FYI, Evergreen has dedicated instructions for both MAD and FMA. FMA seems to be available on DX11 chips only.
Marek On Tue, Jan 7, 2014 at 8:20 PM, Roland Scheidegger <srol...@vmware.com> wrote: > Yes that is certainly related. I'm actually not entirely sure what is > allowed in glsl by default as OpenGL seems to have some lax rules > regarding precision in any case (float calculations not required but > allowed to use denorms, at least earlier versions weren't required to > support Infs neither and so on). > It is quite possible the "MAD" we were always using would have been > allowed to really do fma (at least with OpenGL), unless the "precise" > qualifier was used (which isn't supported yet?). > TGSI also isn't really watertight about such issues neither (that is if > you use it with hw such as r300 then you certainly don't expect ieee754 > rules to be followed but if you've got a d3d10-capable backend then you > are expected to follow rules specified there which are _mostly_ > ieee754-2008). > So I'm not really sure if TGSI MAD should be allowed to do either > rounding or not, but someday it should be figured out and spelled out > explicitly in docs. > > Roland > > > Am 07.01.2014 19:24, schrieb Maxence Le Doré: >> I forgot the link : >> >> https://urldefense.proofpoint.com/v1/url?u=http://www.geeks3d.com/20120106/precise-qualifier-in-glsl-and-nvidia-geforce-cards/&k=oIvRg1%2BdGAgOoM1BIlLLqw%3D%3D%0A&r=F4msKE2WxRzA%2BwN%2B25muztFm5TSPwE8HKJfWfR2NgfY%3D%0A&m=%2FzSAl55KOH0z7T5qkRj6BX164wf6QpYOnJLIzojXBQc%3D%0A&s=0ac5e0fbd69867705f0c52090c9ddf84e7832be80e724a0983c5aa2f5dde72e0 >> >> 2014/1/7 Maxence Le Doré <maxence.led...@gmail.com>: >>> For this reason, GLSL 4.0 introduces the 'precise' qualifier. I invite >>> you to take a look at this article. >>> >>> 2014/1/6 Roland Scheidegger <srol...@vmware.com>: >>>> Am 05.01.2014 01:34, schrieb Maxence Le Doré: >>>>> FMA(a,b,c) keeps extra precision (usually 1 more bit of mantissa, >>>>> afaik) for the result a*b and add this to c, to finally produce a >>>>> IEEE754 32bit float result. >>>>> >>>>> MAD(a,b,c) product a IEEE754 32bit float product a*b and add it to C. >>>>> >>>>> So, fma can be slightly more accurate. An accuracy that is something >>>>> very appreciate. >>>> >>>> Actually in "newer" languages (such as opencl) "mad" is used to indicate >>>> intermediate rounding does not matter, so if your cpu can do fma but not >>>> mul+add in a single cycle it is allowed to use fma instead. >>>> FMA OTOH of course forces no intermediate rounding. >>>> Our tgsi definitions certainly initially were meaning intermediate >>>> rounding should take place, I don't know if we need to keep it that way >>>> or could repurpose that slightly (so if you require the intermediate >>>> rounding you'd just use mul+add). >>>> >>>> Roland >>>> >>>> >>>> >>>>> >>>>> >>>>> 2014/1/5 Marek Olšák <mar...@gmail.com>: >>>>>> How is FMA different from MAD? >>>>>> >>>>>> Please document the new opcodes in src/gallium/docs/source/tgsi.rst. >>>>>> >>>>>> Marek >>>>>> >>>>>> On Sun, Jan 5, 2014 at 12:42 AM, Maxence Le Doré >>>>>> <maxence.led...@gmail.com> wrote: >>>>>>> From: Maxence Le Doré <Maxence Le Doré> >>>>>>> >>>>>>> --- >>>>>>> src/gallium/auxiliary/tgsi/tgsi_info.c | 16 ++++++++++++++++ >>>>>>> src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h | 6 ++++++ >>>>>>> src/gallium/include/pipe/p_shader_tokens.h | 9 ++++++++- >>>>>>> 3 files changed, 30 insertions(+), 1 deletion(-) >>>>>>> >>>>>>> diff --git a/src/gallium/auxiliary/tgsi/tgsi_info.c >>>>>>> b/src/gallium/auxiliary/tgsi/tgsi_info.c >>>>>>> index 0beef44..ed55940 100644 >>>>>>> --- a/src/gallium/auxiliary/tgsi/tgsi_info.c >>>>>>> +++ b/src/gallium/auxiliary/tgsi/tgsi_info.c >>>>>>> @@ -221,6 +221,12 @@ static const struct tgsi_opcode_info >>>>>>> opcode_info[TGSI_OPCODE_LAST] = >>>>>>> { 1, 3, 1, 0, 0, 0, OTHR, "TXL2", TGSI_OPCODE_TXL2 }, >>>>>>> { 1, 2, 0, 0, 0, 0, COMP, "IMUL_HI", TGSI_OPCODE_IMUL_HI }, >>>>>>> { 1, 2, 0, 0, 0, 0, COMP, "UMUL_HI", TGSI_OPCODE_UMUL_HI }, >>>>>>> + { 1, 3, 0, 0, 0, 0, COMP, "FMA", TGSI_OPCODE_FMA }, >>>>>>> + { 1, 1, 0, 0, 0, 0, COMP, "POPCNT", TGSI_OPCODE_POPCNT }, >>>>>>> + { 1, 1, 0, 0, 0, 0, COMP, "IMSB", TGSI_OPCODE_IMSB }, >>>>>>> + { 1, 1, 0, 0, 0, 0, COMP, "ILSB", TGSI_OPCODE_ILSB }, >>>>>>> + { 1, 1, 0, 0, 0, 0, COMP, "UMSB", TGSI_OPCODE_UMSB }, >>>>>>> + { 1, 1, 0, 0, 0, 0, COMP, "ULSB", TGSI_OPCODE_ULSB }, >>>>>>> }; >>>>>>> >>>>>>> const struct tgsi_opcode_info * >>>>>>> @@ -321,6 +327,11 @@ tgsi_opcode_infer_type( uint opcode ) >>>>>>> case TGSI_OPCODE_IABS: >>>>>>> case TGSI_OPCODE_ISSG: >>>>>>> case TGSI_OPCODE_IMUL_HI: >>>>>>> + case TGSI_OPCODE_POPCNT: >>>>>>> + case TGSI_OPCODE_ILSB: >>>>>>> + case TGSI_OPCODE_IMSB: >>>>>>> + case TGSI_OPCODE_ULSB: >>>>>>> + case TGSI_OPCODE_UMSB: >>>>>>> return TGSI_TYPE_SIGNED; >>>>>>> default: >>>>>>> return TGSI_TYPE_FLOAT; >>>>>>> @@ -344,9 +355,14 @@ tgsi_opcode_infer_src_type( uint opcode ) >>>>>>> case TGSI_OPCODE_SAMPLE_I: >>>>>>> case TGSI_OPCODE_SAMPLE_I_MS: >>>>>>> case TGSI_OPCODE_UMUL_HI: >>>>>>> + case TGSI_OPCODE_POPCNT: >>>>>>> + case TGSI_OPCODE_ULSB: >>>>>>> + case TGSI_OPCODE_UMSB: >>>>>>> return TGSI_TYPE_UNSIGNED; >>>>>>> case TGSI_OPCODE_IMUL_HI: >>>>>>> case TGSI_OPCODE_I2F: >>>>>>> + case TGSI_OPCODE_ILSB: >>>>>>> + case TGSI_OPCODE_IMSB: >>>>>>> return TGSI_TYPE_SIGNED; >>>>>>> case TGSI_OPCODE_ARL: >>>>>>> case TGSI_OPCODE_ARR: >>>>>>> diff --git a/src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h >>>>>>> b/src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h >>>>>>> index 1ef78dd..cba0975 100644 >>>>>>> --- a/src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h >>>>>>> +++ b/src/gallium/auxiliary/tgsi/tgsi_opcode_tmp.h >>>>>>> @@ -206,6 +206,12 @@ OP13(UCMP) >>>>>>> >>>>>>> OP12(IMUL_HI) >>>>>>> OP12(UMUL_HI) >>>>>>> +OP13(FMA) >>>>>>> +OP11(POPCNT) >>>>>>> +OP11(IMSB) >>>>>>> +OP11(ILSB) >>>>>>> +OP11(UMSB) >>>>>>> +OP11(ULSB) >>>>>>> >>>>>>> #undef OP00 >>>>>>> #undef OP01 >>>>>>> diff --git a/src/gallium/include/pipe/p_shader_tokens.h >>>>>>> b/src/gallium/include/pipe/p_shader_tokens.h >>>>>>> index 8010902..5ed0c34 100644 >>>>>>> --- a/src/gallium/include/pipe/p_shader_tokens.h >>>>>>> +++ b/src/gallium/include/pipe/p_shader_tokens.h >>>>>>> @@ -453,7 +453,14 @@ struct tgsi_property_data { >>>>>>> #define TGSI_OPCODE_IMUL_HI 180 >>>>>>> #define TGSI_OPCODE_UMUL_HI 181 >>>>>>> >>>>>>> -#define TGSI_OPCODE_LAST 182 >>>>>>> +#define TGSI_OPCODE_FMA 182 >>>>>>> +#define TGSI_OPCODE_POPCNT 183 >>>>>>> +#define TGSI_OPCODE_IMSB 184 >>>>>>> +#define TGSI_OPCODE_ILSB 185 >>>>>>> +#define TGSI_OPCODE_UMSB 186 >>>>>>> +#define TGSI_OPCODE_ULSB 187 >>>>>>> + >>>>>>> +#define TGSI_OPCODE_LAST 188 >>>>>>> >>>>>>> #define TGSI_SAT_NONE 0 /* do not saturate */ >>>>>>> #define TGSI_SAT_ZERO_ONE 1 /* clamp to [0,1] */ >>>>>>> -- >>>>>>> 1.8.5.2 >>>>>>> >>>>>>> _______________________________________________ >>>>>>> mesa-dev mailing list >>>>>>> mesa-dev@lists.freedesktop.org >>>>>>> https://urldefense.proofpoint.com/v1/url?u=http://lists.freedesktop.org/mailman/listinfo/mesa-dev&k=oIvRg1%2BdGAgOoM1BIlLLqw%3D%3D%0A&r=F4msKE2WxRzA%2BwN%2B25muztFm5TSPwE8HKJfWfR2NgfY%3D%0A&m=UbogYegyhJOd8MD5pXDHVLpkdfH0gvvci5OW50vTexw%3D%0A&s=4da499b672e3e50826f923f340c51cfaa5c79830951ccc3034abd52a1b7402a8 >>>>> _______________________________________________ >>>>> mesa-dev mailing list >>>>> mesa-dev@lists.freedesktop.org >>>>> https://urldefense.proofpoint.com/v1/url?u=http://lists.freedesktop.org/mailman/listinfo/mesa-dev&k=oIvRg1%2BdGAgOoM1BIlLLqw%3D%3D%0A&r=F4msKE2WxRzA%2BwN%2B25muztFm5TSPwE8HKJfWfR2NgfY%3D%0A&m=UbogYegyhJOd8MD5pXDHVLpkdfH0gvvci5OW50vTexw%3D%0A&s=4da499b672e3e50826f923f340c51cfaa5c79830951ccc3034abd52a1b7402a8 >>>>> _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev
