On Mon, Jun 5, 2017 at 6:37 PM, Connor Abbott <cwabbo...@gmail.com> wrote:
> I pushed a v2 at > https://cgit.freedesktop.org/~cwabbott0/mesa/log/?h=nir-divergence-v2. > I'm not sure if I like this version better, though. I'll have to think > about it. In the meantime, feel free to take a look. > I've taken a skim through the branch and I agree that I'm not sure either. Here's a few thoughts in no particular order: 1) Other than the fact that it's a pile of churn, it doesn't seem to make too much difference whether dFdx and dFdy are ALU or intrinsics 2) Convergent instructions are, in a lot of ways, easier to deal with than plain cross-thread ones. Convergent ops can always be moved up the dominance tree or down into uniform control-flow. Regular cross-thread instructions can't be moved across any non-uniform control-flow. 3) dFdx and dFdy are weird because they're convergent so it's clear they are special but not clear they should be intrinsics instead of ALU 4) I like the nir_instr_is_convergent() and nir_instr_is_cross_thread() helpers 5) non-convergent cross-thread instructions should definitely be intrinsics. 6) I think the shader ballot stuff is all non-convergent cross-thread as are some of the more advanced subgroup operations (see HLSL shader model 6.0). That's all for now, --Jason > On Mon, Jun 5, 2017 at 2:43 PM, Jason Ekstrand <ja...@jlekstrand.net> > wrote: > > On Mon, Jun 5, 2017 at 1:50 PM, Connor Abbott <cwabbo...@gmail.com> > wrote: > >> > >> On Mon, Jun 5, 2017 at 1:37 PM, Jason Ekstrand <ja...@jlekstrand.net> > >> wrote: > >> > I'm not sure how I feel about having these as ALU operations. ALU > >> > operations are generally pure functions (with the exception > derivative) > >> > that > >> > can be re-ordered at will. I don't really like breaking that. In > fact, > >> > I'd > >> > almost be inclined to make derivatives intrinsics and just > special-case > >> > them > >> > in constant folding. Thoughts? > >> > >> I wasn't too sure about this either. It is a little weird to make > >> these ALU instructions. I followed the rule here that if something can > >> be constant-folded, it should be an ALU instruction, but I guess you > >> can argue that it's just a coincidence that these can be > >> constant-folded anyways. > > > > > > Yeah. As subgroup ops get more complicated, I think a log of the > subgroup > > operations can be constant-folded after a fashion but the rules get weird > > fast. > > > >> > >> I guess the main downside is that it would be > >> impossible to make nir_algebraic patterns with these, although I can't > >> think of too many simple pattern-matching type things you'd want to do > >> on these instructions anyways. > > > > > > Yeah. My gut also tells me that shaders which are "advanced" enough to > use > > subgroup features probably don't need (or it can't be done) the massive > > reductions we do for D3D9-generated shaders. > > > >> > >> Maybe something like not(any(not(foo))) > >> -> all(foo) and vice-versa? > >> > >> > > >> > On Mon, Jun 5, 2017 at 12:22 PM, Connor Abbott <cwabbo...@gmail.com> > >> > wrote: > >> >> > >> >> Signed-off-by: Connor Abbott <cwabbo...@gmail.com> > >> >> --- > >> >> src/compiler/nir/nir_intrinsics.h | 14 ++++++++++++++ > >> >> src/compiler/nir/nir_opcodes.py | 18 ++++++++++++++++-- > >> >> 2 files changed, 30 insertions(+), 2 deletions(-) > >> >> > >> >> diff --git a/src/compiler/nir/nir_intrinsics.h > >> >> b/src/compiler/nir/nir_intrinsics.h > >> >> index 21e7d90..157df7f 100644 > >> >> --- a/src/compiler/nir/nir_intrinsics.h > >> >> +++ b/src/compiler/nir/nir_intrinsics.h > >> >> @@ -330,6 +330,20 @@ SYSTEM_VALUE(channel_num, 1, 0, xx, xx, xx) > >> >> SYSTEM_VALUE(alpha_ref_float, 1, 0, xx, xx, xx) > >> >> SYSTEM_VALUE(layer_id, 1, 0, xx, xx, xx) > >> >> SYSTEM_VALUE(view_index, 1, 0, xx, xx, xx) > >> >> +SYSTEM_VALUE(subgroup_invocation, 1, 0, xx, xx, xx) > >> >> + > >> >> + > >> >> +/* ARB_shader_ballot instructions */ > >> >> + > >> >> +SYSTEM_VALUE(subgroup_eq_mask, 1, 0, xx, xx, xx) > >> >> +SYSTEM_VALUE(subgroup_ge_mask, 1, 0, xx, xx, xx) > >> >> +SYSTEM_VALUE(subgroup_gt_mask, 1, 0, xx, xx, xx) > >> >> +SYSTEM_VALUE(subgroup_le_mask, 1, 0, xx, xx, xx) > >> >> +SYSTEM_VALUE(subgroup_lt_mask, 1, 0, xx, xx, xx) > >> >> + > >> >> +INTRINSIC(ballot, 1, ARR(0), true, 0, 0, 0, xx, xx, xx, > >> >> + NIR_INTRINSIC_CAN_ELIMINATE | NIR_INTRINSIC_CAN_REORDER | > >> >> + NIR_INTRINSIC_CROSS_THREAD) > >> >> > >> >> /* Blend constant color values. Float values are clamped. */ > >> >> SYSTEM_VALUE(blend_const_color_r_float, 1, 0, xx, xx, xx) > >> >> diff --git a/src/compiler/nir/nir_opcodes.py > >> >> b/src/compiler/nir/nir_opcodes.py > >> >> index be3ab6d..05a80b2 100644 > >> >> --- a/src/compiler/nir/nir_opcodes.py > >> >> +++ b/src/compiler/nir/nir_opcodes.py > >> >> @@ -120,8 +120,10 @@ def opcode(name, output_size, output_type, > >> >> input_sizes, input_types, > >> >> input_types, convergent, cross_thread, > >> >> algebraic_properties, const_expr) > >> >> > >> >> -def unop_convert(name, out_type, in_type, const_expr): > >> >> - opcode(name, 0, out_type, [0], [in_type], "", const_expr) > >> >> +def unop_convert(name, out_type, in_type, const_expr, > >> >> cross_thread=False, > >> >> + convergent=False): > >> >> + opcode(name, 0, out_type, [0], [in_type], "", const_expr, > >> >> convergent, > >> >> + cross_thread) > >> >> > >> >> def unop(name, ty, const_expr, convergent=False, > cross_thread=False): > >> >> opcode(name, 0, ty, [0], [ty], "", const_expr, convergent, > >> >> cross_thread) > >> >> @@ -355,6 +357,18 @@ for i in xrange(1, 5): > >> >> for j in xrange(1, 5): > >> >> unop_horiz("fnoise{0}_{1}".format(i, j), i, tfloat, j, > tfloat, > >> >> "0.0f") > >> >> > >> >> +# ARB_shader_ballot instructions > >> >> + > >> >> +opcode("read_invocation", 0, tuint, [0, 1], [tuint, tuint32], "", > >> >> "src0", > >> >> + cross_thread=True) > >> >> +unop("read_first_invocation", tuint, "src0", cross_thread=True) > >> >> + > >> >> +# ARB_shader_group_vote instructions > >> >> + > >> >> +unop("any_invocations", tbool, "src0", cross_thread=True) > >> >> +unop("all_invocations", tbool, "src0", cross_thread=True) > >> >> +unop("all_invocations_equal", tbool, "true", cross_thread=True) > >> >> + > >> >> def binop_convert(name, out_type, in_type, alg_props, const_expr): > >> >> opcode(name, 0, out_type, [0, 0], [in_type, in_type], alg_props, > >> >> const_expr) > >> >> > >> >> -- > >> >> 2.9.3 > >> >> > >> >> _______________________________________________ > >> >> mesa-dev mailing list > >> >> mesa-dev@lists.freedesktop.org > >> >> https://lists.freedesktop.org/mailman/listinfo/mesa-dev > >> > > >> > > > > > >
_______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
