radeonsi: use ordered compares for SSG and face selection

Ordered compares are what you have in C. Unordered compares are the result
of negating ordered compares (they return true if either argument is NaN).

That special NaN behavior is completely useless here, and unordered
compares produce horrible code with all stable LLVM versions.
(I think that has been fixed in LLVM git)

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>

diff --git a/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c b/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c
index c30a9d0..dce5b55 100644 (file)
--- a/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c
+++ b/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c
@@ -1107,9 +1107,9 @@ static void emit_ssg(
                cmp = LLVMBuildICmp(builder, LLVMIntSGE, val, bld_base->int_bld.zero, "");
                val = LLVMBuildSelect(builder, cmp, val, LLVMConstInt(bld_base->int_bld.elem_type, -1, true), "");
        } else { // float SSG
-               cmp = LLVMBuildFCmp(builder, LLVMRealUGT, emit_data->args[0], bld_base->base.zero, "");
+               cmp = LLVMBuildFCmp(builder, LLVMRealOGT, emit_data->args[0], bld_base->base.zero, "");
                val = LLVMBuildSelect(builder, cmp, bld_base->base.one, emit_data->args[0], "");
-               cmp = LLVMBuildFCmp(builder, LLVMRealUGE, val, bld_base->base.zero, "");
+               cmp = LLVMBuildFCmp(builder, LLVMRealOGE, val, bld_base->base.zero, "");
                val = LLVMBuildSelect(builder, cmp, val, LLVMConstReal(bld_base->base.elem_type, -1), "");
        }
 

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index ba42dab..09d7849 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -484,7 +484,7 @@ static void declare_input_fs(
                face = LLVMGetParam(main_fn, SI_PARAM_FRONT_FACE);
 
                is_face_positive = LLVMBuildFCmp(gallivm->builder,
-                                                LLVMRealUGT, face,
+                                                LLVMRealOGT, face,
                                                 lp_build_const_float(gallivm, 0.0f),
                                                 "");