OK, but I'm not sure why this complexity:
> #if SIZEOF_LONG == 8
> +typedef uint64_t mlx4_wc_copy_t;
> #else
> +typedef uint32_t mlx4_wc_copy_t;
Isn't that just a crazy way of coming up with a new name for unsigned long?
How about something like this (it seems to generate pretty good code
on x86-64 at least):
diff --git a/src/qp.c b/src/qp.c
index 8b4adaa..5721860 100644
--- a/src/qp.c
+++ b/src/qp.c
@@ -168,6 +168,20 @@ static void set_data_seg(struct mlx4_wqe_data_seg *dseg,
struct ibv_sge *sg)
dseg->byte_count = htonl(sg->length);
}
+/*
+ * Avoid using memcpy() to copy to BlueFlame page, since memcpy()
+ * implementations may use move-string-buffer assembler instructions,
+ * which do not guarantee order of copying.
+ */
+static void mlx4_bf_copy(unsigned long *dst, unsigned long *src, unsigned
bytecnt)
+{
+ while (bytecnt > 0) {
+ *dst++ = *src++;
+ *dst++ = *src++;
+ bytecnt -= 2 * sizeof (long);
+ }
+}
+
int mlx4_post_send(struct ibv_qp *ibqp, struct ibv_send_wr *wr,
struct ibv_send_wr **bad_wr)
{
@@ -388,7 +402,8 @@ out:
pthread_spin_lock(&ctx->bf_lock);
- memcpy(ctx->bf_page + ctx->bf_offset, ctrl, align(size * 16,
64));
+ mlx4_bf_copy(ctx->bf_page + ctx->bf_offset, (unsigned long *)
ctrl,
+ align(size * 16, 64));
wc_wmb();
ctx->bf_offset ^= ctx->bf_buf_size;
_______________________________________________
general mailing list
[email protected]
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
