[Mesa-dev] [RFC 2/4] gallium: Add fixed block size to pipe_compute_state

[Bas Nieuwenhuizen]

This avoids shader variants for radeonsi, or if we go with
shader variants, it lets us compile an initial variant.

Signed-off-by: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
---
 src/gallium/drivers/trace/tr_dump_state.c | 4 ++++
 src/gallium/include/pipe/p_state.h        | 6 ++++++
 src/gallium/tests/trivial/compute.c       | 1 +
 src/mesa/state_tracker/st_program.c       | 2 ++
 4 files changed, 13 insertions(+)

diff --git a/src/gallium/drivers/trace/tr_dump_state.c b/src/gallium/drivers/trace/tr_dump_state.c
index 394cdaa..4f89af9 100644
--- a/src/gallium/drivers/trace/tr_dump_state.c
+++ b/src/gallium/drivers/trace/tr_dump_state.c
@@ -333,6 +333,10 @@ void trace_dump_compute_state(const struct pipe_compute_state *state)
    trace_dump_member(uint, state, req_private_mem);
    trace_dump_member(uint, state, req_input_mem);
 
+   trace_dump_member_begin("fixed_block");
+   trace_dump_array(uint, state->fixed_block, Elements(state->fixed_block));
+   trace_dump_member_end();
+
    trace_dump_struct_end();
 }
 
diff --git a/src/gallium/include/pipe/p_state.h b/src/gallium/include/pipe/p_state.h
index 8e7a10b..fff90e7 100644
--- a/src/gallium/include/pipe/p_state.h
+++ b/src/gallium/include/pipe/p_state.h
@@ -732,6 +732,12 @@ struct pipe_compute_state
    unsigned req_local_mem; /**< Required size of the LOCAL resource. */
    unsigned req_private_mem; /**< Required size of the PRIVATE resource. */
    unsigned req_input_mem; /**< Required size of the INPUT resource. */
+
+   /**
+    * Block layout if known, or all zeroes if the block layout is either not
+    * known yet or dynamic.
+    */
+   unsigned fixed_block[3];
 };
 
 /**
diff --git a/src/gallium/tests/trivial/compute.c b/src/gallium/tests/trivial/compute.c
index 2ddfc42..af3e3aa 100644
--- a/src/gallium/tests/trivial/compute.c
+++ b/src/gallium/tests/trivial/compute.c
@@ -149,6 +149,7 @@ static void init_prog(struct context *ctx, unsigned local_sz,
                 .req_local_mem = local_sz,
                 .req_private_mem = private_sz,
                 .req_input_mem = input_sz
+                .fixed_block = {0}
         };
         char *psrc = preprocess_prog(ctx, src, defs);
         int ret;
diff --git a/src/mesa/state_tracker/st_program.c b/src/mesa/state_tracker/st_program.c
index 5e282d9..5777e76 100644
--- a/src/mesa/state_tracker/st_program.c
+++ b/src/mesa/state_tracker/st_program.c
@@ -1440,6 +1440,8 @@ st_translate_compute_program(struct st_context *st,
    stcp->tgsi.req_local_mem = stcp->Base.SharedSize;
    stcp->tgsi.req_private_mem = 0;
    stcp->tgsi.req_input_mem = 0;
+   memcpy(stcp->tgsi.fixed_block, stcp->Base.LocalSize,
+          sizeof(stcp->Base.LocalSize));
 
    free_glsl_to_tgsi_visitor(stcp->glsl_to_tgsi);
    stcp->glsl_to_tgsi = NULL;
-- 
2.7.4