diff options
| -rw-r--r-- | src/amd/common/ac_nir_to_llvm.c | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c index ac0a2e67d40..48e2920a158 100644 --- a/src/amd/common/ac_nir_to_llvm.c +++ b/src/amd/common/ac_nir_to_llvm.c @@ -6892,6 +6892,20 @@ static void ac_compile_llvm_module(LLVMTargetMachineRef tm, /* +3 for scratch wave offset and VCC */ config->num_sgprs = MAX2(config->num_sgprs, shader_info->num_input_sgprs + 3); + + /* Enable 64-bit and 16-bit denormals, because there is no performance + * cost. + * + * If denormals are enabled, all floating-point output modifiers are + * ignored. + * + * Don't enable denormals for 32-bit floats, because: + * - Floating-point output modifiers would be ignored by the hw. + * - Some opcodes don't support denormals, such as v_mad_f32. We would + * have to stop using those. + * - SI & CI would be very slow. + */ + config->float_mode |= V_00B028_FP_64_DENORMS; } static void |