diff options
author | Dave Airlie <[email protected]> | 2017-03-17 13:38:41 +1000 |
---|---|---|
committer | Emil Velikov <[email protected]> | 2017-05-10 11:28:45 +0100 |
commit | 072b1f5270ef76f997ee33a1397e14c9eeecbc35 (patch) | |
tree | d0127eb6faeff14428373312f1b6bdf6748007f1 | |
parent | bd79ce435610be9a7ad2eb25bca22dbcb1a384d9 (diff) |
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 <[email protected]>
Signed-off-by: Dave Airlie <[email protected]>
(cherry picked from commit 3bf3f9866c1387872521242921bb00c7fb7c2834)
-rw-r--r-- | src/amd/common/ac_nir_to_llvm.c | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c index 43d0520541f..43a79b833b6 100644 --- a/src/amd/common/ac_nir_to_llvm.c +++ b/src/amd/common/ac_nir_to_llvm.c @@ -1653,10 +1653,18 @@ 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", |