It's coherent and faster. GFX7-GFX9 should also support this but
for now only uses L2 for GFX10 because it's untested on previous gens.
This fixes dEQP-VK.memory.pipeline_barrier.transfer_*
This also fixes some missing geometry in Dawn Of War III because
VBOs weren't updated correctly.
Signed-off-by: Samuel Pitoiset <samuel.pitoi...@gmail.com>
---
src/amd/vulkan/si_cmd_buffer.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/src/amd/vulkan/si_cmd_buffer.c b/src/amd/vulkan/si_cmd_buffer.c
index 21a90cb2514..94f759139ee 100644
--- a/src/amd/vulkan/si_cmd_buffer.c
+++ b/src/amd/vulkan/si_cmd_buffer.c
@@ -1501,6 +1501,14 @@ void si_cp_dma_buffer_copy(struct radv_cmd_buffer
*cmd_buffer,
unsigned dma_flags = 0;
unsigned byte_count = MIN2(size,
cp_dma_max_byte_count(cmd_buffer));
+ if (cmd_buffer->device->physical_device->rad_info.chip_class >=
GFX10) {
+ /* DMA operations via L2 are coherent and faster.
+ * TODO: GFX7-GFX9 should also support this but it
+ * requires tests/benchmarks.
+ */
+ dma_flags |= CP_DMA_USE_L2;
+ }
+
si_cp_dma_prepare(cmd_buffer, byte_count,
size + skipped_size + realign_size,
&dma_flags);
@@ -1545,6 +1553,14 @@ void si_cp_dma_clear_buffer(struct radv_cmd_buffer
*cmd_buffer, uint64_t va,
unsigned byte_count = MIN2(size,
cp_dma_max_byte_count(cmd_buffer));
unsigned dma_flags = CP_DMA_CLEAR;
+ if (cmd_buffer->device->physical_device->rad_info.chip_class >=
GFX10) {
+ /* DMA operations via L2 are coherent and faster.
+ * TODO: GFX7-GFX9 should also support this but it
+ * requires tests/benchmarks.
+ */
+ dma_flags |= CP_DMA_USE_L2;
+ }
+
si_cp_dma_prepare(cmd_buffer, byte_count, size, &dma_flags);
/* Emit the clear packet. */
--
2.22.0
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
