FrozenGene commented on a change in pull request #6117:
URL: https://github.com/apache/incubator-tvm/pull/6117#discussion_r477065824
##########
File path: python/tvm/topi/arm_cpu/tensor_intrin.py
##########
@@ -21,7 +21,186 @@
from tvm import te
from tvm.contrib import util, clang
-def gemv_quantized_impl(M, N, data_type='uint8'):
+def gemm_quantized_4_4_batched():
+ return """
+ // First half
+ // Higher part of a0 * {b0,b1,b2,b3}
+ "umull v8.8h, v0.8b, v4.8b\\n"
+ "umull v9.8h, v0.8b, v5.8b\\n"
+ "umull v10.8h, v0.8b, v6.8b\\n"
+ "umull v11.8h, v0.8b, v7.8b\\n"
+
+ // Higher part of a1 * {b0,b1,b2,b3}
+ "umull v12.8h, v1.8b, v4.8b\\n"
+ "umull v13.8h, v1.8b, v5.8b\\n"
+ "umull v14.8h, v1.8b, v6.8b\\n"
+ "umull v15.8h, v1.8b, v7.8b\\n"
+
+ // Accumulate
+ "uadalp v16.4s, v8.8h\\n"
+ "uadalp v17.4s, v9.8h\\n"
+ "uadalp v18.4s, v10.8h\\n"
+ "uadalp v19.4s, v11.8h\\n"
+ "uadalp v20.4s, v12.8h\\n"
+ "uadalp v21.4s, v13.8h\\n"
+ "uadalp v22.4s, v14.8h\\n"
+ "uadalp v23.4s, v15.8h\\n"
+
+ // Lower part of a0 * {b0,b1,b2,b3}
+ "umull2 v8.8h, v0.16b, v4.16b\\n"
+ "umull2 v9.8h, v0.16b, v5.16b\\n"
+ "umull2 v10.8h, v0.16b, v6.16b\\n"
+ "umull2 v11.8h, v0.16b, v7.16b\\n"
+
+ // Lower part of a1 * {b0,b1,b2,b3}
+ "umull2 v12.8h, v1.16b, v4.16b\\n"
+ "umull2 v13.8h, v1.16b, v5.16b\\n"
+ "umull2 v14.8h, v1.16b, v6.16b\\n"
+ "umull2 v15.8h, v1.16b, v7.16b\\n"
+
+ // Accumulate again
+ "uadalp v16.4s, v8.8h\\n"
+ "uadalp v17.4s, v9.8h\\n"
+ "uadalp v18.4s, v10.8h\\n"
+ "uadalp v19.4s, v11.8h\\n"
+ "uadalp v20.4s, v12.8h\\n"
+ "uadalp v21.4s, v13.8h\\n"
+ "uadalp v22.4s, v14.8h\\n"
+ "uadalp v23.4s, v15.8h\\n"
+
+ // Second half
+ // Lower part of a2 * {b0,b1,b2,b3}
+ "umull v8.8h, v2.8b, v4.8b\\n"
+ "umull v9.8h, v2.8b, v5.8b\\n"
+ "umull v10.8h, v2.8b, v6.8b\\n"
+ "umull v11.8h, v2.8b, v7.8b\\n"
+
+ // Lower part of a3 * {b0,b1,b2,b3}
+ "umull v12.8h, v3.8b, v4.8b\\n"
+ "umull v13.8h, v3.8b, v5.8b\\n"
+ "umull v14.8h, v3.8b, v6.8b\\n"
+ "umull v15.8h, v3.8b, v7.8b\\n"
+
+ // Accumulate
+ "uadalp v24.4s, v8.8h\\n"
+ "uadalp v25.4s, v9.8h\\n"
+ "uadalp v26.4s, v10.8h\\n"
+ "uadalp v27.4s, v11.8h\\n"
+ "uadalp v28.4s, v12.8h\\n"
+ "uadalp v29.4s, v13.8h\\n"
+ "uadalp v30.4s, v14.8h\\n"
+ "uadalp v31.4s, v15.8h\\n"
+
+ // Higher part of a2 * {b0,b1,b2,b3}
+ "umull2 v8.8h, v2.16b, v4.16b\\n"
+ "umull2 v9.8h, v2.16b, v5.16b\\n"
+ "umull2 v10.8h, v2.16b, v6.16b\\n"
+ "umull2 v11.8h, v2.16b, v7.16b\\n"
+
+ // Higher part of a3 * {b0,b1,b2,b3}
+ "umull2 v12.8h, v3.16b, v4.16b\\n"
+ "umull2 v13.8h, v3.16b, v5.16b\\n"
+ "umull2 v14.8h, v3.16b, v6.16b\\n"
+ "umull2 v15.8h, v3.16b, v7.16b\\n"
+
+ // Accumulate again
+ "uadalp v24.4s, v8.8h\\n"
+ "uadalp v25.4s, v9.8h\\n"
+ "uadalp v26.4s, v10.8h\\n"
+ "uadalp v27.4s, v11.8h\\n"
+ "uadalp v28.4s, v12.8h\\n"
+ "uadalp v29.4s, v13.8h\\n"
+ "uadalp v30.4s, v14.8h\\n"
+ "uadalp v31.4s, v15.8h\\n"
+ """
+
+def gemm_quantized_4_4_interleaved():
Review comment:
Ignore. I find it out and this is guarded in the `is_aarch64_arm`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
