Alex-grovety commented on issue #8717: URL: https://github.com/apache/tvm/issues/8717#issuecomment-915902237
output tensor is 8-bit for case when hardware has support for fast int8 arithmetic operations, if hardware hasn't support for fast int8 arithmetic operations we get: ``` PrimFunc([placeholder, placeholder, placeholder, T_cast]) attrs={"from_legacy_te_schedule": (bool)1, "global_symbol": "tvmgen_default_fused_nn_conv2d_add_fixed_point_multiply_clip_cast_cast_21", "tir.noalias": (bool)1} { allocate DepthwiseConv2d[int32 * 1], storage_scope = global for (ax0.ax1.fused.ax2.fused.ax3.fused, 0, 401408) { DepthwiseConv2d[0] = 0 for (di, 0, 3) { for (dj, 0, 3) { DepthwiseConv2d[0] = (DepthwiseConv2d[0] + (int32(tir.if_then_else(((((1 <= (floordiv(ax0.ax1.fused.ax2.fused.ax3.fused, 7168) + di)) && ((floordiv(ax0.ax1.fused.ax2.fused.ax3.fused, 7168) + di) < 57)) && (1 <= (floordiv(floormod(ax0.ax1.fused.ax2.fused.ax3.fused, 7168), 128) + dj))) && ((floordiv(floormod(ax0.ax1.fused.ax2.fused.ax3.fused, 7168), 128) + dj) < 57)), placeholder[((((di*7168) + (dj*128)) + ax0.ax1.fused.ax2.fused.ax3.fused) - 7296)], (int16)0))*int32(placeholder[(((di*384) + (dj*128)) + floormod(ax0.ax1.fused.ax2.fused.ax3.fused, 128))]))) } } T_cast[ax0.ax1.fused.ax2.fused.ax3.fused] = int16(uint8(max(min(tir.q_multiply_shift((DepthwiseConv2d[0] + placeholder[floormod(ax0.ax1.fused.ax2.fused.ax3.fused, 128)]), 2080045879, 31, -4), 255), 0))) } } ``` -- 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. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org