radeonsi: enable WQM in PS prolog when needed

WQM is needed when the PS prolog computes a VGPR that is consumed by a shader
with (implicit or explicit) derivatives.

Depends on http://reviews.llvm.org/D20839 / LLVM r272063 for this to be
effective (otherwise it's just a no-op).

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=95130
Cc: 12.0 <mesa-dev@lists.freedesktop.org>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>

src/gallium/drivers/radeonsi/si_shader.c

@@ -7197,6 +7197,12 @@ static bool si_compile_ps_prolog(struct si_screen *sscreen,
 						   linear_sample[i], base + 10 + i, "");
 	}
 
+	/* Tell LLVM to insert WQM instruction sequence when needed. */
+	if (key->ps_prolog.wqm) {
+		LLVMAddTargetDependentFunctionAttr(func,
+						   "amdgpu-ps-wqm-outputs", "");
+	}
+
 	/* Compile. */
 	LLVMBuildRet(gallivm->builder, ret);
 	radeon_llvm_finalize_module(&ctx.radeon_bld);
@@ -7347,6 +7353,9 @@ static bool si_shader_select_ps_parts(struct si_screen *sscreen,
 	prolog_key.ps_prolog.colors_read = info->colors_read;
 	prolog_key.ps_prolog.num_input_sgprs = shader->info.num_input_sgprs;
 	prolog_key.ps_prolog.num_input_vgprs = shader->info.num_input_vgprs;
+	prolog_key.ps_prolog.wqm = info->uses_derivatives &&
+		(prolog_key.ps_prolog.colors_read ||
+		 prolog_key.ps_prolog.states.force_persample_interp);
 
 	if (info->colors_read) {
 		unsigned *color = shader->selector->color_attr_index;

src/gallium/drivers/radeonsi/si_shader.h

@@ -355,6 +355,7 @@ union si_shader_part_key {
 		unsigned	colors_read:8; /* color input components read */
 		unsigned	num_interp_inputs:5; /* BCOLOR is at this location */
 		unsigned	face_vgpr_index:5;
+		unsigned	wqm:1;
 		char		color_attr_index[2];
 		char		color_interp_vgpr_index[2]; /* -1 == constant */
 	} ps_prolog;