i965/ir: Test thread dispatch packing assumptions.

Not [originally] intended for upstream.  Should cause a GPU hang if
some thread is executed with a non-contiguous dispatch mask breaking
assumptions of brw_stage_has_packed_dispatch().  Doesn't cause any
CTS, DEQP or Piglit regressions, while replacing
brw_stage_has_packed_dispatch() with a dummy implementation that
unconditionally returns true on top of this patch causes multiple GPU
hangs.

v2: Refactor into a separate function instead of emitting the test
    code directly from emit_nir_code(), drop VEC4 test and clean up
    slightly for upstream. (Jason)

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index b60ec71888a0ef784ef4ea1e6225c2d122fa166a..1483f41de9783929063210b1ed6f7fa761e8ef49 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -6786,3 +6786,33 @@ brw_compile_cs(const struct brw_compiler *compiler, void *log_data,
 
    return g.get_assembly(final_assembly_size);
 }
+
+/**
+ * Test the dispatch mask packing assumptions of
+ * brw_stage_has_packed_dispatch().  Call this from e.g. the top of
+ * fs_visitor::emit_nir_code() to cause a GPU hang if any shader invocation is
+ * executed with an unexpected dispatch mask.
+ */
+static UNUSED void
+brw_fs_test_dispatch_packing(const fs_builder &bld)
+{
+   const gl_shader_stage stage = bld.shader->stage;
+
+   if (brw_stage_has_packed_dispatch(bld.shader->devinfo, stage,
+                                     bld.shader->stage_prog_data)) {
+      const fs_builder ubld = bld.exec_all().group(1, 0);
+      const fs_reg tmp = component(bld.vgrf(BRW_REGISTER_TYPE_UD), 0);
+      const fs_reg mask = (stage == MESA_SHADER_FRAGMENT ? brw_vmask_reg() :
+                           brw_dmask_reg());
+
+      ubld.ADD(tmp, mask, brw_imm_ud(1));
+      ubld.AND(tmp, mask, tmp);
+
+      /* This will loop forever if the dispatch mask doesn't have the expected
+       * form '2^n-1', in which case tmp will be non-zero.
+       */
+      bld.emit(BRW_OPCODE_DO);
+      bld.CMP(bld.null_reg_ud(), tmp, brw_imm_ud(0), BRW_CONDITIONAL_NZ);
+      set_predicate(BRW_PREDICATE_NORMAL, bld.emit(BRW_OPCODE_WHILE));
+   }
+}