Function: hypre_BoomerAMGBuildMultipass._omp_fn.0 | Module: exec | Source: par_multi_interp.c:272-276 | Coverage: 0.01% |
---|
Function: hypre_BoomerAMGBuildMultipass._omp_fn.0 | Module: exec | Source: par_multi_interp.c:272-276 | Coverage: 0.01% |
---|
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 272 - 276 |
-------------------------------------------------------------------------------- |
272: #pragma omp parallel for private(i) reduction(+:n_coarse,n_SF ) HYPRE_SMP_SCHEDULE |
273: #endif |
274: for (i=0; i < n_fine; i++) |
275: if (CF_marker[i] == 1) n_coarse++; |
276: else if (CF_marker[i] == -3) n_SF++; |
0x474950 PUSH %RBP |
0x474951 MOV %RSP,%RBP |
0x474954 PUSH %R13 |
0x474956 PUSH %R12 |
0x474958 PUSH %RBX |
0x474959 MOV %RDI,%RBX |
0x47495c AND $-0x40,%RSP |
0x474960 SUB $0x40,%RSP |
0x474964 MOV (%RDI),%R12 |
0x474967 CALL 40f0b0 <omp_get_num_threads@plt> |
0x47496c MOV %EAX,%R13D |
0x47496f CALL 40f1f0 <omp_get_thread_num@plt> |
0x474974 MOVSXD %R13D,%RSI |
0x474977 MOVSXD %EAX,%RCX |
0x47497a MOV 0x8(%RBX),%RAX |
0x47497e CQTO |
0x474980 IDIV %RSI |
0x474983 CMP %RDX,%RCX |
0x474986 JL 474ed0 |
0x47498c IMUL %RAX,%RCX |
0x474990 VPXOR %XMM3,%XMM3,%XMM3 |
0x474994 ADD %RCX,%RDX |
0x474997 LEA (%RAX,%RDX,1),%RDI |
0x47499b CMP %RDI,%RDX |
0x47499e JGE 474e9c |
0x4749a4 LEA -0x1(%RAX),%R9 |
0x4749a8 MOV %RDX,%R8 |
0x4749ab CMP $0x6,%R9 |
0x4749af JBE 474ee8 |
0x4749b5 MOV %RAX,%RCX |
0x4749b8 LEA (%R12,%RDX,8),%R13 |
0x4749bc VPXOR %XMM0,%XMM0,%XMM0 |
0x4749c0 MOV $0x1,%ESI |
0x4749c5 SHR $0x3,%RCX |
0x4749c9 VMOVDQA64 %ZMM0,%ZMM2 |
0x4749cf VPBROADCASTQ %RSI,%ZMM5 |
0x4749d5 MOV $-0x3,%R9 |
0x4749dc SAL $0x6,%RCX |
0x4749e0 VPTERNLOGD $-0x1,%ZMM3,%ZMM3,%ZMM3 |
0x4749e7 VPBROADCASTQ %R9,%ZMM4 |
0x4749ed LEA (%RCX,%R13,1),%R10 |
0x4749f1 SUB $0x40,%RCX |
0x4749f5 SHR $0x6,%RCX |
0x4749f9 INC %RCX |
0x4749fc AND $0x7,%ECX |
0x4749ff JE 474b99 |
0x474a05 CMP $0x1,%RCX |
0x474a09 JE 474b5f |
0x474a0f CMP $0x2,%RCX |
0x474a13 JE 474b2e |
0x474a19 CMP $0x3,%RCX |
0x474a1d JE 474afd |
0x474a23 CMP $0x4,%RCX |
0x474a27 JE 474acc |
0x474a2d CMP $0x5,%RCX |
0x474a31 JE 474a9b |
0x474a33 CMP $0x6,%RCX |
0x474a37 JE 474a6a |
0x474a39 VMOVDQU64 (%R13),%ZMM6 |
0x474a40 ADD $0x40,%R13 |
0x474a44 VPCMPEQQ %ZMM5,%ZMM6,%K1 |
0x474a4b VPCMPEQQ %ZMM4,%ZMM6,%K2 |
0x474a52 VMOVDQA64 %ZMM3,%ZMM2{%K1}{z} |
0x474a58 VMOVDQA64 %ZMM3,%ZMM7{%K2}{z} |
0x474a5e VPSUBQ %ZMM2,%ZMM0,%ZMM2 |
0x474a64 VPSUBQ %ZMM7,%ZMM0,%ZMM0 |
0x474a6a VMOVDQU64 (%R13),%ZMM8 |
0x474a71 ADD $0x40,%R13 |
0x474a75 VPCMPEQQ %ZMM5,%ZMM8,%K3 |
0x474a7c VPCMPEQQ %ZMM4,%ZMM8,%K4 |
0x474a83 VMOVDQA64 %ZMM3,%ZMM9{%K3}{z} |
0x474a89 VMOVDQA64 %ZMM3,%ZMM10{%K4}{z} |
0x474a8f VPSUBQ %ZMM9,%ZMM2,%ZMM2 |
0x474a95 VPSUBQ %ZMM10,%ZMM0,%ZMM0 |
0x474a9b VMOVDQU64 (%R13),%ZMM11 |
0x474aa2 ADD $0x40,%R13 |
0x474aa6 VPCMPEQQ %ZMM5,%ZMM11,%K5 |
0x474aad VPCMPEQQ %ZMM4,%ZMM11,%K6 |
0x474ab4 VMOVDQA64 %ZMM3,%ZMM12{%K5}{z} |
0x474aba VMOVDQA64 %ZMM3,%ZMM13{%K6}{z} |
0x474ac0 VPSUBQ %ZMM12,%ZMM2,%ZMM2 |
0x474ac6 VPSUBQ %ZMM13,%ZMM0,%ZMM0 |
0x474acc VMOVDQU64 (%R13),%ZMM14 |
0x474ad3 ADD $0x40,%R13 |
0x474ad7 VPCMPEQQ %ZMM5,%ZMM14,%K7 |
0x474ade VPCMPEQQ %ZMM4,%ZMM14,%K1 |
0x474ae5 VMOVDQA64 %ZMM3,%ZMM15{%K7}{z} |
0x474aeb VMOVDQA64 %ZMM3,%ZMM1{%K1}{z} |
0x474af1 VPSUBQ %ZMM15,%ZMM2,%ZMM2 |
0x474af7 VPSUBQ %ZMM1,%ZMM0,%ZMM0 |
0x474afd VMOVDQU64 (%R13),%ZMM7 |
0x474b04 ADD $0x40,%R13 |
0x474b08 VPCMPEQQ %ZMM5,%ZMM7,%K2 |
0x474b0f VPCMPEQQ %ZMM4,%ZMM7,%K3 |
0x474b16 VMOVDQA64 %ZMM3,%ZMM6{%K2}{z} |
0x474b1c VMOVDQA64 %ZMM3,%ZMM8{%K3}{z} |
0x474b22 VPSUBQ %ZMM6,%ZMM2,%ZMM2 |
0x474b28 VPSUBQ %ZMM8,%ZMM0,%ZMM0 |
0x474b2e VMOVDQU64 (%R13),%ZMM9 |
0x474b35 ADD $0x40,%R13 |
0x474b39 VPCMPEQQ %ZMM5,%ZMM9,%K4 |
0x474b40 VPCMPEQQ %ZMM4,%ZMM9,%K5 |
0x474b47 VMOVDQA64 %ZMM3,%ZMM10{%K4}{z} |
0x474b4d VMOVDQA64 %ZMM3,%ZMM11{%K5}{z} |
0x474b53 VPSUBQ %ZMM10,%ZMM2,%ZMM2 |
0x474b59 VPSUBQ %ZMM11,%ZMM0,%ZMM0 |
0x474b5f VMOVDQU64 (%R13),%ZMM12 |
0x474b66 ADD $0x40,%R13 |
0x474b6a VPCMPEQQ %ZMM5,%ZMM12,%K6 |
0x474b71 VPCMPEQQ %ZMM4,%ZMM12,%K7 |
0x474b78 VMOVDQA64 %ZMM3,%ZMM13{%K6}{z} |
0x474b7e VMOVDQA64 %ZMM3,%ZMM14{%K7}{z} |
0x474b84 VPSUBQ %ZMM13,%ZMM2,%ZMM2 |
0x474b8a VPSUBQ %ZMM14,%ZMM0,%ZMM0 |
0x474b90 CMP %R10,%R13 |
0x474b93 JE 474d11 |
(684) 0x474b99 VMOVDQU64 (%R13),%ZMM15 |
(684) 0x474ba0 VMOVDQU64 0x40(%R13),%ZMM9 |
(684) 0x474ba7 ADD $0x200,%R13 |
(684) 0x474bae VPCMPEQQ %ZMM5,%ZMM15,%K1 |
(684) 0x474bb5 VPCMPEQQ %ZMM4,%ZMM15,%K2 |
(684) 0x474bbc VPCMPEQQ %ZMM4,%ZMM9,%K4 |
(684) 0x474bc3 VPCMPEQQ %ZMM5,%ZMM9,%K3 |
(684) 0x474bca VMOVDQA64 %ZMM3,%ZMM1{%K1}{z} |
(684) 0x474bd0 VMOVDQA64 %ZMM3,%ZMM6{%K2}{z} |
(684) 0x474bd6 VPSUBQ %ZMM1,%ZMM2,%ZMM7 |
(684) 0x474bdc VPSUBQ %ZMM6,%ZMM0,%ZMM8 |
(684) 0x474be2 VMOVDQU64 -0x180(%R13),%ZMM2 |
(684) 0x474be9 VMOVDQA64 %ZMM3,%ZMM12{%K4}{z} |
(684) 0x474bef VPSUBQ %ZMM12,%ZMM8,%ZMM13 |
(684) 0x474bf5 VMOVDQU64 -0x140(%R13),%ZMM8 |
(684) 0x474bfc VMOVDQA64 %ZMM3,%ZMM10{%K3}{z} |
(684) 0x474c02 VPCMPEQQ %ZMM5,%ZMM2,%K5 |
(684) 0x474c09 VPCMPEQQ %ZMM4,%ZMM2,%K6 |
(684) 0x474c10 VPSUBQ %ZMM10,%ZMM7,%ZMM11 |
(684) 0x474c16 VPCMPEQQ %ZMM5,%ZMM8,%K7 |
(684) 0x474c1d VPCMPEQQ %ZMM4,%ZMM8,%K1 |
(684) 0x474c24 VMOVDQA64 %ZMM3,%ZMM14{%K5}{z} |
(684) 0x474c2a VMOVDQA64 %ZMM3,%ZMM0{%K6}{z} |
(684) 0x474c30 VPSUBQ %ZMM14,%ZMM11,%ZMM15 |
(684) 0x474c36 VMOVDQA64 %ZMM3,%ZMM1{%K7}{z} |
(684) 0x474c3c VMOVDQU64 -0x100(%R13),%ZMM11 |
(684) 0x474c43 VPSUBQ %ZMM0,%ZMM13,%ZMM7 |
(684) 0x474c49 VPSUBQ %ZMM1,%ZMM15,%ZMM9 |
(684) 0x474c4f VMOVDQU64 -0xc0(%R13),%ZMM15 |
(684) 0x474c56 VMOVDQA64 %ZMM3,%ZMM6{%K1}{z} |
(684) 0x474c5c VPCMPEQQ %ZMM5,%ZMM11,%K2 |
(684) 0x474c63 VPCMPEQQ %ZMM4,%ZMM11,%K3 |
(684) 0x474c6a VPSUBQ %ZMM6,%ZMM7,%ZMM10 |
(684) 0x474c70 VPCMPEQQ %ZMM5,%ZMM15,%K4 |
(684) 0x474c77 VPCMPEQQ %ZMM4,%ZMM15,%K5 |
(684) 0x474c7e VMOVDQA64 %ZMM3,%ZMM12{%K2}{z} |
(684) 0x474c84 VMOVDQA64 %ZMM3,%ZMM2{%K3}{z} |
(684) 0x474c8a VPSUBQ %ZMM12,%ZMM9,%ZMM13 |
(684) 0x474c90 VPSUBQ %ZMM2,%ZMM10,%ZMM14 |
(684) 0x474c96 VMOVDQA64 %ZMM3,%ZMM0{%K4}{z} |
(684) 0x474c9c VMOVDQU64 -0x80(%R13),%ZMM10 |
(684) 0x474ca3 VPSUBQ %ZMM0,%ZMM13,%ZMM7 |
(684) 0x474ca9 VMOVDQU64 -0x40(%R13),%ZMM13 |
(684) 0x474cb0 VMOVDQA64 %ZMM3,%ZMM8{%K5}{z} |
(684) 0x474cb6 VPCMPEQQ %ZMM5,%ZMM10,%K6 |
(684) 0x474cbd VPCMPEQQ %ZMM4,%ZMM10,%K7 |
(684) 0x474cc4 VPSUBQ %ZMM8,%ZMM14,%ZMM9 |
(684) 0x474cca VPCMPEQQ %ZMM5,%ZMM13,%K1 |
(684) 0x474cd1 VPCMPEQQ %ZMM4,%ZMM13,%K2 |
(684) 0x474cd8 VMOVDQA64 %ZMM3,%ZMM1{%K6}{z} |
(684) 0x474cde VMOVDQA64 %ZMM3,%ZMM6{%K7}{z} |
(684) 0x474ce4 VPSUBQ %ZMM1,%ZMM7,%ZMM11 |
(684) 0x474cea VPSUBQ %ZMM6,%ZMM9,%ZMM12 |
(684) 0x474cf0 VMOVDQA64 %ZMM3,%ZMM2{%K1}{z} |
(684) 0x474cf6 VMOVDQA64 %ZMM3,%ZMM14{%K2}{z} |
(684) 0x474cfc VPSUBQ %ZMM2,%ZMM11,%ZMM2 |
(684) 0x474d02 VPSUBQ %ZMM14,%ZMM12,%ZMM0 |
(684) 0x474d08 CMP %R10,%R13 |
(684) 0x474d0b JNE 474b99 |
0x474d11 VEXTRACTI64X4 $0x1,%ZMM0,%YMM3 |
0x474d18 VEXTRACTI64X4 $0x1,%ZMM2,%YMM10 |
0x474d1f MOV %RAX,%R11 |
0x474d22 VPADDQ %YMM3,%YMM0,%YMM1 |
0x474d26 AND $-0x8,%R11 |
0x474d2a VEXTRACTI64X2 $0x1,%YMM1,%XMM15 |
0x474d31 ADD %R11,%RDX |
0x474d34 VPADDQ %XMM15,%XMM1,%XMM0 |
0x474d39 VPSRLDQ $0x8,%XMM0,%XMM7 |
0x474d3e VPADDQ %XMM7,%XMM0,%XMM8 |
0x474d42 VPADDQ %YMM10,%YMM2,%YMM0 |
0x474d47 VEXTRACTI64X2 $0x1,%YMM0,%XMM6 |
0x474d4e VMOVQ %XMM8,%RCX |
0x474d53 VPADDQ %XMM6,%XMM0,%XMM12 |
0x474d57 VPSRLDQ $0x8,%XMM12,%XMM13 |
0x474d5d VPADDQ %XMM13,%XMM12,%XMM2 |
0x474d62 VMOVQ %XMM2,%R10 |
0x474d67 CMP %R11,%RAX |
0x474d6a JE 474e8e |
0x474d70 SUB %R11,%RAX |
0x474d73 LEA -0x1(%RAX),%R13 |
0x474d77 CMP $0x3,%R13 |
0x474d7b JBE 474df7 |
0x474d7d ADD %R8,%R11 |
0x474d80 MOV $0x1,%R8D |
0x474d86 VMOVDQU (%R12,%R11,8),%YMM14 |
0x474d8c VPBROADCASTQ %R8,%YMM5 |
0x474d92 MOV $-0x3,%R11 |
0x474d99 VPBROADCASTQ %R11,%YMM15 |
0x474d9f VPCMPEQQ %YMM5,%YMM14,%YMM3 |
0x474da4 VPSUBQ %YMM3,%YMM0,%YMM4 |
0x474da8 VPCMPEQQ %YMM15,%YMM14,%YMM0 |
0x474dad VEXTRACTI64X2 $0x1,%YMM4,%XMM12 |
0x474db4 VPADDQ %XMM12,%XMM4,%XMM13 |
0x474db9 VPSUBQ %YMM0,%YMM1,%YMM1 |
0x474dbd VPSRLDQ $0x8,%XMM13,%XMM2 |
0x474dc3 VEXTRACTI64X2 $0x1,%YMM1,%XMM8 |
0x474dca VPADDQ %XMM2,%XMM13,%XMM14 |
0x474dce VPADDQ %XMM8,%XMM1,%XMM9 |
0x474dd3 VMOVQ %XMM14,%R10 |
0x474dd8 VPSRLDQ $0x8,%XMM9,%XMM10 |
0x474dde VPADDQ %XMM10,%XMM9,%XMM11 |
0x474de3 VMOVQ %XMM11,%RCX |
0x474de8 TEST $0x3,%AL |
0x474dea JE 474e8e |
0x474df0 AND $-0x4,%RAX |
0x474df4 ADD %RAX,%RDX |
0x474df7 MOV (%R12,%RDX,8),%RAX |
0x474dfb LEA (,%RDX,8),%RSI |
0x474e03 CMP $0x1,%RAX |
0x474e07 JE 474f00 |
0x474e0d CMP $-0x3,%RAX |
0x474e11 SETE %R9B |
0x474e15 MOVZX %R9B,%R13D |
0x474e19 ADD %R13,%RCX |
0x474e1c LEA 0x1(%RDX),%R8 |
0x474e20 CMP %R8,%RDI |
0x474e23 JLE 474e8e |
0x474e25 MOV 0x8(%R12,%RSI,1),%R11 |
0x474e2a CMP $0x1,%R11 |
0x474e2e JE 474f10 |
0x474e34 CMP $-0x3,%R11 |
0x474e38 SETE %AL |
0x474e3b MOVZX %AL,%R9D |
0x474e3f ADD %R9,%RCX |
0x474e42 LEA 0x2(%RDX),%R13 |
0x474e46 CMP %R13,%RDI |
0x474e49 JLE 474e8e |
0x474e4b MOV 0x10(%R12,%RSI,1),%R8 |
0x474e50 CMP $0x1,%R8 |
0x474e54 JE 474ee0 |
0x474e5a CMP $-0x3,%R8 |
0x474e5e SETE %R11B |
0x474e62 MOVZX %R11B,%EAX |
0x474e66 ADD %RAX,%RCX |
0x474e69 ADD $0x3,%RDX |
0x474e6d CMP %RDX,%RDI |
0x474e70 JLE 474e8e |
0x474e72 MOV 0x18(%R12,%RSI,1),%R12 |
0x474e77 CMP $0x1,%R12 |
0x474e7b JE 474f20 |
0x474e81 CMP $-0x3,%R12 |
0x474e85 SETE %DL |
0x474e88 MOVZX %DL,%EDI |
0x474e8b ADD %RDI,%RCX |
0x474e8e VMOVQ %RCX,%XMM5 |
0x474e93 VPINSRQ $0x1,%R10,%XMM5,%XMM3 |
0x474e99 VZEROUPPER |
0x474e9c VMOVDQA %XMM3,0x30(%RSP) |
0x474ea2 CALL 40f2d0 <GOMP_atomic_start@plt> |
0x474ea7 VMOVDQA 0x30(%RSP),%XMM4 |
0x474ead VPADDQ 0x10(%RBX),%XMM4,%XMM15 |
0x474eb2 VMOVDQU %XMM15,0x10(%RBX) |
0x474eb7 LEA -0x18(%RBP),%RSP |
0x474ebb POP %RBX |
0x474ebc POP %R12 |
0x474ebe POP %R13 |
0x474ec0 POP %RBP |
0x474ec1 JMP 40f260 |
0x474ec6 NOPW %CS:(%RAX,%RAX,1) |
0x474ed0 INC %RAX |
0x474ed3 XOR %EDX,%EDX |
0x474ed5 JMP 47498c |
0x474eda NOPW (%RAX,%RAX,1) |
0x474ee0 INC %R10 |
0x474ee3 JMP 474e69 |
0x474ee5 NOPL (%RAX) |
0x474ee8 VPXOR %XMM1,%XMM1,%XMM1 |
0x474eec XOR %R11D,%R11D |
0x474eef XOR %ECX,%ECX |
0x474ef1 XOR %R10D,%R10D |
0x474ef4 VMOVDQA %YMM1,%YMM0 |
0x474ef8 JMP 474d70 |
0x474efd NOPL (%RAX) |
0x474f00 INC %R10 |
0x474f03 JMP 474e1c |
0x474f08 NOPL (%RAX,%RAX,1) |
0x474f10 INC %R10 |
0x474f13 JMP 474e42 |
0x474f18 NOPL (%RAX,%RAX,1) |
0x474f20 INC %R10 |
0x474f23 JMP 474e8e |
0x474f28 NOPL (%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○100.00 | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | par_multi_interp.c:272-276 |
Module | exec |
nb instructions | 239 |
nb uops | 302 |
loop length | 1128 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 16 |
used ymm registers | 9 |
used zmm registers | 16 |
nb stack references | 2 |
micro-operation queue | 75.50 cycles |
front end | 75.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 57.50 | 57.50 | 10.00 | 10.00 | 9.00 | 57.50 | 57.50 | 9.00 |
cycles | 57.50 | 57.50 | 10.00 | 10.00 | 9.00 | 57.50 | 57.50 | 9.00 |
Cycles executing div or sqrt instructions | 24.00-90.00 |
FE+BE cycles | 60.96-104.55 |
Stall cycles | 0.00-43.50 |
Front-end | 75.50 |
Dispatch | 57.50 |
DIV/SQRT | 24.00-90.00 |
Overall L1 | 75.50-90.00 |
all | 68% |
load | 90% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 55% |
all | 53% |
load | 73% |
store | 25% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 67% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 47% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x40,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0x40,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV (%RDI),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 40f0b0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %EAX,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 40f1f0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD %R13D,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVSXD %EAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x8(%RBX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IDIV %RSI | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JL 474ed0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
IMUL %RAX,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXOR %XMM3,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %RCX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RAX,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 474e9c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RAX),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP $0x6,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JBE 474ee8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA (%R12,%RDX,8),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x1,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x3,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMOVDQA64 %ZMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPBROADCASTQ %RSI,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV $-0x3,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SAL $0x6,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VPTERNLOGD $-0x1,%ZMM3,%ZMM3,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPBROADCASTQ %R9,%ZMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%RCX,%R13,1),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB $0x40,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x6,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x7,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474b99 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474b5f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474b2e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x3,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474afd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474acc | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x5,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474a9b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x6,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474a6a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVDQU64 (%R13),%ZMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM6,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM6,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM2{%K1}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM7{%K2}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM2,%ZMM0,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM7,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM8,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM8,%K4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM9{%K3}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM10{%K4}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM9,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM10,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM11,%K5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM11,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM12{%K5}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM13{%K6}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM12,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM13,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM14,%K7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM14,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM15{%K7}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM1{%K1}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM15,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM1,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM7,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM7,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM6{%K2}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM8{%K3}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM6,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM8,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM9,%K4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM9,%K5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM10{%K4}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM11{%K5}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM10,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM11,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM12,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM12,%K7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM13{%K6}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM14{%K7}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM13,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM14,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R10,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474d11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VEXTRACTI64X4 $0x1,%ZMM0,%YMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VEXTRACTI64X4 $0x1,%ZMM2,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
MOV %RAX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPADDQ %YMM3,%YMM0,%YMM1 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
AND $-0x8,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VEXTRACTI64X2 $0x1,%YMM1,%XMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
ADD %R11,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPADDQ %XMM15,%XMM1,%XMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSRLDQ $0x8,%XMM0,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ %XMM7,%XMM0,%XMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPADDQ %YMM10,%YMM2,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VEXTRACTI64X2 $0x1,%YMM0,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVQ %XMM8,%RCX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
VPADDQ %XMM6,%XMM0,%XMM12 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSRLDQ $0x8,%XMM12,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ %XMM13,%XMM12,%XMM2 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM2,%R10 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
CMP %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
SUB %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x1(%RAX),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP $0x3,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JBE 474df7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %R8,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%R8D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVDQU (%R12,%R11,8),%YMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VPBROADCASTQ %R8,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV $-0x3,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPBROADCASTQ %R11,%YMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %YMM5,%YMM14,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPSUBQ %YMM3,%YMM0,%YMM4 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPCMPEQQ %YMM15,%YMM14,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VEXTRACTI64X2 $0x1,%YMM4,%XMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDQ %XMM12,%XMM4,%XMM13 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSUBQ %YMM0,%YMM1,%YMM1 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSRLDQ $0x8,%XMM13,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VEXTRACTI64X2 $0x1,%YMM1,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDQ %XMM2,%XMM13,%XMM14 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPADDQ %XMM8,%XMM1,%XMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM14,%R10 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
VPSRLDQ $0x8,%XMM9,%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ %XMM10,%XMM9,%XMM11 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM11,%RCX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
TEST $0x3,%AL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV (%R12,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (,%RDX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP $0x1,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474f00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $-0x3,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %R9B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVZX %R9B,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %R13,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x1(%RDX),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R8,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x8(%R12,%RSI,1),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x1,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474f10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $-0x3,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %AL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVZX %AL,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %R9,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x2(%RDX),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R13,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x10(%R12,%RSI,1),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x1,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474ee0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $-0x3,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %R11B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVZX %R11B,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x3,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x18(%R12,%RSI,1),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x1,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474f20 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $-0x3,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %DL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVZX %DL,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %RDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVQ %RCX,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPINSRQ $0x1,%R10,%XMM5,%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 2 | 0 | 0 | 3 | 2 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VMOVDQA %XMM3,0x30(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 4 | 1 |
CALL 40f2d0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVDQA 0x30(%RSP),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPADDQ 0x10(%RBX),%XMM4,%XMM15 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
VMOVDQU %XMM15,0x10(%RBX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 4 | 1 |
LEA -0x18(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
JMP 40f260 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 47498c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 474e69 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPXOR %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA %YMM1,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 474d70 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 474e1c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 474e42 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 474e8e | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | par_multi_interp.c:272-276 |
Module | exec |
nb instructions | 239 |
nb uops | 302 |
loop length | 1128 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 16 |
used ymm registers | 9 |
used zmm registers | 16 |
nb stack references | 2 |
micro-operation queue | 75.50 cycles |
front end | 75.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 57.50 | 57.50 | 10.00 | 10.00 | 9.00 | 57.50 | 57.50 | 9.00 |
cycles | 57.50 | 57.50 | 10.00 | 10.00 | 9.00 | 57.50 | 57.50 | 9.00 |
Cycles executing div or sqrt instructions | 24.00-90.00 |
FE+BE cycles | 60.96-104.55 |
Stall cycles | 0.00-43.50 |
Front-end | 75.50 |
Dispatch | 57.50 |
DIV/SQRT | 24.00-90.00 |
Overall L1 | 75.50-90.00 |
all | 68% |
load | 90% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 55% |
all | 53% |
load | 73% |
store | 25% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 67% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 47% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x40,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0x40,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV (%RDI),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 40f0b0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %EAX,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 40f1f0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD %R13D,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVSXD %EAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x8(%RBX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IDIV %RSI | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JL 474ed0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
IMUL %RAX,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXOR %XMM3,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %RCX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RAX,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 474e9c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RAX),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP $0x6,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JBE 474ee8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA (%R12,%RDX,8),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x1,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x3,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMOVDQA64 %ZMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPBROADCASTQ %RSI,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV $-0x3,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SAL $0x6,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VPTERNLOGD $-0x1,%ZMM3,%ZMM3,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPBROADCASTQ %R9,%ZMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%RCX,%R13,1),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB $0x40,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x6,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x7,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474b99 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474b5f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474b2e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x3,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474afd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474acc | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x5,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474a9b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x6,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474a6a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVDQU64 (%R13),%ZMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM6,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM6,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM2{%K1}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM7{%K2}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM2,%ZMM0,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM7,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM8,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM8,%K4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM9{%K3}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM10{%K4}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM9,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM10,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM11,%K5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM11,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM12{%K5}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM13{%K6}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM12,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM13,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM14,%K7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM14,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM15{%K7}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM1{%K1}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM15,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM1,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM7,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM7,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM6{%K2}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM8{%K3}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM6,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM8,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM9,%K4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM9,%K5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM10{%K4}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM11{%K5}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM10,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM11,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVDQU64 (%R13),%ZMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
ADD $0x40,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPCMPEQQ %ZMM5,%ZMM12,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %ZMM4,%ZMM12,%K7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDQA64 %ZMM3,%ZMM13{%K6}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA64 %ZMM3,%ZMM14{%K7}{z} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPSUBQ %ZMM13,%ZMM2,%ZMM2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPSUBQ %ZMM14,%ZMM0,%ZMM0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R10,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474d11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VEXTRACTI64X4 $0x1,%ZMM0,%YMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VEXTRACTI64X4 $0x1,%ZMM2,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
MOV %RAX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPADDQ %YMM3,%YMM0,%YMM1 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
AND $-0x8,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VEXTRACTI64X2 $0x1,%YMM1,%XMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
ADD %R11,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPADDQ %XMM15,%XMM1,%XMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSRLDQ $0x8,%XMM0,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ %XMM7,%XMM0,%XMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPADDQ %YMM10,%YMM2,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VEXTRACTI64X2 $0x1,%YMM0,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVQ %XMM8,%RCX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
VPADDQ %XMM6,%XMM0,%XMM12 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSRLDQ $0x8,%XMM12,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ %XMM13,%XMM12,%XMM2 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM2,%R10 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
CMP %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
SUB %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x1(%RAX),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP $0x3,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JBE 474df7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %R8,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%R8D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVDQU (%R12,%R11,8),%YMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VPBROADCASTQ %R8,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV $-0x3,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPBROADCASTQ %R11,%YMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPCMPEQQ %YMM5,%YMM14,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPSUBQ %YMM3,%YMM0,%YMM4 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPCMPEQQ %YMM15,%YMM14,%YMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VEXTRACTI64X2 $0x1,%YMM4,%XMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDQ %XMM12,%XMM4,%XMM13 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSUBQ %YMM0,%YMM1,%YMM1 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSRLDQ $0x8,%XMM13,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VEXTRACTI64X2 $0x1,%YMM1,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDQ %XMM2,%XMM13,%XMM14 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPADDQ %XMM8,%XMM1,%XMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM14,%R10 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
VPSRLDQ $0x8,%XMM9,%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ %XMM10,%XMM9,%XMM11 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM11,%RCX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
TEST $0x3,%AL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV (%R12,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (,%RDX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP $0x1,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474f00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $-0x3,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %R9B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVZX %R9B,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %R13,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x1(%RDX),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R8,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x8(%R12,%RSI,1),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x1,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474f10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $-0x3,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %AL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVZX %AL,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %R9,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x2(%RDX),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R13,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x10(%R12,%RSI,1),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x1,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474ee0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $-0x3,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %R11B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVZX %R11B,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x3,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 474e8e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x18(%R12,%RSI,1),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x1,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 474f20 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $-0x3,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %DL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVZX %DL,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %RDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVQ %RCX,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPINSRQ $0x1,%R10,%XMM5,%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 2 | 0 | 0 | 3 | 2 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VMOVDQA %XMM3,0x30(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 4 | 1 |
CALL 40f2d0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVDQA 0x30(%RSP),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPADDQ 0x10(%RBX),%XMM4,%XMM15 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
VMOVDQU %XMM15,0x10(%RBX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 4 | 1 |
LEA -0x18(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
JMP 40f260 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 47498c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 474e69 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPXOR %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQA %YMM1,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 474d70 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 474e1c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 474e42 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 474e8e | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼hypre_BoomerAMGBuildMultipass._omp_fn.0– | 0.01 | 0.01 |
○Loop 684 - par_multi_interp.c:275-276 - exec | 0.01 | 0.01 |