Mesa (master): r600g: Use blitter rather than DMA for 128bpp on cayman (v3)
Alex Deucher
agd5f at kemper.freedesktop.org
Sun Mar 17 17:42:58 UTC 2013
Module: Mesa
Branch: master
Commit: 4409758a046a47b09cdd339f97afd22107c68f0c
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=4409758a046a47b09cdd339f97afd22107c68f0c
Author: Alex Deucher <alexander.deucher at amd.com>
Date: Fri Mar 15 14:29:24 2013 -0400
r600g: Use blitter rather than DMA for 128bpp on cayman (v3)
On cayman, 128bpp surfaces require non_disp ordering for hw
access to both linear and tiled surfaces. When we use the 3D
engine we can set the non_disp ordering on both the tiled and
linear sides (via CB or texture), but when we use the DMA
engine, we can only set the non_disp ordering on the tiled
side, so after a L2T operation with the DMA engine, the data
ends up in the wrong order on the tiled side.
v2: cayman/TN only
v3: fix comments
Fixes:
https://bugs.freedesktop.org/show_bug.cgi?id=60802
Note: this is a candidate for the 9.1 branch.
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
src/gallium/drivers/r600/evergreen_state.c | 11 +++++++++++
1 files changed, 11 insertions(+), 0 deletions(-)
diff --git a/src/gallium/drivers/r600/evergreen_state.c b/src/gallium/drivers/r600/evergreen_state.c
index 2bdefb0..6b6d93e 100644
--- a/src/gallium/drivers/r600/evergreen_state.c
+++ b/src/gallium/drivers/r600/evergreen_state.c
@@ -3674,6 +3674,17 @@ boolean evergreen_dma_blit(struct pipe_context *ctx,
return FALSE;
}
+ /* 128 bpp surfaces require non_disp_tiling for both
+ * tiled and linear buffers on cayman. However, async
+ * DMA only supports it on the tiled side. As such
+ * the tile order is backwards after a L2T/T2L packet.
+ */
+ if ((rctx->chip_class == CAYMAN) &&
+ (src_mode != dst_mode) &&
+ (util_format_get_blocksize(src->format) >= 16)) {
+ return FALSE;
+ }
+
if (src_mode == dst_mode) {
uint64_t dst_offset, src_offset;
/* simple dma blit would do NOTE code here assume :
More information about the mesa-commit
mailing list