radeonsi: use minnum and maxnum LLVM intrinsics for MIN and MAX opcodes
So far it has been compiled into pretty ugly code (8 instructions or so
for either opcode).
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index 40a2f90..037811e 100644
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -2737,6 +2737,13 @@
bld_base->op_actions[TGSI_OPCODE_EMIT].emit = si_llvm_emit_vertex;
bld_base->op_actions[TGSI_OPCODE_ENDPRIM].emit = si_llvm_emit_primitive;
+ if (HAVE_LLVM >= 0x0306) {
+ bld_base->op_actions[TGSI_OPCODE_MAX].emit = build_tgsi_intrinsic_nomem;
+ bld_base->op_actions[TGSI_OPCODE_MAX].intr_name = "llvm.maxnum.f32";
+ bld_base->op_actions[TGSI_OPCODE_MIN].emit = build_tgsi_intrinsic_nomem;
+ bld_base->op_actions[TGSI_OPCODE_MIN].intr_name = "llvm.minnum.f32";
+ }
+
si_shader_ctx.radeon_bld.load_system_value = declare_system_value;
si_shader_ctx.tokens = sel->tokens;
tgsi_parse_init(&si_shader_ctx.parse, si_shader_ctx.tokens);