I just tried out this change. It seems like it works in that the simulator now decodes the instruction correctly, but I would have expected to get an unimplemented instruction crash, and I don't. Does gem5 just skip the instruction in this case?
On Fri, Oct 27, 2017 at 4:53 PM Gabe Black <[email protected]> wrote: > https://gem5-review.googlesource.com/c/public/gem5/+/5281 > > On Fri, Oct 27, 2017 at 1:18 PM, Gabe Black <[email protected]> wrote: > > > Actually, I remember implementing most if not all of SSE of some > > particular vintage, so those should work just fine. I even used a test > > program QEMU has to do some small amount of verification! :-) But > > unfortunately I think you're right that the AVX instructions which aren't > > also SSE instructions are basically unimplemented. They should be decoded > > properly however, so it's probably worth looking into why this one > wasn't. > > > > Gabe > > > > On Fri, Oct 27, 2017 at 1:07 PM, Sam Xi <[email protected]> wrote: > > > >> Ah, I see...I noticed a few commits involving decoding of VEX-prefix > >> instructions and so I assumed that AVX was supported. Or is the problem > >> that the decoding is supported to some degree but the actual execution > >> hasn't been implemented? > >> > >> For what I need to do at the moment, not having good x86 SIMD support > is a > >> bit of a pain but not a dealbreaker. > >> > >> On Fri, Oct 27, 2017 at 4:02 PM Jason Lowe-Power <[email protected]> > >> wrote: > >> > >> > Hey Sam, > >> > > >> > I've got some bad news... I don't think we've implemented any of the > AVX > >> > instructions in gem5. In fact, many of the SSE instructions are still > >> > unimplemented. > >> > > >> > Overall, the SIMD support for x86 is pretty awful, as of the last > time I > >> > checked (some can correct me if things have changed significantly). > It's > >> > much better for ARM. I believe most, if not all, of the NEON > >> instructions > >> > are implemented. > >> > > >> > It would be great for someone to tackle the SIMD instructions on x86! > In > >> > fact, since the ARM SIMD instructions were implemented there is a new > >> > vector register interface that we should migrate the x86 ISA to use. > >> It's > >> > possible that AMD has some of this code internally that's not pushed > out > >> > yet. Brad, Tony, care to comment? > >> > > >> > Sorry this isn't better news. This has been a pain point for me for a > >> > while, but I haven't had any time to work on it. > >> > > >> > Cheers, > >> > Jason > >> > > >> > On Fri, Oct 27, 2017 at 12:38 PM Sam Xi <[email protected]> > >> wrote: > >> > > >> > > Hi all, > >> > > > >> > > I ran into a problem today involving an incorrectly decoded AVX > >> > > instruction. Hoping someone can tell me of a workaround or a quick > fix > >> > > other than disabling AVX (unless that's the only solution). > >> > > > >> > > Here's a basic testcase. > >> > > > >> > > int main() { > >> > > float x; > >> > > __asm__("vxorps %0, %0, %0" : "=x"(x) : "x"(x) :); > >> > > > >> > > return x == 0; > >> > > } > >> > > > >> > > Compiled with gcc 5.4: > >> > > gcc -static -O3 -o test -mavx test.c > >> > > > >> > > Produces the following assembly: > >> > > > >> > > 00000000004005f0 <main>: > >> > > 4005f0: 66 0f ef c9 pxor xmm1,xmm1 > >> > > 4005f4: 31 c0 xor eax,eax > >> > > 4005f6: 66 0f ef c0 pxor xmm0,xmm0 > >> > > 4005fa: ba 00 00 00 00 mov edx,0x0 > >> > > 4005ff: c5 f8 57 c0 vxorps xmm0,xmm0,xmm0 > >> > > 400603: 0f 2e c1 ucomiss xmm0,xmm1 > >> > > 400606: 0f 9b c0 setnp al > >> > > 400609: 0f 45 c2 cmovne eax,edx > >> > > 40060c: c3 ret > >> > > 40060d: 0f 1f 00 nop DWORD PTR [rax] > >> > > > >> > > gem5 decodes the instruction as XORPS_XMM_M, instead of (something > >> more > >> > > like) VXORPS_XMM_XMM_XMM. This leads to a segfault in the simulated > >> > program > >> > > when it attempts to access an unmapped address > >> > > > >> > > Here is the relevant section of the debug trace. > >> > > > >> > > 416293000: system.cpu: Fetch > >> > > 416293000: system.cpu: Translating address 0x4005f0 > >> > > 416293000: system.cpu: Sending fetch for addr 0x4005f0(pa: 0x5f0) > >> > > 416293000: system.cpu: -- pkt addr: 0x5f0 > >> > > 416348000: system.cpu.icache_port: Received fetch response 0x5f0 > >> > > 416348000: system.cpu: Complete ICache Fetch for addr 0x5f0 > >> > > 416348000: global: Getting more bytes. > >> > > 416348000: global: Setting origPC to 0x4005f0 > >> > > 416348000: global: Found VEX two-byte prefix 0xc5. > >> > > 416348000: global: Found VEX opcode 0x57. > >> > > 416348000: global: Found modrm byte 0x57. > >> > > 416348000: global: Collecting 1 byte displacement, got 1 bytes. > >> > > 416348000: global: Collected displacement 0xffffffffffffffc9. > >> > > 416348000: global: Calculating the instruction size: basePC: > 0x4005f0 > >> > > offset: 0x4 origPC: 0x4005f0 size: 4 > >> > > 416348000: global: XORPS_XMM_M : ldfp: The address is > >> 0xffffffffffffffca > >> > > 416348000: system.cpu: Fault occured, scheduling fetch event > >> > > panic: Tried to read unmapped address 0xffffffffffffffca. > >> > > > >> > > > >> > > Toolchain information > >> > > ===================== > >> > > > >> > > samxi $ gcc --version > >> > > gcc (Ubuntu 5.4.0-6ubuntu1~16.04.5) 5.4.0 20160609 > >> > > > >> > > > >> > > samxi $ as --version > >> > > GNU assembler (GNU Binutils for Ubuntu) 2.26.1 > >> > > > >> > > gem5 revision: e79c4c6f033581f84072ddb45d2ec9543c31af55 > >> > > > >> > > Thanks, > >> > > Sam > >> > > > >> > > -- > >> > > Thanks, > >> > > > >> > > Sam Xi > >> > > Harvard University > >> > > Computer Science, Ph.D. Candidate > >> > > http://www.samxi.org > >> > > _______________________________________________ > >> > > gem5-dev mailing list > >> > > [email protected] > >> > > http://m5sim.org/mailman/listinfo/gem5-dev > >> > _______________________________________________ > >> > gem5-dev mailing list > >> > [email protected] > >> > http://m5sim.org/mailman/listinfo/gem5-dev > >> > >> -- > >> Thanks, > >> > >> Sam Xi > >> Harvard University > >> Computer Science, Ph.D. Candidate > >> http://www.samxi.org > >> _______________________________________________ > >> gem5-dev mailing list > >> [email protected] > >> http://m5sim.org/mailman/listinfo/gem5-dev > >> > > > > > _______________________________________________ > gem5-dev mailing list > [email protected] > http://m5sim.org/mailman/listinfo/gem5-dev -- Thanks, Sam Xi Harvard University Computer Science, Ph.D. Candidate http://www.samxi.org _______________________________________________ gem5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/gem5-dev
