From: Nicolai Hähnle Date: Tue, 24 Nov 2015 13:54:54 +0000 (+0100) Subject: radeon: scale query buffer size to result size X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=b9fc01aee75dcc2d56750ea430e32d74127faf69;p=mesa.git radeon: scale query buffer size to result size Performance monitor queries can become very big, especially considering that instances of a block in different shader engines are queried separately. Reviewed-by: Marek Olšák --- diff --git a/src/gallium/drivers/radeon/r600_query.c b/src/gallium/drivers/radeon/r600_query.c index b1cfb6e462b..38bbbbf8a5e 100644 --- a/src/gallium/drivers/radeon/r600_query.c +++ b/src/gallium/drivers/radeon/r600_query.c @@ -232,7 +232,7 @@ void r600_query_hw_destroy(struct r600_common_context *rctx, static struct r600_resource *r600_new_query_buffer(struct r600_common_context *ctx, struct r600_query_hw *query) { - unsigned buf_size = 4096; + unsigned buf_size = MAX2(query->result_size, 4096); /* Queries are normally read by the CPU after * being written by the gpu, hence staging is probably a good