Announcement

Collapse
No announcement yet.

MIPS Loongson 3A Benchmarks On Debian

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Originally posted by maldorordiscord View Post
    I found the article:
    "GODSON-3: A SCALABLE MULTICORE
    RISC PROCESSOR WITH X86
    EMULATION"

    http://www.google.de/url?sa=t&rct=j&...UkCyWNUjQXuoiA

    free to read without paying 19 dollar.
    i read the article and the Loongson3A can accelerate in hardware: integer x86 and FPU-X87 and MMX and SSE1 and SSE2.

    Comment


    • Originally posted by TobiSGD View Post
      Please show me the part in that text were the author states that he is translating SSE into Loongson's SIMD format. He is stating that he has done that that with MMX on a Loongson 2F, which was possible because it has a 64 bit SIMD unit that is somewhat similar to MMX. You still fail to give a proof for your claims. Also, I don't think to spend 19$ on an article that I think will also not contain a proof for your claims.
      I did your work the Loongson 3A can accelerate : integer x86 and FPU-X87 and MMX and SSE1 and SSE2 in hardware.

      source and directlink to the article: http://www.google.de/url?sa=t&rct=j&...UkCyWNUjQXuoiA

      the Loongson3A only get 70% of the speed of a native x86 core because it accelerate integer x86 and FPU-X87 and MMX and SSE1 and SSE2 in hardware.

      Comment


      • Originally posted by maldorordiscord View Post
        I did your work the Loongson 3A can accelerate : integer x86 and FPU-X87 and MMX and SSE1 and SSE2 in hardware.

        source and directlink to the article: LINK EDITED OUT TO PREVENT DAMAGE TO THE FORUM DUE TO COPYRIGHT INFRINGEMENT

        the Loongson3A only get 70% of the speed of a native x86 core because it accelerate integer x86 and FPU-X87 and MMX and SSE1 and SSE2 in hardware.
        So finally you came up with a proof for at least a part of your statements and it took you only 3 days to do so.
        Sadly, the shown graphs say nothing about the SSE performance since there is no information about compiler options and which SIMD units (or the FPU) were used during the benchmarks.
        I would also like to see a complete benchmark comparison with an mainstream x86-CPU, like the AMD A8 or a Phenom II X4 to see how fast those CPUs are in reality and if gaming would be an option, which I still doubt.
        Last edited by TobiSGD; 07-08-2012, 07:04 PM.

        Comment


        • Originally posted by TobiSGD View Post
          So finally you came up with a proof for at least a part of your statements and it took you only 3 days to do so.
          The source is the same you just don't read it because you don't want to pay 19 dollar. It took me 3 days to find a "pirate copy" edition to save you 19 dollar.
          And I'm sure these haters in this forum will ban me for showing you the truth.

          Originally posted by TobiSGD View Post
          Sadly, the shown graphs say nothing about the SSE performance since there is no information about compiler options and which SIMD units (or the FPU) were used during the benchmarks.
          I would also like to see a complete benchmark comparison with an mainstream x86-CPU, like the AMD A8 or a Phenom II X4 to see how fast those CPUs are in reality and if gaming would be an option, which I still doubt.
          Sure this would be nice. Maybe Michael get hardware to benchmark these CPUs.
          But one is for sure the Loongson is the most advance MIPS CPU on planet earth and in my point of view its also more advance than all ARM chips together.

          Comment


          • Originally posted by maldorordiscord View Post
            The source is the same you just don't read it because you don't want to pay 19 dollar. It took me 3 days to find a "pirate copy" edition to save you 19 dollar.
            And I'm sure these haters in this forum will ban me for showing you the truth.
            Rather strange that you have to find a pirated version of an article you already have. Also nice that you mentioned that this is a pirated version of that article, so that I could edit out the link from the quote I made to prevent damage to the forum due to copyright infringement.

            Comment


            • Originally posted by TobiSGD View Post
              Rather strange that you have to find a pirated version of an article you already have. Also nice that you mentioned that this is a pirated version of that article, so that I could edit out the link from the quote I made to prevent damage to the forum due to copyright infringement.
              LOL its funny you blame me for not showing you the source and after you consume the source for free because of my research about the article in the internet you blame me for copyright infringement.
              And no I don't had the article before I found the free one in the web.
              I just interpolated the information with logic based on a minimal basic information set.
              My argumentation was based on interpolating informations with logic.
              I told you already that I'm very good at thinking things complex.

              And interpolating informations in a unknown area is complex thinking

              Comment


              • Originally posted by maldorordiscord View Post
                LOL its funny you blame me for not showing you the source and after you consume the source for free because of my research about the article in the internet you blame me for copyright infringement.
                You do really think that this is funny? Yes, I blame you for copyright infringement, you posted a direct link to a PDF without stating that this is a pirated version of the copyrighted article you mentioned in an earlier post. That is exactly what copyright infringement means. With that you can damage Phoronix and every one that actually downloads that PDF.
                Nice, Sherlock, very nice.

                And no I don't had the article before I found the free one in the web.
                I just interpolated the information with logic based on a minimal basic information set.
                My argumentation was based on interpolating informations with logic.
                I told you already that I'm very good at thinking things complex.

                And interpolating informations in a unknown area is complex thinking
                Yeah, exactly, you can guess what is written in an technical article before reading it and then use it as proof for your facts without even knowing the content of the article. This is complex lying, not complex thinking.

                Comment


                • Originally posted by TobiSGD View Post
                  You do really think that this is funny? Yes, I blame you for copyright infringement, you posted a direct link to a PDF without stating that this is a pirated version of the copyrighted article you mentioned in an earlier post. That is exactly what copyright infringement means. With that you can damage Phoronix and every one that actually downloads that PDF.
                  Nice, Sherlock, very nice.
                  I'm so sorry you deserve it.

                  Originally posted by TobiSGD View Post
                  Yeah, exactly, you can guess what is written in an technical article before reading it and then use it as proof for your facts without even knowing the content of the article. This is complex lying, not complex thinking.
                  LOL "complex lying" but the original article cover my "complex lying" this turns it into Intellectual giftedness.
                  O man you are so simple in "Mind"
                  Compared to your simple-linear-thinking I'm really a High-Complex-Ingenious-genius.
                  You are pathetic limited.

                  Compared to you I'm a real Master of Mind.

                  Comment


                  • Originally posted by maldorordiscord View Post
                    I'm so sorry you deserve it.
                    You don't even know me, but think I would deserve it to be accused for copyright infringement for your stupid actions? And what is with the damage you may do to Phoronix with such actions? Does Michael deserve it also? You are a moron and I hope you will soon get banned, if not for being Qaridarium circumventing the moderator decisions then for such dumb actions.

                    LOL "complex lying" but the original article cover my "complex lying" this turns it into Intellectual giftedness.
                    O man you are so simple in "Mind"
                    Compared to your simple-linear-thinking I'm really a High-Complex-Ingenious-genius.
                    You are pathetic limited.

                    Compared to you I'm a real Master of Mind.
                    Only a third of your claims were proven to be right by that article. You have made 3 statements:
                    1. The Loongson 3 can emulate SSE in hardware.
                    2. It can handle 8 SSE instructions at a time.
                    3. It does this with 70% of native speed.
                    You have only proven number 1 to be true with this article. 33%. Mastermind? With having only 1 of 3 statements right? You are a master of overestimation of your own capabilities, but not a master of mind. You can't even do this simple math, but I am simple in mind, absolutely.
                    If one here is pathetic, it is definitely not me.

                    Comment


                    • Originally posted by TobiSGD View Post
                      You don't even know me, but think I would deserve it to be accused for copyright infringement for your stupid actions?
                      Stupid Actions? This depends on the objective. And your babbling prove that I reach my goal.
                      You worked hard for it to teach me who you are and what is your need.

                      Originally posted by TobiSGD View Post
                      And what is with the damage you may do to Phoronix with such actions? Does Michael deserve it also?
                      He is not liable for user-generated content.

                      Originally posted by TobiSGD View Post
                      You are a moron and I hope you will soon get banned, if not for being Qaridarium circumventing the moderator decisions then for such dumb actions.
                      Worth it!

                      Originally posted by TobiSGD View Post
                      Only a third of your claims were proven to be right by that article. You have made 3 statements:
                      1. The Loongson 3 can emulate SSE in hardware.
                      2. It can handle 8 SSE instructions at a time.
                      3. It does this with 70% of native speed.
                      You have only proven number 1 to be true with this article. 33%. Mastermind? With having only 1 of 3 statements right? You are a master of overestimation of your own capabilities, but not a master of mind. You can't even do this simple math, but I am simple in mind, absolutely.
                      If one here is pathetic, it is definitely not me.
                      If you read the article carefully the 3A do have 2piece of Vector-SIMD units with 128bit per core
                      This means the 3A can handle 2 SSE(64bit) instructions at the same time per core.
                      but the 3A do have 4 cores 4*2=8
                      But the 3B do have 2*256bit simd-vector units per core and the 3C do have 2*512bit vector-simd units.
                      the 3A can already handle 8 SSE instructions at a time with all cores together.
                      the 3C can handle 256 ---> 64bit-sse instructions at a time.....
                      but you will still claim that the loongson 3C can not handle 8 pieces of 64bit-SSE instructions at the same time...
                      This means I'm 66% right. And the last one "It does this with 70% of native speed." has no relevance right now because to validate this we need real hardware and more real benchmarks.

                      Comment


                      • Originally posted by maldorordiscord View Post
                        If you read the article carefully the 3A do have 2piece of Vector-SIMD units with 128bit per core
                        This means the 3A can handle 2 SSE(64bit) instructions at the same time per core.
                        but the 3A do have 4 cores 4*2=8
                        But the 3B do have 2*256bit simd-vector units per core and the 3C do have 2*512bit vector-simd units.
                        the 3A can already handle 8 SSE instructions at a time with all cores together.
                        the 3C can handle 256 ---> 64bit-sse instructions at a time.....
                        but you will still claim that the loongson 3C can not handle 8 pieces of 64bit-SSE instructions at the same time...
                        The one here claiming things are you. Here for example you claim that the Loongson can handle as much SSE instructions at a time as fit physically into the registers. Do you have any proof for that? The article does not say anything like that at all, so we are still at 33%, since the article doesn't deliver a proof for your claim. And I will not claim that it can't handle that, claiming things that are unknown is your part here. May be it can do that, but there is no proof for that given here from you.

                        And the last one "It does this with 70% of native speed." has no relevance right now because to validate this we need real hardware and more real benchmarks.
                        It doesn't matter at all if you have already run benchmarks on that hardware or not. You have claimed that it will run with 70% performance. Proof or admit that you made that up without having evidences, simple as that. This is not a church, this is a technical forum. If you can't proof your claims than they have no worth at all.

                        Comment


                        • Originally posted by TobiSGD View Post
                          The one here claiming things are you. Here for example you claim that the Loongson can handle as much SSE instructions at a time as fit physically into the registers. Do you have any proof for that? The article does not say anything like that at all, so we are still at 33%, since the article doesn't deliver a proof for your claim. And I will not claim that it can't handle that, claiming things that are unknown is your part here. May be it can do that, but there is no proof for that given here from you.
                          you really do have zero understanding what is a vector space and what is a simd unit.
                          First of all what is a vector Array data structure http://en.wikipedia.org/wiki/Array_data_structure
                          now you get it you can fill a big vector array data structure with small vector array data structures.
                          for the CPU it doesn't matter he can calculate it as 1 single vector array.
                          because SIMD means calculating all data in the same time in a loop-level parallelism.
                          http://en.wikipedia.org/wiki/Data_parallelism
                          this calculating of many small vector arrays is also called Parallel array http://en.wikipedia.org/wiki/Parallel_array

                          maybe now you get it. its the same with x86 cpus they also calculate 2 SSE instructions in a 128bit vector unit and 4 in a 256bit vector unit.

                          Originally posted by TobiSGD View Post
                          It doesn't matter at all if you have already run benchmarks on that hardware or not. You have claimed that it will run with 70% performance. Proof or admit that you made that up without having evidences, simple as that. This is not a church, this is a technical forum. If you can't proof your claims than they have no worth at all.
                          the time will show the truth we know the truth after michael do some real hardware benchmarks.

                          Comment


                          • Originally posted by maldorordiscord View Post
                            the time will show the truth we know the truth after michael do some real hardware benchmarks.
                            So you admit that you have no clue if your statement is true, finally. Has taken a long time.

                            Comment


                            • Originally posted by maldorordiscord View Post
                              you really do have zero understanding what is a vector space and what is a simd unit.
                              First of all what is a vector Array data structure http://en.wikipedia.org/wiki/Array_data_structure
                              now you get it you can fill a big vector array data structure with small vector array data structures.
                              for the CPU it doesn't matter he can calculate it as 1 single vector array.
                              because SIMD means calculating all data in the same time in a loop-level parallelism.
                              http://en.wikipedia.org/wiki/Data_parallelism
                              this calculating of many small vector arrays is also called Parallel array http://en.wikipedia.org/wiki/Parallel_array

                              maybe now you get it. its the same with x86 cpus they also calculate 2 SSE instructions in a 128bit vector unit and 4 in a 256bit vector unit.
                              x86 CPUs that have SSE registers don't need to emulate SSE, they can execute it natively. So you are absolutely sure that these emulation units can handle the same amount of data without having losses due to the emulation?

                              Comment


                              • Originally posted by TobiSGD View Post
                                x86 CPUs that have SSE registers don't need to emulate SSE, they can execute it natively. So you are absolutely sure that these emulation units can handle the same amount of data without having losses due to the emulation?
                                The loongson don't need to emulate SSE because the loongson can execute it natively !
                                The loongson losses speed but not in the moment of execute the vector stuff.
                                The loongson losses the speed by translating the format but that work comes before the executing.
                                An native x86 core just load the stuff and execute it means 2 steps the loongson do have 3 steps.
                                Load the stuff then translate the format and then execute it.
                                I hope its clear now.

                                The other side is the loongson 3A don't have SSE3,SSE4.2,AVX,FMA that and because of the lost of translating the format makes clear they don't have any chance to win any benchmark but its only because of the 100% Intel monopole abuse. Also the lag of PCI passthrough in the chip-set makes it complicated to use 3D acceleration in the Qemu windows emulation and Qemu can not handle wine-lib openGL pass-through like virtual-box this ends in the result that you can not play games with that cpu in the emulation right now ... But its not a cpu problem its a software and hardware (main-board chipset) problem

                                Comment

                                Working...
                                X