intel/tools: Handle strides better when dumping buffers

The old code would only break at stride boundaries if the stride was
less than 32B; otherwise it would just break every 32B.  This commit
makes it break at stride boundaries and 32B boundaries (starting from
the last stride).  This makes reading large vertex buffers in aubinator
much nicer.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3642>

diff --git a/src/intel/common/gen_batch_decoder.c b/src/intel/common/gen_batch_decoder.c
index 2a5261b2f929e73f4859ab73fa306ee230383a2d..e03a5e1d26c1842f35f02938b86b6ef4e96aefc8 100644 (file)
--- a/src/intel/common/gen_batch_decoder.c
+++ b/src/intel/common/gen_batch_decoder.c
@@ -176,11 +176,13 @@ ctx_print_buffer(struct gen_batch_decode_ctx *ctx,
    const uint32_t *dw_end =
          bo.map + ROUND_DOWN_TO(MIN2(bo.size, read_length), 4);
 
-   int column_count = 0, line_count = -1;
+   int column_count = 0, pitch_col_count = 0, line_count = -1;
    for (const uint32_t *dw = bo.map; dw < dw_end; dw++) {
-      if (column_count * 4 == pitch || column_count == 8) {
+      if (pitch_col_count * 4 == pitch || column_count == 8) {
          fprintf(ctx->fp, "\n");
          column_count = 0;
+         if (pitch_col_count * 4 == pitch)
+            pitch_col_count = 0;
          line_count++;
 
          if (max_lines >= 0 && line_count >= max_lines)
@@ -194,6 +196,7 @@ ctx_print_buffer(struct gen_batch_decode_ctx *ctx,
          fprintf(ctx->fp, "  0x%08x", *dw);
 
       column_count++;
+      pitch_col_count++;
    }
    fprintf(ctx->fp, "\n");
 }