libxsmm_intrinsics_x86.h
  277. include/libxsmm_macros.h
  278. include/libxsmm_malloc.h
  279. include/libxsmm_math.h
  280. include/libxsmm_memory.h
  281. include/libxsmm_mhd.h
  282. include/libxsmm_rng.h
  283. include/libxsmm_source.h
  284. include/libxsmm_spmdm.h
  285. include/libxsmm_sync.h
  286. include/libxsmm_timer.h
  287. include/libxsmm_typedefs.h
  288. include/libxsmm_version.h
  289. lib/libxsmm.so
  290. lib/libxsmm.so.1
  291. lib/libxsmm.so.1.17.0
  292. lib/libxsmmext.so
  293. lib/libxsmmext.so.1
  294. lib/libxsmmext.so.1.17.0
  295. lib/libxsmmf.so
  296. lib/libxsmmf.so.1
  297. lib/libxsmmf.so.1.17.0
  298. lib/libxsmmgen.so
  299. lib/libxsmmgen.so.1
  300. lib/libxsmmgen.so.1.17.0
  301. lib/libxsmmnoblas.so
  302. lib/libxsmmnoblas.so.1
  303. lib/libxsmmnoblas.so.1.17.0
  304. libdata/pkgconfig/libxsmm.pc
  305. libdata/pkgconfig/libxsmmext.pc
  306. libdata/pkgconfig/libxsmmf.pc
  307. libdata/pkgconfig/libxsmmnoblas.pc
  308. share/libxsmm/CONTRIBUTING.md
  309. share/libxsmm/LICENSE.md
  310. share/libxsmm/README.md
  311. share/libxsmm/SECURITY.md
  312. share/libxsmm/build.txt
  313. share/libxsmm/cp2k.md
  314. share/libxsmm/gxm.md
  315. share/libxsmm/index.md
  316. share/libxsmm/libxsmm.env
  317. share/libxsmm/libxsmm.pdf
  318. share/libxsmm/libxsmm_aux.md
  319. share/libxsmm/libxsmm_be.md
  320. share/libxsmm/libxsmm_compat.md
  321. share/libxsmm/libxsmm_dl.md
  322. share/libxsmm/libxsmm_fortran.md
  323. share/libxsmm/libxsmm_mm.md
  324. share/libxsmm/libxsmm_prof.md
  325. share/libxsmm/libxsmm_qna.md
  326. share/libxsmm/libxsmm_samples.md
  327. share/libxsmm/libxsmm_samples.pdf
  328. share/libxsmm/libxsmm_tune.md
  329. share/libxsmm/libxsmm_valid.md
  330. share/libxsmm/tensorflow.md
  331. share/libxsmm/tensorflow.pdf
  332. share/libxsmm/version.txt
  333. @owner
  334. @group
  335. @mode
Collapse this list.
Dependency lines:
  • libxsmm>0:math/libxsmm
To install the port:
cd /usr/ports/math/libxsmm/ && make install clean
To add the package, run one of these commands:
  • pkg install math/libxsmm
  • pkg install libxsmm
NOTE: If this package has multiple flavors (see below), then use one of them instead of the name specified above.
PKGNAME: libxsmm
Flavors: there is no flavor information for this port.
distinfo:
TIMESTAMP = 1657690125 SHA256 (hfp-libxsmm-1.17_GH0.tar.gz) = 8b642127880e92e8a75400125307724635ecdf4020ca4481e5efe7640451bb92 SIZE (hfp-libxsmm-1.17_GH0.tar.gz) = 2528419

Packages (timestamps in pop-ups are UTC):
libxsmm
ABIaarch64amd64armv6armv7i386powerpcpowerpc64powerpc64le
FreeBSD:13:latest-1.17_1-1.17_1----
FreeBSD:13:quarterly-1.17_1-1.17_1--1.17_11.17_1
FreeBSD:14:latest-1.17_1-1.17_1----
FreeBSD:14:quarterly-1.17_1-1.17_1--1.17_11.17_1
FreeBSD:15:latest-1.17_1n/a1.17_1n/a-1.17_11.17_1
Dependencies
NOTE: FreshPorts displays only information on required and default dependencies. Optional dependencies are not covered.
Build dependencies:
  1. bash : shells/bash
  2. gfortran12 : lang/gcc12
  3. gmake>=4.3 : devel/gmake
  4. python3.9 : lang/python39
  5. as : devel/binutils
Runtime dependencies:
  1. gfortran12 : lang/gcc12
This port is required by:
for Run
  1. science/py-PyFR

Configuration Options:
No options to configure
Options name:
math_libxsmm
USES:
cpe fortran gmake localbase:ldflags python:build shebangfix
FreshPorts was unable to extract/find any pkg message
Master Sites:
Expand this list (1 items)
Collapse this list.
  1. https://codeload.github.com/hfp/libxsmm/tar.gz/1.17?dummy=/
Collapse this list.

Number of commits found: 22

Commit History - (may be incomplete: for full details, see links to repositories near top of page)
CommitCreditsLog message
1.17_1
23 Apr 2023 09:09:58
commit hash: 8d3e020ed032a8db00208994d0db646de7dc6f5bcommit hash: 8d3e020ed032a8db00208994d0db646de7dc6f5bcommit hash: 8d3e020ed032a8db00208994d0db646de7dc6f5bcommit hash: 8d3e020ed032a8db00208994d0db646de7dc6f5b files touched by this commit
Gerald Pfeifer (gerald) search for other commits by this committer
*: Bump PORTREVISIONs for math/mpc update to 1.3.1
07 Sep 2022 21:58:51
commit hash: fb16dfecae4a6efac9f3a78e0b759fb7a3c53de4commit hash: fb16dfecae4a6efac9f3a78e0b759fb7a3c53de4commit hash: fb16dfecae4a6efac9f3a78e0b759fb7a3c53de4commit hash: fb16dfecae4a6efac9f3a78e0b759fb7a3c53de4 files touched by this commit
Stefan Eßer (se) search for other commits by this committer
Remove WWW entries moved into port Makefiles

Commit b7f05445c00f has added WWW entries to port Makefiles based on
WWW: lines in pkg-descr files.

This commit removes the WWW: lines of moved-over URLs from these
pkg-descr files.

Approved by:		portmgr (tcberner)
1.17
07 Sep 2022 21:10:59
commit hash: b7f05445c00f2625aa19b4154ebcbce5ed2daa52commit hash: b7f05445c00f2625aa19b4154ebcbce5ed2daa52commit hash: b7f05445c00f2625aa19b4154ebcbce5ed2daa52commit hash: b7f05445c00f2625aa19b4154ebcbce5ed2daa52 files touched by this commit
Stefan Eßer (se) search for other commits by this committer
Add WWW entries to port Makefiles

It has been common practice to have one or more URLs at the end of the
ports' pkg-descr files, one per line and prefixed with "WWW:". These
URLs should point at a project website or other relevant resources.

Access to these URLs required processing of the pkg-descr files, and
they have often become stale over time. If more than one such URL was
present in a pkg-descr file, only the first one was tarnsfered into
the port INDEX, but for many ports only the last line did contain the
port specific URL to further information.

There have been several proposals to make a project URL available as
a macro in the ports' Makefiles, over time.
(Only the first 15 lines of the commit message are shown above View all of this commit message)
1.17
14 Jul 2022 18:41:35
commit hash: f5b6d4a7c866e7c94167c77ff3eabe77a72e7d34commit hash: f5b6d4a7c866e7c94167c77ff3eabe77a72e7d34commit hash: f5b6d4a7c866e7c94167c77ff3eabe77a72e7d34commit hash: f5b6d4a7c866e7c94167c77ff3eabe77a72e7d34 files touched by this commit
Yuri Victorovich (yuri) search for other commits by this committer
math/libxsmm: Broken on arm64

Reported by:	fallout
1.17
13 Jul 2022 05:45:37
commit hash: 581d55bb174297d34146368e5bb5cfea4d5e6bbecommit hash: 581d55bb174297d34146368e5bb5cfea4d5e6bbecommit hash: 581d55bb174297d34146368e5bb5cfea4d5e6bbecommit hash: 581d55bb174297d34146368e5bb5cfea4d5e6bbe files touched by this commit
Yuri Victorovich (yuri) search for other commits by this committer
math/libxsmm: Update 1.16.3 -> 1.17
1.16.3
20 Jan 2022 07:21:41
commit hash: 2195fb882f0369663ab7d7ce8a2ecd81f20be474commit hash: 2195fb882f0369663ab7d7ce8a2ecd81f20be474commit hash: 2195fb882f0369663ab7d7ce8a2ecd81f20be474commit hash: 2195fb882f0369663ab7d7ce8a2ecd81f20be474 files touched by this commit
Yuri Victorovich (yuri) search for other commits by this committer
math/libxsmm: Broken on i386

Reported by:	fallout
1.16.3
25 Nov 2021 16:25:59
commit hash: 08c6efbca1c4266eb9403f366ddf0022268dd9b3commit hash: 08c6efbca1c4266eb9403f366ddf0022268dd9b3commit hash: 08c6efbca1c4266eb9403f366ddf0022268dd9b3commit hash: 08c6efbca1c4266eb9403f366ddf0022268dd9b3 files touched by this commit
Piotr Kubaj (pkubaj) search for other commits by this committer
math/libxsmm: fix build on non-amd64

On non-amd64, PLATFORM=1 needs to be passed to disable JIT.

Also, add a way to read TBR that does not depend on glibc.
1.16.3
22 Oct 2021 08:57:01
commit hash: 53ae6828fadc03e5da3d2a22c8ca791772274b3bcommit hash: 53ae6828fadc03e5da3d2a22c8ca791772274b3bcommit hash: 53ae6828fadc03e5da3d2a22c8ca791772274b3bcommit hash: 53ae6828fadc03e5da3d2a22c8ca791772274b3b files touched by this commit
Yuri Victorovich (yuri) search for other commits by this committer
math/libxsmm: Update 1.16.1 -> 1.16.3; Add the 'test' target

Reported by:	portscout
1.16.1
19 Oct 2021 11:14:36
commit hash: de6bda1fc056c52b0c0bc51a7a2baa2caa50b0b4commit hash: de6bda1fc056c52b0c0bc51a7a2baa2caa50b0b4commit hash: de6bda1fc056c52b0c0bc51a7a2baa2caa50b0b4commit hash: de6bda1fc056c52b0c0bc51a7a2baa2caa50b0b4 files touched by this commit
Stefan Eßer (se) search for other commits by this committer
math/libxsmm: Add CPE information

Approved by:	portmgr (blanket)
1.16.1
07 Apr 2021 08:09:01
commit hash: cf118ccf875508b9a1c570044c93cfcc82bd455ccommit hash: cf118ccf875508b9a1c570044c93cfcc82bd455ccommit hash: cf118ccf875508b9a1c570044c93cfcc82bd455ccommit hash: cf118ccf875508b9a1c570044c93cfcc82bd455c files touched by this commit
Mathieu Arnold (mat) search for other commits by this committer
One more small cleanup, forgotten yesterday.
Reported by:	lwhsu
1.16.1
06 Apr 2021 14:31:07
commit hash: 305f148f482daf30dcf728039d03d019f88344ebcommit hash: 305f148f482daf30dcf728039d03d019f88344ebcommit hash: 305f148f482daf30dcf728039d03d019f88344ebcommit hash: 305f148f482daf30dcf728039d03d019f88344eb files touched by this commit
Mathieu Arnold (mat) search for other commits by this committer
Remove # $FreeBSD$ from Makefiles.
1.16.1
21 Sep 2020 17:19:26
Revision:549464Original commit files touched by this commit
yuri search for other commits by this committer
math/libxsmm: Update 1.10 -> 1.16.1
1.10_6
08 Mar 2020 21:56:37
Revision:528082Original commit files touched by this commit
jbeich search for other commits by this committer
Drop dependency on devel/openmp

- Drop if devel/llvm* was used as a substitute

Approved by:	yuri, rene (earlier version)
Differential Revision:	https://reviews.freebsd.org/D23020
1.10_5
21 Sep 2019 18:59:57
Revision:512535Original commit files touched by this commit
jbeich search for other commits by this committer
devel/openmp: update to 9.0.0

- Connect tests to the framework to help QA remaining patches
- Force rebuild all consumers after https://reviews.llvm.org/D59783

Changes:	http://llvm.org/viewvc/llvm-project/openmp/tags/RELEASE_900/final/?view=log
ABI:		https://abi-laboratory.pro/tracker/timeline/llvm_openmp/
1.10_4
26 Jul 2019 20:46:57
Revision:507372Original commit files touched by this commit
gerald search for other commits by this committer
Bump PORTREVISION for ports depending on the canonical version of GCC
as defined in Mk/bsd.default-versions.mk which has moved from GCC 8.3
to GCC 9.1 under most circumstances now after revision 507371.

This includes ports
 - with USE_GCC=yes or USE_GCC=any,
 - with USES=fortran,
 - using Mk/bsd.octave.mk which in turn features USES=fortran, and
 - with USES=compiler specifying openmp, nestedfct, c11, c++0x, c++11-lang,
   c++11-lib, c++14-lang, c++17-lang, or gcc-c++11-lib
plus, everything INDEX-11 shows with a dependency on lang/gcc9 now.

PR:		238330
1.10_3
21 Jun 2019 11:56:52
Revision:504790Original commit files touched by this commit
linimon search for other commits by this committer
Switch to ONLY_FOR_ARCHS=amd64.

This port does not build on e.g. powerpc64 due to hardwired assumptions
about x86 e.g. in the unconditionally-built src/libxsmm_cpuid_x86.c.

Previously it had been marked BROKEN on i386 since it requires 64-bit.
So, the easiest thing to do in this case is mark it amd64-only.

Approved by:	portmgr (tier-2 blanket)
1.10_3
08 May 2019 16:05:53
Revision:501030Original commit files touched by this commit
jbeich search for other commits by this committer
devel/openmp: phase out

- Expire after the last version without /usr/lib/libomp.so
- Drop SOVERSION for seamless transition (i.e., avoid conditionals)

PR:		236907
Approved by:	bapt (maintainer)
Differential Revision:	https://reviews.freebsd.org/D19767
1.10_2
22 Apr 2019 13:16:34
Revision:499638Original commit files touched by this commit
gerald search for other commits by this committer
Related to revision 499061 bump ports with USES=fortran to have them
benefit from the improved situation where libgcc_s is only used when
absolutely necessary.

Suggested by:	tijl
1.10_1
05 Jan 2019 14:46:04
Revision:489345Original commit files touched by this commit
antoine search for other commits by this committer
Fix plist
1.10_1
12 Dec 2018 01:35:36
Revision:487272Original commit files touched by this commit
gerald search for other commits by this committer
Bump PORTREVISION for ports depending on the canonical version of GCC
defined via Mk/bsd.default-versions.mk which has moved from GCC 7.4 t
GCC 8.2 under most circumstances.

This includes ports
 - with USE_GCC=yes or USE_GCC=any,
 - with USES=fortran,
 - using Mk/bsd.octave.mk which in turn features USES=fortran, and
 - with USES=compiler specifying openmp, nestedfct, c11, c++0x, c++11-lang,
   c++11-lib, c++14-lang, c++17-lang, or gcc-c++11-lib
plus, as a double check, everything INDEX-11 showed depending on lang/gcc7.

PR:		231590
1.10
15 Nov 2018 04:23:39
Revision:485001Original commit files touched by this commit
yuri search for other commits by this committer
math/libxsmm: Update 1.9 -> 1.10

Bump science/py-PyFR due to the extensive headers change in math/libxsmm.
1.9
20 Sep 2018 17:44:47
Revision:480184Original commit files touched by this commit
yuri search for other commits by this committer
New port: math/libxsmm: Library for dense and sparse matrix operations and deep
learning

Number of commits found: 22