From 98452b740669d8f7644f41f1e4a01747bb55e907 Mon Sep 17 00:00:00 2001 From: Edward Swarthout Date: Sat, 8 Feb 2020 12:53:07 -0600 Subject: [PATCH] QNNPACK: q8gemm/8x8-dq-aarch64-neon.S fix mov operand for gcc Unlike glang, GNU assembler does not support 4s on neon mov, so use 16b. Fixes: 8x8-dq-aarch64-neon.S: Assembler messages: 8x8-dq-aarch64-neon.S:657: Error: operand mismatch -- `mov V8.4s,V9.4s' Info: did you mean this? Info: mov v8.8b, v9.8b Info: other valid variant(s): Info: mov v8.16b, v9.16b Signed-off-by: Edward Swarthout --- .../cpu/qnnpack/src/q8gemm/8x8-dq-aarch64-neon.S | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/aten/src/ATen/native/quantized/cpu/qnnpack/src/q8gemm/8x8-dq-aarch64-neon.S b/aten/src/ATen/native/quantized/cpu/qnnpack/src/q8gemm/8x8-dq-aarch64-neon.S index 7dc8611..60ad8d1 100644 --- a/aten/src/ATen/native/quantized/cpu/qnnpack/src/q8gemm/8x8-dq-aarch64-neon.S +++ b/aten/src/ATen/native/quantized/cpu/qnnpack/src/q8gemm/8x8-dq-aarch64-neon.S @@ -659,14 +659,14 @@ BEGIN_FUNCTION pytorch_q8gemm_dq_ukernel_8x8__aarch64_neon SUB x1, x1, 4 - MOV V8.4s, V9.4s - MOV v10.4s, v11.4s - MOV v12.4s, V13.4s - MOV V14.4s, V15.4s - MOV V16.4s, V17.4s - MOV V18.4s, V19.4s - MOV V20.4s, V21.4s - MOV V22.4s, V23.4s + MOV V8.16b, V9.16b + MOV v10.16b, v11.16b + MOV v12.16b, V13.16b + MOV V14.16b, V15.16b + MOV V16.16b, V17.16b + MOV V18.16b, V19.16b + MOV V20.16b, V21.16b + MOV V22.16b, V23.16b 5: CMP x1, 2 -- 2.7.4