i965/fs: Rework the fs_visitor LOAD_PAYLOAD instruction

The newly reworked instruction is far more straightforward than the
original.  Before, the LOAD_PAYLOAD instruction was lowered by a the
complicated and broken-by-design pile of heuristics to try and guess
force_writemask_all, exec_size, and a number of other factors on the
sources.

Instead, we use the header_size on the instruction to denote which sources
are "header sources".  Header sources are required to be a single physical
hardware register that is copied verbatim.  The registers that follow are
considered the actual payload registers and have a width that correspond's
to the LOAD_PAYLOAD's exec_size and are treated as being per-channel.  This
gives us a fairly straightforward lowering:

 1) All header sources are copied directly using force_writemask_all and,
    since they are guaranteed to be a single register, there are no
    force_sechalf issues.

 2) All non-header sources are copied using the exact same force_sechalf
    and force_writemask_all modifiers as the LOAD_PAYLOAD operation itself.

 3) In order to accommodate older gens that need interleaved colors,
    lower_load_payload detects when the destination is a COMPR4 register
    and automatically interleaves the non-header sources.  The
    lower_load_payload pass does the right thing here regardless of whether
    or not the hardware actually supports COMPR4.

This patch commit itself is made up of a bunch of smaller changes squashed
together.  Individual change descriptions follow:

i965/fs: Rework fs_visitor::LOAD_PAYLOAD

   We rework LOAD_PAYLOAD to verify that all of the sources that count as
   headers are, indeed, exactly one register and that all of the non-header
   sources match the destination width.  We then take the exec_size for
   LOAD_PAYLOAD directly from the destination width.

i965/fs: Make destinations of load_payload have the appropreate width

i965/fs: Rework fs_visitor::lower_load_payload

   v2: Don't allow the saturate flag on LOAD_PAYLOAD instructions

i965/fs_cse: Support the new-style LOAD_PAYLOAD

i965/fs_inst::is_copy_payload: Support the new-style LOAD_PAYLOAD

i965/fs: Simplify setup_color_payload

   Previously, setup_color_payload was a a big helper function that did a
   lot of gen-specific special casing for setting up the color sources of
   the LOAD_PAYLOAD instruction.  Now that lower_load_payload is much more
   sane, most of that complexity isn't needed anymore.  Instead, we can do
   a simple fixup pass for color clamps and then just stash sources
   directly in the LOAD_PAYLOAD.  We can trust lower_load_payload to do the
   right thing with respect to COMPR4.

Reviewed-by: Kenneth Graunke <[email protected]>

1 files changed, 24 insertions, 7 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_fs_cse.cpp b/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
index a582e6a8e4b..db01f8cf7ab 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
@@ -174,17 +174,34 @@ create_copy_instr(fs_visitor *v, fs_inst *inst, fs_reg src, bool negate)
 {
    int written = inst->regs_written;
    int dst_width = inst->dst.width / 8;
-   fs_reg dst = inst->dst;
    fs_inst *copy;
 
    if (written > dst_width) {
-      fs_reg *sources = ralloc_array(v->mem_ctx, fs_reg, written / dst_width);
-      for (int i = 0; i < written / dst_width; i++)
-         sources[i] = offset(src, i);
-      copy = v->LOAD_PAYLOAD(dst, sources, written / dst_width,
-                             inst->header_size);
+      fs_reg *payload;
+      int sources, header_size;
+      if (inst->opcode == SHADER_OPCODE_LOAD_PAYLOAD) {
+         sources = inst->sources;
+         header_size = inst->header_size;
+      } else {
+         assert(written % dst_width == 0);
+         sources = written / dst_width;
+         header_size = 0;
+      }
+
+      assert(src.file == GRF);
+      payload = ralloc_array(v->mem_ctx, fs_reg, sources);
+      for (int i = 0; i < header_size; i++) {
+         payload[i] = src;
+         payload[i].width = 8;
+         src.reg_offset++;
+      }
+      for (int i = header_size; i < sources; i++) {
+         payload[i] = src;
+         src = offset(src, 1);
+      }
+      copy = v->LOAD_PAYLOAD(inst->dst, payload, sources, header_size);
    } else {
-      copy = v->MOV(dst, src);
+      copy = v->MOV(inst->dst, src);
       copy->force_writemask_all = inst->force_writemask_all;
       copy->src[0].negate = negate;
    }