From 3bf3f9866c1387872521242921bb00c7fb7c2834 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Fri, 17 Mar 2017 13:38:41 +1000 Subject: radv/ac: canonicalize the output for 32-bit float min/max. This fixes: dEQP-VK.glsl.builtin.precision.min.* dEQP-VK.glsl.builtin.precision.max.* dEQP-VK.glsl.builtin.precision.clamp.* The problem is the hw doesn't compare denorms properly, so we have to flush them, even though the spec says flushing is optional, if you don't flush the results should be correct. The -pro driver changes the shader float mode, it would be nice if llvm could grow that perhaps. Acked-by: Bas Nieuwenhuizen Signed-off-by: Dave Airlie --- src/amd/common/ac_nir_to_llvm.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'src/amd/common/ac_nir_to_llvm.c') diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c index dbb8ebedd93..fccac1a3219 100644 --- a/src/amd/common/ac_nir_to_llvm.c +++ b/src/amd/common/ac_nir_to_llvm.c @@ -1748,10 +1748,18 @@ static void visit_alu(struct nir_to_llvm_context *ctx, nir_alu_instr *instr) case nir_op_fmax: result = emit_intrin_2f_param(ctx, "llvm.maxnum", to_float_type(ctx, def_type), src[0], src[1]); + if (instr->dest.dest.ssa.bit_size == 32) + result = emit_intrin_1f_param(ctx, "llvm.canonicalize", + to_float_type(ctx, def_type), + result); break; case nir_op_fmin: result = emit_intrin_2f_param(ctx, "llvm.minnum", to_float_type(ctx, def_type), src[0], src[1]); + if (instr->dest.dest.ssa.bit_size == 32) + result = emit_intrin_1f_param(ctx, "llvm.canonicalize", + to_float_type(ctx, def_type), + result); break; case nir_op_ffma: result = emit_intrin_3f_param(ctx, "llvm.fma", -- cgit v1.2.3