4x16 lane AArch64 NEON GEMM/IGEMM ld64 microkernel

PiperOrigin-RevId: 411642422
diff --git a/test/qs8-igemm-minmax-fp32.yaml b/test/qs8-igemm-minmax-fp32.yaml
index 8403032..c5cd1a0 100644
--- a/test/qs8-igemm-minmax-fp32.yaml
+++ b/test/qs8-igemm-minmax-fp32.yaml
@@ -144,6 +144,12 @@
 - name: xnn_qs8_igemm_minmax_fp32_ukernel_4x16__aarch64_neon_mlal_lane_cortex_a53
   init: xnn_init_qs8_conv_minmax_fp32_neonv8_params
   k-block: 8
+- name: xnn_qs8_igemm_minmax_fp32_ukernel_4x16__aarch64_neon_mlal_lane_prfm_ld64
+  init: xnn_init_qs8_conv_minmax_fp32_neonv8_params
+  k-block: 8
+- name: xnn_qs8_igemm_minmax_fp32_ukernel_4x16__aarch64_neon_mlal_lane_ld64
+  init: xnn_init_qs8_conv_minmax_fp32_neonv8_params
+  k-block: 8
 - name: xnn_qs8_igemm_minmax_fp32_ukernel_4x16c4__aarch64_neondot_cortex_a55
   init: xnn_init_qs8_conv_minmax_fp32_neonv8_params
   k-block: 16