diff options
author | Kenneth Graunke <[email protected]> | 2016-06-08 22:21:22 -0700 |
---|---|---|
committer | Kenneth Graunke <[email protected]> | 2016-06-12 00:38:26 -0700 |
commit | 87d062a94080373995170f51063a9649c96c6dea (patch) | |
tree | a0057a7ebd072ec6104b83d17fb6ec7f396f60c7 /src/mesa/drivers/dri/i965/gen7_cs_state.c | |
parent | 3f48548a6f65fe90b97956c7be73268917c6f2f9 (diff) |
i965: Fix shared local memory size for Gen9+.
Skylake changes the representation of shared local memory size:
Size | 0 kB | 1 kB | 2 kB | 4 kB | 8 kB | 16 kB | 32 kB | 64 kB |
-------------------------------------------------------------------
Gen7-8 | 0 | none | none | 1 | 2 | 4 | 8 | 16 |
-------------------------------------------------------------------
Gen9+ | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
The old formula would substantially underallocate the amount of space.
This fixes GPU hangs on Skylake when running with full thread counts.
v2: Fix the Vulkan driver too, use a helper function, and fix the table
in the comments and commit message.
Cc: "12.0" <[email protected]>
Signed-off-by: Kenneth Graunke <[email protected]>
Reviewed-by: Francisco Jerez <[email protected]>
Reviewed-by: Jordan Justen <[email protected]>
Diffstat (limited to 'src/mesa/drivers/dri/i965/gen7_cs_state.c')
-rw-r--r-- | src/mesa/drivers/dri/i965/gen7_cs_state.c | 11 |
1 files changed, 2 insertions, 9 deletions
diff --git a/src/mesa/drivers/dri/i965/gen7_cs_state.c b/src/mesa/drivers/dri/i965/gen7_cs_state.c index 750aa2ccdf1..a71a5957191 100644 --- a/src/mesa/drivers/dri/i965/gen7_cs_state.c +++ b/src/mesa/drivers/dri/i965/gen7_cs_state.c @@ -45,6 +45,7 @@ brw_upload_cs_state(struct brw_context *brw) struct brw_stage_state *stage_state = &brw->cs.base; struct brw_cs_prog_data *cs_prog_data = brw->cs.prog_data; struct brw_stage_prog_data *prog_data = &cs_prog_data->base; + const struct brw_device_info *devinfo = brw->intelScreen->devinfo; if (INTEL_DEBUG & DEBUG_SHADER_TIME) { brw->vtbl.emit_buffer_surface_state( @@ -147,15 +148,7 @@ brw_upload_cs_state(struct brw_context *brw) SET_FIELD(cs_prog_data->threads, MEDIA_GPGPU_THREAD_COUNT); assert(cs_prog_data->threads <= brw->max_cs_threads); - assert(prog_data->total_shared <= 64 * 1024); - uint32_t slm_size = 0; - if (prog_data->total_shared > 0) { - /* slm_size is in 4k increments, but must be a power of 2. */ - slm_size = 4 * 1024; - while (slm_size < prog_data->total_shared) - slm_size <<= 1; - slm_size /= 4 * 1024; - } + const uint32_t slm_size = encode_slm_size(devinfo, prog_data->total_shared); desc[dw++] = SET_FIELD(cs_prog_data->uses_barrier, MEDIA_BARRIER_ENABLE) | |