Function: hypre_CSRMatrixMatvecOutOfPlace.extracted | Module: exec | Source: csr_matvec.c:243-404 [...] | Coverage: 58.13% |
---|
Function: hypre_CSRMatrixMatvecOutOfPlace.extracted | Module: exec | Source: csr_matvec.c:243-404 [...] | Coverage: 58.13% |
---|
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 243 - 404 |
-------------------------------------------------------------------------------- |
243: #pragma omp parallel private(i,jj,tempx) |
244: #endif |
245: { |
246: HYPRE_Int iBegin = hypre_CSRMatrixGetLoadBalancedPartitionBegin(A); |
247: HYPRE_Int iEnd = hypre_CSRMatrixGetLoadBalancedPartitionEnd(A); |
248: hypre_assert(iBegin <= iEnd); |
249: hypre_assert(iBegin >= 0 && iBegin <= num_rows); |
250: hypre_assert(iEnd >= 0 && iEnd <= num_rows); |
251: |
252: if (0 == temp) |
253: { |
254: if (1 == alpha) // JSP: a common path |
255: { |
256: for (i = iBegin; i < iEnd; i++) |
257: { |
258: tempx = 0.0; |
259: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
260: { |
261: tempx += A_data[jj] * x_data[A_j[jj]]; |
262: } |
263: y_data[i] = tempx; |
264: } |
265: } // y = A*x |
266: else if (-1 == alpha) |
267: { |
268: for (i = iBegin; i < iEnd; i++) |
269: { |
270: tempx = 0.0; |
271: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
272: { |
273: tempx -= A_data[jj] * x_data[A_j[jj]]; |
274: } |
275: y_data[i] = tempx; |
276: } |
277: } // y = -A*x |
278: else |
279: { |
280: for (i = iBegin; i < iEnd; i++) |
281: { |
282: tempx = 0.0; |
283: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
284: { |
285: tempx += A_data[jj] * x_data[A_j[jj]]; |
286: } |
287: y_data[i] = alpha*tempx; |
288: } |
289: } // y = alpha*A*x |
290: } // temp == 0 |
291: else if (-1 == temp) // beta == -alpha |
292: { |
293: if (1 == alpha) // JSP: a common path |
294: { |
295: for (i = iBegin; i < iEnd; i++) |
296: { |
297: tempx = -b_data[i]; |
298: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
299: { |
300: tempx += A_data[jj] * x_data[A_j[jj]]; |
301: } |
302: y_data[i] = tempx; |
303: } |
304: } // y = A*x - y |
305: else if (-1 == alpha) // JSP: a common path |
306: { |
307: for (i = iBegin; i < iEnd; i++) |
308: { |
309: tempx = b_data[i]; |
310: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
311: { |
312: tempx -= A_data[jj] * x_data[A_j[jj]]; |
313: } |
314: y_data[i] = tempx; |
315: } |
316: } // y = -A*x + y |
317: else |
318: { |
319: for (i = iBegin; i < iEnd; i++) |
320: { |
321: tempx = -b_data[i]; |
322: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
323: { |
324: tempx += A_data[jj] * x_data[A_j[jj]]; |
325: } |
326: y_data[i] = alpha*tempx; |
327: } |
328: } // y = alpha*(A*x - y) |
329: } // temp == -1 |
330: else if (1 == temp) |
331: { |
332: if (1 == alpha) // JSP: a common path |
333: { |
334: for (i = iBegin; i < iEnd; i++) |
335: { |
336: tempx = b_data[i]; |
337: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
338: { |
339: tempx += A_data[jj] * x_data[A_j[jj]]; |
340: } |
341: y_data[i] = tempx; |
342: } |
343: } // y = A*x + y |
344: else if (-1 == alpha) |
345: { |
346: for (i = iBegin; i < iEnd; i++) |
347: { |
348: tempx = -b_data[i]; |
349: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
350: { |
351: tempx -= A_data[jj] * x_data[A_j[jj]]; |
352: } |
353: y_data[i] = tempx; |
354: } |
355: } // y = -A*x - y |
356: else |
357: { |
358: for (i = iBegin; i < iEnd; i++) |
359: { |
360: tempx = b_data[i]; |
361: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
362: { |
363: tempx += A_data[jj] * x_data[A_j[jj]]; |
364: } |
365: y_data[i] = alpha*tempx; |
[...] |
371: if (1 == alpha) // JSP: a common path |
372: { |
373: for (i = iBegin; i < iEnd; i++) |
374: { |
375: tempx = b_data[i]*temp; |
376: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
377: { |
378: tempx += A_data[jj] * x_data[A_j[jj]]; |
379: } |
380: y_data[i] = tempx; |
381: } |
382: } // y = A*x + temp*y |
383: else if (-1 == alpha) |
384: { |
385: for (i = iBegin; i < iEnd; i++) |
386: { |
387: tempx = -b_data[i]*temp; |
388: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
389: { |
390: tempx -= A_data[jj] * x_data[A_j[jj]]; |
391: } |
392: y_data[i] = tempx; |
393: } |
394: } // y = -A*x - temp*y |
395: else |
396: { |
397: for (i = iBegin; i < iEnd; i++) |
398: { |
399: tempx = b_data[i]*temp; |
400: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
401: { |
402: tempx += A_data[jj] * x_data[A_j[jj]]; |
403: } |
404: y_data[i] = alpha*tempx; |
0x4d45c0 PUSH %RBP |
0x4d45c1 MOV %RSP,%RBP |
0x4d45c4 PUSH %R15 |
0x4d45c6 PUSH %R14 |
0x4d45c8 PUSH %R13 |
0x4d45ca PUSH %R12 |
0x4d45cc PUSH %RBX |
0x4d45cd SUB $0x18,%RSP |
0x4d45d1 MOV %R9,%R14 |
0x4d45d4 MOV %R8,%R15 |
0x4d45d7 MOV %RCX,%R12 |
0x4d45da MOV %RDX,-0x40(%RBP) |
0x4d45de MOV %RCX,%RDI |
0x4d45e1 CALL 4d3050 <hypre_CSRMatrixGetLoadBalancedPartitionBegin> |
0x4d45e6 MOV %RAX,%R13 |
0x4d45e9 MOV %R12,%RDI |
0x4d45ec CALL 4d30d0 <hypre_CSRMatrixGetLoadBalancedPartitionEnd> |
0x4d45f1 MOV %RAX,-0x30(%RBP) |
0x4d45f5 CMP %RAX,%R13 |
0x4d45f8 JLE 4d4628 |
0x4d45fa MOV 0x585bf(%RIP),%RDI |
0x4d4601 MOV $0x505dec,%ESI |
0x4d4606 MOV $0x507bbf,%EDX |
0x4d460b XOR %EAX,%EAX |
0x4d460d CALL 4ddb80 <hypre_fprintf> |
0x4d4612 MOV $0x5084d1,%EDI |
0x4d4617 MOV $0xf8,%ESI |
0x4d461c MOV $0x1,%EDX |
0x4d4621 XOR %ECX,%ECX |
0x4d4623 CALL 4dfac0 <hypre_error_handler> |
0x4d4628 MOV 0x18(%RBP),%RBX |
0x4d462c MOV %R13,-0x38(%RBP) |
0x4d4630 TEST %R13,%R13 |
0x4d4633 JS 4d463b |
0x4d4635 CMP %RBX,-0x38(%RBP) |
0x4d4639 JLE 4d4669 |
0x4d463b MOV 0x5857e(%RIP),%RDI |
0x4d4642 MOV $0x505dec,%ESI |
0x4d4647 MOV $0x50854a,%EDX |
0x4d464c XOR %EAX,%EAX |
0x4d464e CALL 4ddb80 <hypre_fprintf> |
0x4d4653 MOV $0x5084d1,%EDI |
0x4d4658 MOV $0xf9,%ESI |
0x4d465d MOV $0x1,%EDX |
0x4d4662 XOR %ECX,%ECX |
0x4d4664 CALL 4dfac0 <hypre_error_handler> |
0x4d4669 VMOVSD 0x38(%RBP),%XMM5 |
0x4d466e CMPQ $0,-0x30(%RBP) |
0x4d4673 JS 4d467b |
0x4d4675 CMP %RBX,-0x30(%RBP) |
0x4d4679 JLE 4d46ae |
0x4d467b MOV 0x5853e(%RIP),%RDI |
0x4d4682 MOV $0x505dec,%ESI |
0x4d4687 MOV $0x50856c,%EDX |
0x4d468c XOR %EAX,%EAX |
0x4d468e CALL 4ddb80 <hypre_fprintf> |
0x4d4693 MOV $0x5084d1,%EDI |
0x4d4698 MOV $0xfa,%ESI |
0x4d469d MOV $0x1,%EDX |
0x4d46a2 XOR %ECX,%ECX |
0x4d46a4 CALL 4dfac0 <hypre_error_handler> |
0x4d46a9 VMOVSD 0x38(%RBP),%XMM5 |
0x4d46ae MOV 0x20(%RBP),%R9 |
0x4d46b2 MOV 0x10(%RBP),%R11 |
0x4d46b6 VMOVSD -0x40(%RBP),%XMM0 |
0x4d46bb VXORPD %XMM1,%XMM1,%XMM1 |
0x4d46bf VUCOMISD %XMM1,%XMM5 |
0x4d46c3 JNE 4d47bd |
0x4d46c9 VUCOMISD 0x20937(%RIP),%XMM0 |
0x4d46d1 MOV -0x38(%RBP),%RSI |
0x4d46d5 JNE 4d48cd |
0x4d46db CMP -0x30(%RBP),%RSI |
0x4d46df JGE 4d526d |
0x4d46e5 MOV %RSI,%RAX |
0x4d46e8 NOT %RAX |
0x4d46eb ADD %RAX,-0x30(%RBP) |
0x4d46ef XOR %R13D,%R13D |
0x4d46f2 JMP 4d471b |
0x4d46f4 NOPW %CS:(%RAX,%RAX,1) |
(3976) 0x4d4700 MOV 0x30(%RBP),%RAX |
(3976) 0x4d4704 VMOVSD %XMM0,(%RAX,%R10,8) |
(3976) 0x4d470a LEA 0x1(%R13),%RAX |
(3976) 0x4d470e CMP -0x30(%RBP),%R13 |
(3976) 0x4d4712 MOV %RAX,%R13 |
(3976) 0x4d4715 JE 4d526d |
(3976) 0x4d471b LEA (%RSI,%R13,1),%R10 |
(3976) 0x4d471f MOV (%R14,%R10,8),%R8 |
(3976) 0x4d4723 MOV 0x8(%R14,%R10,8),%RAX |
(3976) 0x4d4728 VXORPD %XMM0,%XMM0,%XMM0 |
(3976) 0x4d472c MOV %RAX,%R12 |
(3976) 0x4d472f SUB %R8,%R12 |
(3976) 0x4d4732 JLE 4d4700 |
(3976) 0x4d4734 MOV %R12,%RDX |
(3976) 0x4d4737 AND $-0x4,%RDX |
(3976) 0x4d473b JE 4d4796 |
(3976) 0x4d473d LEA -0x1(%RDX),%RCX |
(3976) 0x4d4741 LEA (%R15,%R8,8),%RDI |
(3976) 0x4d4745 LEA (%R11,%R8,8),%RSI |
(3976) 0x4d4749 VXORPD %XMM0,%XMM0,%XMM0 |
(3976) 0x4d474d XOR %EBX,%EBX |
(3976) 0x4d474f NOP |
(3978) 0x4d4750 VMOVUPD (%RSI,%RBX,8),%YMM1 |
(3978) 0x4d4755 KXNORW %K0,%K0,%K1 |
(3978) 0x4d4759 VXORPD %XMM2,%XMM2,%XMM2 |
(3978) 0x4d475d VGATHERQPD (%R9,%YMM1,8),%YMM2{%K1} |
(3978) 0x4d4764 VFMADD231PD (%RDI,%RBX,8),%YMM2,%YMM0 |
(3978) 0x4d476a ADD $0x4,%RBX |
(3978) 0x4d476e CMP %RCX,%RBX |
(3978) 0x4d4771 JBE 4d4750 |
(3976) 0x4d4773 VEXTRACTF128 $0x1,%YMM0,%XMM1 |
(3976) 0x4d4779 VADDPD %XMM1,%XMM0,%XMM0 |
(3976) 0x4d477d VPERMILPD $0x1,%XMM0,%XMM1 |
(3976) 0x4d4783 VADDSD %XMM1,%XMM0,%XMM0 |
(3976) 0x4d4787 CMP %RDX,%R12 |
(3976) 0x4d478a MOV -0x38(%RBP),%RSI |
(3976) 0x4d478e JE 4d4700 |
(3976) 0x4d4794 JMP 4d479c |
(3976) 0x4d4796 VXORPD %XMM0,%XMM0,%XMM0 |
(3976) 0x4d479a XOR %EDX,%EDX |
(3976) 0x4d479c ADD %R8,%RDX |
(3976) 0x4d479f NOP |
(3977) 0x4d47a0 MOV (%R11,%RDX,8),%RCX |
(3977) 0x4d47a4 VMOVSD (%R9,%RCX,8),%XMM1 |
(3977) 0x4d47aa VFMADD231SD (%R15,%RDX,8),%XMM1,%XMM0 |
(3977) 0x4d47b0 INC %RDX |
(3977) 0x4d47b3 CMP %RDX,%RAX |
(3977) 0x4d47b6 JNE 4d47a0 |
(3976) 0x4d47b8 JMP 4d4700 |
0x4d47bd VUCOMISD 0x2153b(%RIP),%XMM5 |
0x4d47c5 MOV -0x38(%RBP),%RBX |
0x4d47c9 JNE 4d49bd |
0x4d47cf VUCOMISD 0x20831(%RIP),%XMM0 |
0x4d47d7 JNE 4d4acd |
0x4d47dd CMP -0x30(%RBP),%RBX |
0x4d47e1 JGE 4d526d |
0x4d47e7 MOV %RBX,%RAX |
0x4d47ea NOT %RAX |
0x4d47ed ADD %RAX,-0x30(%RBP) |
0x4d47f1 XOR %R8D,%R8D |
0x4d47f4 VMOVDDUP 0x212c4(%RIP),%XMM0 |
0x4d47fc JMP 4d481b |
0x4d47fe XCHG %AX,%AX |
(3967) 0x4d4800 MOV 0x30(%RBP),%RAX |
(3967) 0x4d4804 VMOVSD %XMM1,(%RAX,%R13,8) |
(3967) 0x4d480a LEA 0x1(%R8),%RAX |
(3967) 0x4d480e CMP -0x30(%RBP),%R8 |
(3967) 0x4d4812 MOV %RAX,%R8 |
(3967) 0x4d4815 JE 4d526d |
(3967) 0x4d481b LEA (%RBX,%R8,1),%R13 |
(3967) 0x4d481f MOV 0x28(%RBP),%RAX |
(3967) 0x4d4823 VMOVSD (%RAX,%R13,8),%XMM1 |
(3967) 0x4d4829 VXORPD %XMM0,%XMM1,%XMM1 |
(3967) 0x4d482d MOV (%R14,%R13,8),%R10 |
(3967) 0x4d4831 MOV 0x8(%R14,%R13,8),%RAX |
(3967) 0x4d4836 MOV %RAX,%R12 |
(3967) 0x4d4839 SUB %R10,%R12 |
(3967) 0x4d483c JLE 4d4800 |
(3967) 0x4d483e MOV %R12,%RDX |
(3967) 0x4d4841 AND $-0x4,%RDX |
(3967) 0x4d4845 JE 4d48aa |
(3967) 0x4d4847 LEA -0x1(%RDX),%RCX |
(3967) 0x4d484b LEA (%R15,%R10,8),%RSI |
(3967) 0x4d484f LEA (%R11,%R10,8),%RDI |
(3967) 0x4d4853 VXORPD %XMM2,%XMM2,%XMM2 |
(3967) 0x4d4857 XOR %EBX,%EBX |
(3967) 0x4d4859 NOPL (%RAX) |
(3969) 0x4d4860 VMOVUPD (%RDI,%RBX,8),%YMM3 |
(3969) 0x4d4865 KXNORW %K0,%K0,%K1 |
(3969) 0x4d4869 VXORPD %XMM4,%XMM4,%XMM4 |
(3969) 0x4d486d VGATHERQPD (%R9,%YMM3,8),%YMM4{%K1} |
(3969) 0x4d4874 VFMADD231PD (%RSI,%RBX,8),%YMM4,%YMM2 |
(3969) 0x4d487a ADD $0x4,%RBX |
(3969) 0x4d487e CMP %RCX,%RBX |
(3969) 0x4d4881 JBE 4d4860 |
(3967) 0x4d4883 VEXTRACTF128 $0x1,%YMM2,%XMM3 |
(3967) 0x4d4889 VADDPD %XMM3,%XMM2,%XMM2 |
(3967) 0x4d488d VPERMILPD $0x1,%XMM2,%XMM3 |
(3967) 0x4d4893 VADDSD %XMM3,%XMM2,%XMM2 |
(3967) 0x4d4897 VADDSD %XMM2,%XMM1,%XMM1 |
(3967) 0x4d489b CMP %RDX,%R12 |
(3967) 0x4d489e MOV -0x38(%RBP),%RBX |
(3967) 0x4d48a2 JE 4d4800 |
(3967) 0x4d48a8 JMP 4d48ac |
(3967) 0x4d48aa XOR %EDX,%EDX |
(3967) 0x4d48ac ADD %R10,%RDX |
(3967) 0x4d48af NOP |
(3968) 0x4d48b0 MOV (%R11,%RDX,8),%RCX |
(3968) 0x4d48b4 VMOVSD (%R9,%RCX,8),%XMM2 |
(3968) 0x4d48ba VFMADD231SD (%R15,%RDX,8),%XMM2,%XMM1 |
(3968) 0x4d48c0 INC %RDX |
(3968) 0x4d48c3 CMP %RDX,%RAX |
(3968) 0x4d48c6 JNE 4d48b0 |
(3967) 0x4d48c8 JMP 4d4800 |
0x4d48cd VUCOMISD 0x2142b(%RIP),%XMM0 |
0x4d48d5 JNE 4d4bcd |
0x4d48db CMP -0x30(%RBP),%RSI |
0x4d48df JGE 4d526d |
0x4d48e5 MOV %RSI,%RAX |
0x4d48e8 NOT %RAX |
0x4d48eb ADD %RAX,-0x30(%RBP) |
0x4d48ef XOR %R13D,%R13D |
0x4d48f2 JMP 4d491b |
0x4d48f4 NOPW %CS:(%RAX,%RAX,1) |
(3973) 0x4d4900 MOV 0x30(%RBP),%RAX |
(3973) 0x4d4904 VMOVSD %XMM0,(%RAX,%R10,8) |
(3973) 0x4d490a LEA 0x1(%R13),%RAX |
(3973) 0x4d490e CMP -0x30(%RBP),%R13 |
(3973) 0x4d4912 MOV %RAX,%R13 |
(3973) 0x4d4915 JE 4d526d |
(3973) 0x4d491b LEA (%RSI,%R13,1),%R10 |
(3973) 0x4d491f MOV (%R14,%R10,8),%R8 |
(3973) 0x4d4923 MOV 0x8(%R14,%R10,8),%RAX |
(3973) 0x4d4928 VXORPD %XMM0,%XMM0,%XMM0 |
(3973) 0x4d492c MOV %RAX,%R12 |
(3973) 0x4d492f SUB %R8,%R12 |
(3973) 0x4d4932 JLE 4d4900 |
(3973) 0x4d4934 MOV %R12,%RDX |
(3973) 0x4d4937 AND $-0x4,%RDX |
(3973) 0x4d493b JE 4d4996 |
(3973) 0x4d493d LEA -0x1(%RDX),%RBX |
(3973) 0x4d4941 LEA (%R15,%R8,8),%RDI |
(3973) 0x4d4945 LEA (%R11,%R8,8),%RSI |
(3973) 0x4d4949 VXORPD %XMM0,%XMM0,%XMM0 |
(3973) 0x4d494d XOR %ECX,%ECX |
(3973) 0x4d494f NOP |
(3975) 0x4d4950 VMOVUPD (%RSI,%RCX,8),%YMM1 |
(3975) 0x4d4955 KXNORW %K0,%K0,%K1 |
(3975) 0x4d4959 VXORPD %XMM2,%XMM2,%XMM2 |
(3975) 0x4d495d VGATHERQPD (%R9,%YMM1,8),%YMM2{%K1} |
(3975) 0x4d4964 VFNMADD231PD (%RDI,%RCX,8),%YMM2,%YMM0 |
(3975) 0x4d496a ADD $0x4,%RCX |
(3975) 0x4d496e CMP %RBX,%RCX |
(3975) 0x4d4971 JBE 4d4950 |
(3973) 0x4d4973 VEXTRACTF128 $0x1,%YMM0,%XMM1 |
(3973) 0x4d4979 VADDPD %XMM1,%XMM0,%XMM0 |
(3973) 0x4d497d VPERMILPD $0x1,%XMM0,%XMM1 |
(3973) 0x4d4983 VADDSD %XMM1,%XMM0,%XMM0 |
(3973) 0x4d4987 CMP %RDX,%R12 |
(3973) 0x4d498a MOV -0x38(%RBP),%RSI |
(3973) 0x4d498e JE 4d4900 |
(3973) 0x4d4994 JMP 4d499c |
(3973) 0x4d4996 VXORPD %XMM0,%XMM0,%XMM0 |
(3973) 0x4d499a XOR %EDX,%EDX |
(3973) 0x4d499c ADD %R8,%RDX |
(3973) 0x4d499f NOP |
(3974) 0x4d49a0 MOV (%R11,%RDX,8),%RCX |
(3974) 0x4d49a4 VMOVSD (%R9,%RCX,8),%XMM1 |
(3974) 0x4d49aa VFNMADD231SD (%R15,%RDX,8),%XMM1,%XMM0 |
(3974) 0x4d49b0 INC %RDX |
(3974) 0x4d49b3 CMP %RDX,%RAX |
(3974) 0x4d49b6 JNE 4d49a0 |
(3973) 0x4d49b8 JMP 4d4900 |
0x4d49bd VUCOMISD 0x20643(%RIP),%XMM5 |
0x4d49c5 JNE 4d4cbd |
0x4d49cb VUCOMISD 0x20635(%RIP),%XMM0 |
0x4d49d3 JNE 4d4dbd |
0x4d49d9 CMP -0x30(%RBP),%RBX |
0x4d49dd JGE 4d526d |
0x4d49e3 MOV %RBX,%RAX |
0x4d49e6 NOT %RAX |
0x4d49e9 ADD %RAX,-0x30(%RBP) |
0x4d49ed XOR %R8D,%R8D |
0x4d49f0 JMP 4d4a1b |
0x4d49f2 NOPW %CS:(%RAX,%RAX,1) |
(3958) 0x4d4a00 MOV 0x30(%RBP),%RAX |
(3958) 0x4d4a04 VMOVSD %XMM0,(%RAX,%R10,8) |
(3958) 0x4d4a0a LEA 0x1(%R8),%RAX |
(3958) 0x4d4a0e CMP -0x30(%RBP),%R8 |
(3958) 0x4d4a12 MOV %RAX,%R8 |
(3958) 0x4d4a15 JE 4d526d |
(3958) 0x4d4a1b LEA (%RBX,%R8,1),%R10 |
(3958) 0x4d4a1f MOV 0x28(%RBP),%RAX |
(3958) 0x4d4a23 VMOVSD (%RAX,%R10,8),%XMM0 |
(3958) 0x4d4a29 MOV (%R14,%R10,8),%R13 |
(3958) 0x4d4a2d MOV 0x8(%R14,%R10,8),%RAX |
(3958) 0x4d4a32 MOV %RAX,%R12 |
(3958) 0x4d4a35 SUB %R13,%R12 |
(3958) 0x4d4a38 JLE 4d4a00 |
(3958) 0x4d4a3a MOV %R12,%RSI |
(3958) 0x4d4a3d AND $-0x4,%RSI |
(3958) 0x4d4a41 JE 4d4aaa |
(3958) 0x4d4a43 LEA -0x1(%RSI),%RBX |
(3958) 0x4d4a47 LEA (%R15,%R13,8),%RCX |
(3958) 0x4d4a4b LEA (%R11,%R13,8),%RDI |
(3958) 0x4d4a4f VXORPD %XMM1,%XMM1,%XMM1 |
(3958) 0x4d4a53 XOR %EDX,%EDX |
(3958) 0x4d4a55 NOPW %CS:(%RAX,%RAX,1) |
(3960) 0x4d4a60 VMOVUPD (%RDI,%RDX,8),%YMM2 |
(3960) 0x4d4a65 KXNORW %K0,%K0,%K1 |
(3960) 0x4d4a69 VXORPD %XMM3,%XMM3,%XMM3 |
(3960) 0x4d4a6d VGATHERQPD (%R9,%YMM2,8),%YMM3{%K1} |
(3960) 0x4d4a74 VFMADD231PD (%RCX,%RDX,8),%YMM3,%YMM1 |
(3960) 0x4d4a7a ADD $0x4,%RDX |
(3960) 0x4d4a7e CMP %RBX,%RDX |
(3960) 0x4d4a81 JBE 4d4a60 |
(3958) 0x4d4a83 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
(3958) 0x4d4a89 VADDPD %XMM2,%XMM1,%XMM1 |
(3958) 0x4d4a8d VPERMILPD $0x1,%XMM1,%XMM2 |
(3958) 0x4d4a93 VADDSD %XMM2,%XMM1,%XMM1 |
(3958) 0x4d4a97 VADDSD %XMM1,%XMM0,%XMM0 |
(3958) 0x4d4a9b CMP %RSI,%R12 |
(3958) 0x4d4a9e MOV -0x38(%RBP),%RBX |
(3958) 0x4d4aa2 JE 4d4a00 |
(3958) 0x4d4aa8 JMP 4d4aac |
(3958) 0x4d4aaa XOR %ESI,%ESI |
(3958) 0x4d4aac ADD %R13,%RSI |
(3958) 0x4d4aaf NOP |
(3959) 0x4d4ab0 MOV (%R11,%RSI,8),%RCX |
(3959) 0x4d4ab4 VMOVSD (%R9,%RCX,8),%XMM1 |
(3959) 0x4d4aba VFMADD231SD (%R15,%RSI,8),%XMM1,%XMM0 |
(3959) 0x4d4ac0 INC %RSI |
(3959) 0x4d4ac3 CMP %RSI,%RAX |
(3959) 0x4d4ac6 JNE 4d4ab0 |
(3958) 0x4d4ac8 JMP 4d4a00 |
0x4d4acd VUCOMISD 0x2122b(%RIP),%XMM0 |
0x4d4ad5 JNE 4d4ebd |
0x4d4adb CMP -0x30(%RBP),%RBX |
0x4d4adf JGE 4d526d |
0x4d4ae5 MOV %RBX,%RAX |
0x4d4ae8 NOT %RAX |
0x4d4aeb ADD %RAX,-0x30(%RBP) |
0x4d4aef XOR %R8D,%R8D |
0x4d4af2 JMP 4d4b1b |
0x4d4af4 NOPW %CS:(%RAX,%RAX,1) |
(3964) 0x4d4b00 MOV 0x30(%RBP),%RAX |
(3964) 0x4d4b04 VMOVSD %XMM0,(%RAX,%R10,8) |
(3964) 0x4d4b0a LEA 0x1(%R8),%RAX |
(3964) 0x4d4b0e CMP -0x30(%RBP),%R8 |
(3964) 0x4d4b12 MOV %RAX,%R8 |
(3964) 0x4d4b15 JE 4d526d |
(3964) 0x4d4b1b LEA (%RBX,%R8,1),%R10 |
(3964) 0x4d4b1f MOV 0x28(%RBP),%RAX |
(3964) 0x4d4b23 VMOVSD (%RAX,%R10,8),%XMM0 |
(3964) 0x4d4b29 MOV (%R14,%R10,8),%R13 |
(3964) 0x4d4b2d MOV 0x8(%R14,%R10,8),%RAX |
(3964) 0x4d4b32 MOV %RAX,%R12 |
(3964) 0x4d4b35 SUB %R13,%R12 |
(3964) 0x4d4b38 JLE 4d4b00 |
(3964) 0x4d4b3a MOV %R12,%RSI |
(3964) 0x4d4b3d AND $-0x4,%RSI |
(3964) 0x4d4b41 JE 4d4baa |
(3964) 0x4d4b43 LEA -0x1(%RSI),%RBX |
(3964) 0x4d4b47 LEA (%R15,%R13,8),%RCX |
(3964) 0x4d4b4b LEA (%R11,%R13,8),%RDI |
(3964) 0x4d4b4f VXORPD %XMM1,%XMM1,%XMM1 |
(3964) 0x4d4b53 XOR %EDX,%EDX |
(3964) 0x4d4b55 NOPW %CS:(%RAX,%RAX,1) |
(3966) 0x4d4b60 VMOVUPD (%RDI,%RDX,8),%YMM2 |
(3966) 0x4d4b65 KXNORW %K0,%K0,%K1 |
(3966) 0x4d4b69 VXORPD %XMM3,%XMM3,%XMM3 |
(3966) 0x4d4b6d VGATHERQPD (%R9,%YMM2,8),%YMM3{%K1} |
(3966) 0x4d4b74 VFNMADD231PD (%RCX,%RDX,8),%YMM3,%YMM1 |
(3966) 0x4d4b7a ADD $0x4,%RDX |
(3966) 0x4d4b7e CMP %RBX,%RDX |
(3966) 0x4d4b81 JBE 4d4b60 |
(3964) 0x4d4b83 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
(3964) 0x4d4b89 VADDPD %XMM2,%XMM1,%XMM1 |
(3964) 0x4d4b8d VPERMILPD $0x1,%XMM1,%XMM2 |
(3964) 0x4d4b93 VADDSD %XMM2,%XMM1,%XMM1 |
(3964) 0x4d4b97 VADDSD %XMM1,%XMM0,%XMM0 |
(3964) 0x4d4b9b CMP %RSI,%R12 |
(3964) 0x4d4b9e MOV -0x38(%RBP),%RBX |
(3964) 0x4d4ba2 JE 4d4b00 |
(3964) 0x4d4ba8 JMP 4d4bac |
(3964) 0x4d4baa XOR %ESI,%ESI |
(3964) 0x4d4bac ADD %R13,%RSI |
(3964) 0x4d4baf NOP |
(3965) 0x4d4bb0 MOV (%R11,%RSI,8),%RCX |
(3965) 0x4d4bb4 VMOVSD (%R9,%RCX,8),%XMM1 |
(3965) 0x4d4bba VFNMADD231SD (%R15,%RSI,8),%XMM1,%XMM0 |
(3965) 0x4d4bc0 INC %RSI |
(3965) 0x4d4bc3 CMP %RSI,%RAX |
(3965) 0x4d4bc6 JNE 4d4bb0 |
(3964) 0x4d4bc8 JMP 4d4b00 |
0x4d4bcd CMP -0x30(%RBP),%RSI |
0x4d4bd1 JGE 4d526d |
0x4d4bd7 MOV %RSI,%RAX |
0x4d4bda NOT %RAX |
0x4d4bdd ADD %RAX,-0x30(%RBP) |
0x4d4be1 XOR %R13D,%R13D |
0x4d4be4 JMP 4d4c0f |
0x4d4be6 NOPW %CS:(%RAX,%RAX,1) |
(3970) 0x4d4bf0 VMULSD %XMM0,%XMM1,%XMM1 |
(3970) 0x4d4bf4 MOV 0x30(%RBP),%RAX |
(3970) 0x4d4bf8 VMOVSD %XMM1,(%RAX,%R10,8) |
(3970) 0x4d4bfe LEA 0x1(%R13),%RAX |
(3970) 0x4d4c02 CMP -0x30(%RBP),%R13 |
(3970) 0x4d4c06 MOV %RAX,%R13 |
(3970) 0x4d4c09 JE 4d526d |
(3970) 0x4d4c0f LEA (%RSI,%R13,1),%R10 |
(3970) 0x4d4c13 MOV (%R14,%R10,8),%R8 |
(3970) 0x4d4c17 MOV 0x8(%R14,%R10,8),%RAX |
(3970) 0x4d4c1c VXORPD %XMM1,%XMM1,%XMM1 |
(3970) 0x4d4c20 MOV %RAX,%R12 |
(3970) 0x4d4c23 SUB %R8,%R12 |
(3970) 0x4d4c26 JLE 4d4bf0 |
(3970) 0x4d4c28 MOV %R12,%RDX |
(3970) 0x4d4c2b AND $-0x4,%RDX |
(3970) 0x4d4c2f JE 4d4c96 |
(3970) 0x4d4c31 LEA -0x1(%RDX),%RBX |
(3970) 0x4d4c35 LEA (%R15,%R8,8),%RDI |
(3970) 0x4d4c39 LEA (%R11,%R8,8),%RSI |
(3970) 0x4d4c3d VXORPD %XMM1,%XMM1,%XMM1 |
(3970) 0x4d4c41 XOR %ECX,%ECX |
(3970) 0x4d4c43 NOPW %CS:(%RAX,%RAX,1) |
(3972) 0x4d4c50 VMOVUPD (%RSI,%RCX,8),%YMM2 |
(3972) 0x4d4c55 VXORPD %XMM3,%XMM3,%XMM3 |
(3972) 0x4d4c59 KXNORW %K0,%K0,%K1 |
(3972) 0x4d4c5d VGATHERQPD (%R9,%YMM2,8),%YMM3{%K1} |
(3972) 0x4d4c64 VFMADD231PD (%RDI,%RCX,8),%YMM3,%YMM1 |
(3972) 0x4d4c6a ADD $0x4,%RCX |
(3972) 0x4d4c6e CMP %RBX,%RCX |
(3972) 0x4d4c71 JBE 4d4c50 |
(3970) 0x4d4c73 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
(3970) 0x4d4c79 VADDPD %XMM2,%XMM1,%XMM1 |
(3970) 0x4d4c7d VPERMILPD $0x1,%XMM1,%XMM2 |
(3970) 0x4d4c83 VADDSD %XMM2,%XMM1,%XMM1 |
(3970) 0x4d4c87 CMP %RDX,%R12 |
(3970) 0x4d4c8a MOV -0x38(%RBP),%RSI |
(3970) 0x4d4c8e JE 4d4bf0 |
(3970) 0x4d4c94 JMP 4d4c9c |
(3970) 0x4d4c96 VXORPD %XMM1,%XMM1,%XMM1 |
(3970) 0x4d4c9a XOR %EDX,%EDX |
(3970) 0x4d4c9c ADD %R8,%RDX |
(3970) 0x4d4c9f NOP |
(3971) 0x4d4ca0 MOV (%R11,%RDX,8),%RCX |
(3971) 0x4d4ca4 VMOVSD (%R9,%RCX,8),%XMM2 |
(3971) 0x4d4caa VFMADD231SD (%R15,%RDX,8),%XMM2,%XMM1 |
(3971) 0x4d4cb0 INC %RDX |
(3971) 0x4d4cb3 CMP %RDX,%RAX |
(3971) 0x4d4cb6 JNE 4d4ca0 |
(3970) 0x4d4cb8 JMP 4d4bf0 |
0x4d4cbd VUCOMISD 0x20343(%RIP),%XMM0 |
0x4d4cc5 JNE 4d4fad |
0x4d4ccb CMP -0x30(%RBP),%RBX |
0x4d4ccf JGE 4d526d |
0x4d4cd5 MOV %RBX,%RAX |
0x4d4cd8 NOT %RAX |
0x4d4cdb ADD %RAX,-0x30(%RBP) |
0x4d4cdf XOR %R8D,%R8D |
0x4d4ce2 JMP 4d4d0b |
0x4d4ce4 NOPW %CS:(%RAX,%RAX,1) |
(3949) 0x4d4cf0 MOV 0x30(%RBP),%RAX |
(3949) 0x4d4cf4 VMOVSD %XMM0,(%RAX,%R10,8) |
(3949) 0x4d4cfa LEA 0x1(%R8),%RAX |
(3949) 0x4d4cfe CMP -0x30(%RBP),%R8 |
(3949) 0x4d4d02 MOV %RAX,%R8 |
(3949) 0x4d4d05 JE 4d526d |
(3949) 0x4d4d0b LEA (%RBX,%R8,1),%R10 |
(3949) 0x4d4d0f MOV 0x28(%RBP),%RAX |
(3949) 0x4d4d13 VMULSD (%RAX,%R10,8),%XMM5,%XMM0 |
(3949) 0x4d4d19 MOV (%R14,%R10,8),%R13 |
(3949) 0x4d4d1d MOV 0x8(%R14,%R10,8),%RAX |
(3949) 0x4d4d22 MOV %RAX,%RDX |
(3949) 0x4d4d25 SUB %R13,%RDX |
(3949) 0x4d4d28 JLE 4d4cf0 |
(3949) 0x4d4d2a MOV %RDX,%RSI |
(3949) 0x4d4d2d AND $-0x4,%RSI |
(3949) 0x4d4d31 JE 4d4d9b |
(3949) 0x4d4d33 LEA -0x1(%RSI),%RBX |
(3949) 0x4d4d37 LEA (%R15,%R13,8),%RCX |
(3949) 0x4d4d3b LEA (%R11,%R13,8),%RDI |
(3949) 0x4d4d3f VXORPD %XMM1,%XMM1,%XMM1 |
(3949) 0x4d4d43 XOR %R12D,%R12D |
(3949) 0x4d4d46 NOPW %CS:(%RAX,%RAX,1) |
(3951) 0x4d4d50 VMOVUPD (%RDI,%R12,8),%YMM2 |
(3951) 0x4d4d56 VXORPD %XMM3,%XMM3,%XMM3 |
(3951) 0x4d4d5a KXNORW %K0,%K0,%K1 |
(3951) 0x4d4d5e VGATHERQPD (%R9,%YMM2,8),%YMM3{%K1} |
(3951) 0x4d4d65 VFMADD231PD (%RCX,%R12,8),%YMM3,%YMM1 |
(3951) 0x4d4d6b ADD $0x4,%R12 |
(3951) 0x4d4d6f CMP %RBX,%R12 |
(3951) 0x4d4d72 JBE 4d4d50 |
(3949) 0x4d4d74 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
(3949) 0x4d4d7a VADDPD %XMM2,%XMM1,%XMM1 |
(3949) 0x4d4d7e VPERMILPD $0x1,%XMM1,%XMM2 |
(3949) 0x4d4d84 VADDSD %XMM2,%XMM1,%XMM1 |
(3949) 0x4d4d88 VADDSD %XMM1,%XMM0,%XMM0 |
(3949) 0x4d4d8c CMP %RSI,%RDX |
(3949) 0x4d4d8f MOV -0x38(%RBP),%RBX |
(3949) 0x4d4d93 JE 4d4cf0 |
(3949) 0x4d4d99 JMP 4d4d9d |
(3949) 0x4d4d9b XOR %ESI,%ESI |
(3949) 0x4d4d9d ADD %R13,%RSI |
(3950) 0x4d4da0 MOV (%R11,%RSI,8),%RCX |
(3950) 0x4d4da4 VMOVSD (%R9,%RCX,8),%XMM1 |
(3950) 0x4d4daa VFMADD231SD (%R15,%RSI,8),%XMM1,%XMM0 |
(3950) 0x4d4db0 INC %RSI |
(3950) 0x4d4db3 CMP %RSI,%RAX |
(3950) 0x4d4db6 JNE 4d4da0 |
(3949) 0x4d4db8 JMP 4d4cf0 |
0x4d4dbd VUCOMISD 0x20f3b(%RIP),%XMM0 |
0x4d4dc5 JNE 4d50ad |
0x4d4dcb CMP -0x30(%RBP),%RBX |
0x4d4dcf JGE 4d526d |
0x4d4dd5 MOV %RBX,%RAX |
0x4d4dd8 NOT %RAX |
0x4d4ddb ADD %RAX,-0x30(%RBP) |
0x4d4ddf XOR %R8D,%R8D |
0x4d4de2 VMOVDDUP 0x20cd6(%RIP),%XMM0 |
0x4d4dea JMP 4d4e0b |
0x4d4dec NOPL (%RAX) |
(3955) 0x4d4df0 MOV 0x30(%RBP),%RAX |
(3955) 0x4d4df4 VMOVSD %XMM1,(%RAX,%R10,8) |
(3955) 0x4d4dfa LEA 0x1(%R8),%RAX |
(3955) 0x4d4dfe CMP -0x30(%RBP),%R8 |
(3955) 0x4d4e02 MOV %RAX,%R8 |
(3955) 0x4d4e05 JE 4d526d |
(3955) 0x4d4e0b LEA (%RBX,%R8,1),%R10 |
(3955) 0x4d4e0f MOV 0x28(%RBP),%RAX |
(3955) 0x4d4e13 VMOVSD (%RAX,%R10,8),%XMM1 |
(3955) 0x4d4e19 VXORPD %XMM0,%XMM1,%XMM1 |
(3955) 0x4d4e1d MOV (%R14,%R10,8),%R13 |
(3955) 0x4d4e21 MOV 0x8(%R14,%R10,8),%RAX |
(3955) 0x4d4e26 MOV %RAX,%R12 |
(3955) 0x4d4e29 SUB %R13,%R12 |
(3955) 0x4d4e2c JLE 4d4df0 |
(3955) 0x4d4e2e MOV %R12,%RSI |
(3955) 0x4d4e31 AND $-0x4,%RSI |
(3955) 0x4d4e35 JE 4d4e9a |
(3955) 0x4d4e37 LEA -0x1(%RSI),%RBX |
(3955) 0x4d4e3b LEA (%R15,%R13,8),%RCX |
(3955) 0x4d4e3f LEA (%R11,%R13,8),%RDI |
(3955) 0x4d4e43 VXORPD %XMM2,%XMM2,%XMM2 |
(3955) 0x4d4e47 XOR %EDX,%EDX |
(3955) 0x4d4e49 NOPL (%RAX) |
(3957) 0x4d4e50 VMOVUPD (%RDI,%RDX,8),%YMM3 |
(3957) 0x4d4e55 KXNORW %K0,%K0,%K1 |
(3957) 0x4d4e59 VXORPD %XMM4,%XMM4,%XMM4 |
(3957) 0x4d4e5d VGATHERQPD (%R9,%YMM3,8),%YMM4{%K1} |
(3957) 0x4d4e64 VFNMADD231PD (%RCX,%RDX,8),%YMM4,%YMM2 |
(3957) 0x4d4e6a ADD $0x4,%RDX |
(3957) 0x4d4e6e CMP %RBX,%RDX |
(3957) 0x4d4e71 JBE 4d4e50 |
(3955) 0x4d4e73 VEXTRACTF128 $0x1,%YMM2,%XMM3 |
(3955) 0x4d4e79 VADDPD %XMM3,%XMM2,%XMM2 |
(3955) 0x4d4e7d VPERMILPD $0x1,%XMM2,%XMM3 |
(3955) 0x4d4e83 VADDSD %XMM3,%XMM2,%XMM2 |
(3955) 0x4d4e87 VADDSD %XMM2,%XMM1,%XMM1 |
(3955) 0x4d4e8b CMP %RSI,%R12 |
(3955) 0x4d4e8e MOV -0x38(%RBP),%RBX |
(3955) 0x4d4e92 JE 4d4df0 |
(3955) 0x4d4e98 JMP 4d4e9c |
(3955) 0x4d4e9a XOR %ESI,%ESI |
(3955) 0x4d4e9c ADD %R13,%RSI |
(3955) 0x4d4e9f NOP |
(3956) 0x4d4ea0 MOV (%R11,%RSI,8),%RCX |
(3956) 0x4d4ea4 VMOVSD (%R9,%RCX,8),%XMM2 |
(3956) 0x4d4eaa VFNMADD231SD (%R15,%RSI,8),%XMM2,%XMM1 |
(3956) 0x4d4eb0 INC %RSI |
(3956) 0x4d4eb3 CMP %RSI,%RAX |
(3956) 0x4d4eb6 JNE 4d4ea0 |
(3955) 0x4d4eb8 JMP 4d4df0 |
0x4d4ebd CMP -0x30(%RBP),%RBX |
0x4d4ec1 JGE 4d526d |
0x4d4ec7 MOV %RBX,%RAX |
0x4d4eca NOT %RAX |
0x4d4ecd ADD %RAX,-0x30(%RBP) |
0x4d4ed1 XOR %R8D,%R8D |
0x4d4ed4 VMOVDDUP 0x20be4(%RIP),%XMM1 |
0x4d4edc JMP 4d4eff |
0x4d4ede XCHG %AX,%AX |
(3961) 0x4d4ee0 VMULSD %XMM0,%XMM2,%XMM2 |
(3961) 0x4d4ee4 MOV 0x30(%RBP),%RAX |
(3961) 0x4d4ee8 VMOVSD %XMM2,(%RAX,%R10,8) |
(3961) 0x4d4eee LEA 0x1(%R8),%RAX |
(3961) 0x4d4ef2 CMP -0x30(%RBP),%R8 |
(3961) 0x4d4ef6 MOV %RAX,%R8 |
(3961) 0x4d4ef9 JE 4d526d |
(3961) 0x4d4eff LEA (%RBX,%R8,1),%R10 |
(3961) 0x4d4f03 MOV 0x28(%RBP),%RAX |
(3961) 0x4d4f07 VMOVSD (%RAX,%R10,8),%XMM2 |
(3961) 0x4d4f0d VXORPD %XMM1,%XMM2,%XMM2 |
(3961) 0x4d4f11 MOV (%R14,%R10,8),%R13 |
(3961) 0x4d4f15 MOV 0x8(%R14,%R10,8),%RAX |
(3961) 0x4d4f1a MOV %RAX,%R12 |
(3961) 0x4d4f1d SUB %R13,%R12 |
(3961) 0x4d4f20 JLE 4d4ee0 |
(3961) 0x4d4f22 MOV %R12,%RSI |
(3961) 0x4d4f25 AND $-0x4,%RSI |
(3961) 0x4d4f29 JE 4d4f8a |
(3961) 0x4d4f2b LEA -0x1(%RSI),%RBX |
(3961) 0x4d4f2f LEA (%R15,%R13,8),%RCX |
(3961) 0x4d4f33 LEA (%R11,%R13,8),%RDI |
(3961) 0x4d4f37 VXORPD %XMM3,%XMM3,%XMM3 |
(3961) 0x4d4f3b XOR %EDX,%EDX |
(3961) 0x4d4f3d NOPL (%RAX) |
(3963) 0x4d4f40 VMOVUPD (%RDI,%RDX,8),%YMM4 |
(3963) 0x4d4f45 KXNORW %K0,%K0,%K1 |
(3963) 0x4d4f49 VXORPD %XMM5,%XMM5,%XMM5 |
(3963) 0x4d4f4d VGATHERQPD (%R9,%YMM4,8),%YMM5{%K1} |
(3963) 0x4d4f54 VFMADD231PD (%RCX,%RDX,8),%YMM5,%YMM3 |
(3963) 0x4d4f5a ADD $0x4,%RDX |
(3963) 0x4d4f5e CMP %RBX,%RDX |
(3963) 0x4d4f61 JBE 4d4f40 |
(3961) 0x4d4f63 VEXTRACTF128 $0x1,%YMM3,%XMM4 |
(3961) 0x4d4f69 VADDPD %XMM4,%XMM3,%XMM3 |
(3961) 0x4d4f6d VPERMILPD $0x1,%XMM3,%XMM4 |
(3961) 0x4d4f73 VADDSD %XMM4,%XMM3,%XMM3 |
(3961) 0x4d4f77 VADDSD %XMM3,%XMM2,%XMM2 |
(3961) 0x4d4f7b CMP %RSI,%R12 |
(3961) 0x4d4f7e MOV -0x38(%RBP),%RBX |
(3961) 0x4d4f82 JE 4d4ee0 |
(3961) 0x4d4f88 JMP 4d4f8c |
(3961) 0x4d4f8a XOR %ESI,%ESI |
(3961) 0x4d4f8c ADD %R13,%RSI |
(3961) 0x4d4f8f NOP |
(3962) 0x4d4f90 MOV (%R11,%RSI,8),%RCX |
(3962) 0x4d4f94 VMOVSD (%R9,%RCX,8),%XMM3 |
(3962) 0x4d4f9a VFMADD231SD (%R15,%RSI,8),%XMM3,%XMM2 |
(3962) 0x4d4fa0 INC %RSI |
(3962) 0x4d4fa3 CMP %RSI,%RAX |
(3962) 0x4d4fa6 JNE 4d4f90 |
(3961) 0x4d4fa8 JMP 4d4ee0 |
0x4d4fad VUCOMISD 0x20d4b(%RIP),%XMM0 |
0x4d4fb5 JNE 4d518d |
0x4d4fbb CMP -0x30(%RBP),%RBX |
0x4d4fbf JGE 4d526d |
0x4d4fc5 VXORPD 0x20af1(%RIP){1to2},%XMM5,%XMM0 |
0x4d4fcf MOV %RBX,%RAX |
0x4d4fd2 NOT %RAX |
0x4d4fd5 ADD %RAX,-0x30(%RBP) |
0x4d4fd9 XOR %R8D,%R8D |
0x4d4fdc JMP 4d4ff9 |
(3946) 0x4d4fde MOV 0x30(%RBP),%RAX |
(3946) 0x4d4fe2 VMOVSD %XMM1,(%RAX,%R10,8) |
(3946) 0x4d4fe8 LEA 0x1(%R8),%RAX |
(3946) 0x4d4fec CMP -0x30(%RBP),%R8 |
(3946) 0x4d4ff0 MOV %RAX,%R8 |
(3946) 0x4d4ff3 JE 4d526d |
(3946) 0x4d4ff9 LEA (%RBX,%R8,1),%R10 |
(3946) 0x4d4ffd MOV 0x28(%RBP),%RAX |
(3946) 0x4d5001 VMULSD (%RAX,%R10,8),%XMM0,%XMM1 |
(3946) 0x4d5007 MOV (%R14,%R10,8),%R12 |
(3946) 0x4d500b MOV 0x8(%R14,%R10,8),%RAX |
(3946) 0x4d5010 MOV %RAX,%RDX |
(3946) 0x4d5013 SUB %R12,%RDX |
(3946) 0x4d5016 JLE 4d4fde |
(3946) 0x4d5018 MOV %RDX,%RSI |
(3946) 0x4d501b AND $-0x4,%RSI |
(3946) 0x4d501f JE 4d508b |
(3946) 0x4d5021 LEA -0x1(%RSI),%RBX |
(3946) 0x4d5025 LEA (%R15,%R12,8),%RCX |
(3946) 0x4d5029 LEA (%R11,%R12,8),%RDI |
(3946) 0x4d502d VXORPD %XMM2,%XMM2,%XMM2 |
(3946) 0x4d5031 XOR %R13D,%R13D |
(3946) 0x4d5034 NOPW %CS:(%RAX,%RAX,1) |
(3948) 0x4d5040 VMOVUPD (%RDI,%R13,8),%YMM3 |
(3948) 0x4d5046 KXNORW %K0,%K0,%K1 |
(3948) 0x4d504a VXORPD %XMM4,%XMM4,%XMM4 |
(3948) 0x4d504e VGATHERQPD (%R9,%YMM3,8),%YMM4{%K1} |
(3948) 0x4d5055 VFNMADD231PD (%RCX,%R13,8),%YMM4,%YMM2 |
(3948) 0x4d505b ADD $0x4,%R13 |
(3948) 0x4d505f CMP %RBX,%R13 |
(3948) 0x4d5062 JBE 4d5040 |
(3946) 0x4d5064 VEXTRACTF128 $0x1,%YMM2,%XMM3 |
(3946) 0x4d506a VADDPD %XMM3,%XMM2,%XMM2 |
(3946) 0x4d506e VPERMILPD $0x1,%XMM2,%XMM3 |
(3946) 0x4d5074 VADDSD %XMM3,%XMM2,%XMM2 |
(3946) 0x4d5078 VADDSD %XMM2,%XMM1,%XMM1 |
(3946) 0x4d507c CMP %RSI,%RDX |
(3946) 0x4d507f MOV -0x38(%RBP),%RBX |
(3946) 0x4d5083 JE 4d4fde |
(3946) 0x4d5089 JMP 4d508d |
(3946) 0x4d508b XOR %ESI,%ESI |
(3946) 0x4d508d ADD %R12,%RSI |
(3947) 0x4d5090 MOV (%R11,%RSI,8),%RCX |
(3947) 0x4d5094 VMOVSD (%R9,%RCX,8),%XMM2 |
(3947) 0x4d509a VFNMADD231SD (%R15,%RSI,8),%XMM2,%XMM1 |
(3947) 0x4d50a0 INC %RSI |
(3947) 0x4d50a3 CMP %RSI,%RAX |
(3947) 0x4d50a6 JNE 4d5090 |
(3946) 0x4d50a8 JMP 4d4fde |
0x4d50ad CMP -0x30(%RBP),%RBX |
0x4d50b1 JGE 4d526d |
0x4d50b7 MOV %RBX,%RAX |
0x4d50ba NOT %RAX |
0x4d50bd ADD %RAX,-0x30(%RBP) |
0x4d50c1 XOR %R8D,%R8D |
0x4d50c4 JMP 4d50e5 |
(3952) 0x4d50c6 VMULSD %XMM0,%XMM1,%XMM1 |
(3952) 0x4d50ca MOV 0x30(%RBP),%RAX |
(3952) 0x4d50ce VMOVSD %XMM1,(%RAX,%R10,8) |
(3952) 0x4d50d4 LEA 0x1(%R8),%RAX |
(3952) 0x4d50d8 CMP -0x30(%RBP),%R8 |
(3952) 0x4d50dc MOV %RAX,%R8 |
(3952) 0x4d50df JE 4d526d |
(3952) 0x4d50e5 LEA (%RBX,%R8,1),%R10 |
(3952) 0x4d50e9 MOV 0x28(%RBP),%RAX |
(3952) 0x4d50ed VMOVSD (%RAX,%R10,8),%XMM1 |
(3952) 0x4d50f3 MOV (%R14,%R10,8),%R13 |
(3952) 0x4d50f7 MOV 0x8(%R14,%R10,8),%RAX |
(3952) 0x4d50fc MOV %RAX,%R12 |
(3952) 0x4d50ff SUB %R13,%R12 |
(3952) 0x4d5102 JLE 4d50c6 |
(3952) 0x4d5104 MOV %R12,%RSI |
(3952) 0x4d5107 AND $-0x4,%RSI |
(3952) 0x4d510b JE 4d516a |
(3952) 0x4d510d LEA -0x1(%RSI),%RBX |
(3952) 0x4d5111 LEA (%R15,%R13,8),%RCX |
(3952) 0x4d5115 LEA (%R11,%R13,8),%RDI |
(3952) 0x4d5119 VXORPD %XMM2,%XMM2,%XMM2 |
(3952) 0x4d511d XOR %EDX,%EDX |
(3952) 0x4d511f NOP |
(3954) 0x4d5120 VMOVUPD (%RDI,%RDX,8),%YMM3 |
(3954) 0x4d5125 KXNORW %K0,%K0,%K1 |
(3954) 0x4d5129 VXORPD %XMM4,%XMM4,%XMM4 |
(3954) 0x4d512d VGATHERQPD (%R9,%YMM3,8),%YMM4{%K1} |
(3954) 0x4d5134 VFMADD231PD (%RCX,%RDX,8),%YMM4,%YMM2 |
(3954) 0x4d513a ADD $0x4,%RDX |
(3954) 0x4d513e CMP %RBX,%RDX |
(3954) 0x4d5141 JBE 4d5120 |
(3952) 0x4d5143 VEXTRACTF128 $0x1,%YMM2,%XMM3 |
(3952) 0x4d5149 VADDPD %XMM3,%XMM2,%XMM2 |
(3952) 0x4d514d VPERMILPD $0x1,%XMM2,%XMM3 |
(3952) 0x4d5153 VADDSD %XMM3,%XMM2,%XMM2 |
(3952) 0x4d5157 VADDSD %XMM2,%XMM1,%XMM1 |
(3952) 0x4d515b CMP %RSI,%R12 |
(3952) 0x4d515e MOV -0x38(%RBP),%RBX |
(3952) 0x4d5162 JE 4d50c6 |
(3952) 0x4d5168 JMP 4d516c |
(3952) 0x4d516a XOR %ESI,%ESI |
(3952) 0x4d516c ADD %R13,%RSI |
(3952) 0x4d516f NOP |
(3953) 0x4d5170 MOV (%R11,%RSI,8),%RCX |
(3953) 0x4d5174 VMOVSD (%R9,%RCX,8),%XMM2 |
(3953) 0x4d517a VFMADD231SD (%R15,%RSI,8),%XMM2,%XMM1 |
(3953) 0x4d5180 INC %RSI |
(3953) 0x4d5183 CMP %RSI,%RAX |
(3953) 0x4d5186 JNE 4d5170 |
(3952) 0x4d5188 JMP 4d50c6 |
0x4d518d CMP -0x30(%RBP),%RBX |
0x4d5191 JGE 4d526d |
0x4d5197 MOV %RBX,%RAX |
0x4d519a NOT %RAX |
0x4d519d ADD %RAX,-0x30(%RBP) |
0x4d51a1 XOR %EDI,%EDI |
0x4d51a3 JMP 4d51c4 |
(3943) 0x4d51a5 VMULSD %XMM0,%XMM1,%XMM1 |
(3943) 0x4d51a9 MOV 0x30(%RBP),%RAX |
(3943) 0x4d51ad VMOVSD %XMM1,(%RAX,%R10,8) |
(3943) 0x4d51b3 LEA 0x1(%RDI),%RAX |
(3943) 0x4d51b7 CMP -0x30(%RBP),%RDI |
(3943) 0x4d51bb MOV %RAX,%RDI |
(3943) 0x4d51be JE 4d526d |
(3943) 0x4d51c4 LEA (%RBX,%RDI,1),%R10 |
(3943) 0x4d51c8 MOV 0x28(%RBP),%RAX |
(3943) 0x4d51cc VMULSD (%RAX,%R10,8),%XMM5,%XMM1 |
(3943) 0x4d51d2 MOV (%R14,%R10,8),%R12 |
(3943) 0x4d51d6 MOV 0x8(%R14,%R10,8),%RAX |
(3943) 0x4d51db MOV %RAX,%RDX |
(3943) 0x4d51de SUB %R12,%RDX |
(3943) 0x4d51e1 JLE 4d51a5 |
(3943) 0x4d51e3 MOV %RDX,%RSI |
(3943) 0x4d51e6 AND $-0x4,%RSI |
(3943) 0x4d51ea JE 4d524b |
(3943) 0x4d51ec LEA -0x1(%RSI),%RBX |
(3943) 0x4d51f0 LEA (%R15,%R12,8),%RCX |
(3943) 0x4d51f4 LEA (%R11,%R12,8),%R8 |
(3943) 0x4d51f8 VXORPD %XMM2,%XMM2,%XMM2 |
(3943) 0x4d51fc XOR %R13D,%R13D |
(3943) 0x4d51ff NOP |
(3945) 0x4d5200 VMOVUPD (%R8,%R13,8),%YMM3 |
(3945) 0x4d5206 KXNORW %K0,%K0,%K1 |
(3945) 0x4d520a VXORPD %XMM4,%XMM4,%XMM4 |
(3945) 0x4d520e VGATHERQPD (%R9,%YMM3,8),%YMM4{%K1} |
(3945) 0x4d5215 VFMADD231PD (%RCX,%R13,8),%YMM4,%YMM2 |
(3945) 0x4d521b ADD $0x4,%R13 |
(3945) 0x4d521f CMP %RBX,%R13 |
(3945) 0x4d5222 JBE 4d5200 |
(3943) 0x4d5224 VEXTRACTF128 $0x1,%YMM2,%XMM3 |
(3943) 0x4d522a VADDPD %XMM3,%XMM2,%XMM2 |
(3943) 0x4d522e VPERMILPD $0x1,%XMM2,%XMM3 |
(3943) 0x4d5234 VADDSD %XMM3,%XMM2,%XMM2 |
(3943) 0x4d5238 VADDSD %XMM2,%XMM1,%XMM1 |
(3943) 0x4d523c CMP %RSI,%RDX |
(3943) 0x4d523f MOV -0x38(%RBP),%RBX |
(3943) 0x4d5243 JE 4d51a5 |
(3943) 0x4d5249 JMP 4d524d |
(3943) 0x4d524b XOR %ESI,%ESI |
(3943) 0x4d524d ADD %R12,%RSI |
(3944) 0x4d5250 MOV (%R11,%RSI,8),%RCX |
(3944) 0x4d5254 VMOVSD (%R9,%RCX,8),%XMM2 |
(3944) 0x4d525a VFMADD231SD (%R15,%RSI,8),%XMM2,%XMM1 |
(3944) 0x4d5260 INC %RSI |
(3944) 0x4d5263 CMP %RSI,%RAX |
(3944) 0x4d5266 JNE 4d5250 |
(3943) 0x4d5268 JMP 4d51a5 |
0x4d526d ADD $0x18,%RSP |
0x4d5271 POP %RBX |
0x4d5272 POP %R12 |
0x4d5274 POP %R13 |
0x4d5276 POP %R14 |
0x4d5278 POP %R15 |
0x4d527a POP %RBP |
0x4d527b VZEROUPPER |
0x4d527e RET |
0x4d527f NOP |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►61.81+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_CSRMatrixMatvecOutOfPlac[...] | csr_matvec.c:243 | exec |
○ | hypre_ParCSRMatrixMatvecOutOfP[...] | par_csr_matvec.c:216 | exec |
○ | hypre_ParCSRRelax | ams.c:78 | exec |
○ | hypre_BoomerAMGCycle | par_cycle.c:322 | exec |
○ | hypre_BoomerAMGSolve | par_amg_solve.c:272 | exec |
○ | hypre_PCGSolve | pcg.c:545 | exec |
○ | main | amg.c:419 | exec |
○ | __libc_init_first | libc.so.6 | |
►15.56+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_CSRMatrixMatvecOutOfPlac[...] | csr_matvec.c:243 | exec |
○ | hypre_ParCSRMatrixMatvecOutOfP[...] | par_csr_matvec.c:216 | exec |
○ | hypre_BoomerAMGCycle | par_cycle.c:425 | exec |
○ | hypre_BoomerAMGSolve | par_amg_solve.c:272 | exec |
○ | hypre_PCGSolve | pcg.c:545 | exec |
○ | main | amg.c:419 | exec |
○ | __libc_init_first | libc.so.6 | |
►14.93+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_CSRMatrixMatvecOutOfPlac[...] | csr_matvec.c:243 | exec |
○ | hypre_ParCSRMatrixMatvecOutOfP[...] | par_csr_matvec.c:216 | exec |
○ | hypre_PCGSolve | pcg.c:496 | exec |
○ | main | amg.c:419 | exec |
○ | __libc_init_first | libc.so.6 | |
►3.12+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_CSRMatrixMatvecOutOfPlac[...] | csr_matvec.c:243 | exec |
○ | hypre_ParCSRMatrixMatvecOutOfP[...] | par_csr_matvec.c:216 | exec |
○ | hypre_BoomerAMGCycle | par_cycle.c:456 | exec |
○ | hypre_BoomerAMGSolve | par_amg_solve.c:272 | exec |
○ | hypre_PCGSolve | pcg.c:545 | exec |
○ | main | amg.c:419 | exec |
○ | __libc_init_first | libc.so.6 | |
►2.96+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_CSRMatrixMatvecOutOfPlac[...] | csr_matvec.c:243 | exec |
○ | hypre_ParCSRMatrixMatvecOutOfP[...] | par_csr_matvec.c:216 | exec |
○ | hypre_ParCSRRelax | ams.c:78 | exec |
○ | hypre_BoomerAMGCycle | par_cycle.c:322 | exec |
○ | hypre_BoomerAMGSolve | par_amg_solve.c:272 | exec |
○ | hypre_PCGSolve | pcg.c:424 | exec |
○ | main | amg.c:419 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Source file and lines | csr_matvec.c:243-404 |
Module | exec |
nb instructions | 197 |
nb uops | 230 |
loop length | 845 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 57.50 cycles |
front end | 57.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 30.00 | 29.42 | 29.33 | 29.33 | 29.00 | 29.58 | 30.00 | 29.33 |
cycles | 30.00 | 29.42 | 29.33 | 29.33 | 29.00 | 29.58 | 30.00 | 29.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 54.91 |
Stall cycles | 0.00 |
Front-end | 57.50 |
Dispatch | 30.00 |
Overall L1 | 57.50 |
all | 1% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 1% |
all | 10% |
load | 5% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
all | 3% |
load | 1% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 4% |
all | 10% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 9% |
all | 13% |
load | 13% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
all | 10% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 10% |
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 %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
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 |
SUB $0x18,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4d3050 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4d30d0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %RAX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4d4628 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x585bf(%RIP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x505dec,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x507bbf,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4ddb80 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV $0x5084d1,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0xf8,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4dfac0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x18(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R13,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
TEST %R13,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JS 4d463b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP %RBX,-0x38(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 4d4669 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x5857e(%RIP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x505dec,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x50854a,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4ddb80 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV $0x5084d1,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0xf9,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4dfac0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD 0x38(%RBP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0,-0x30(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JS 4d467b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP %RBX,-0x30(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 4d46ae | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x5853e(%RIP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x505dec,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x50856c,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4ddb80 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV $0x5084d1,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0xfa,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4dfac0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD 0x38(%RBP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0x40(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD %XMM1,%XMM5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d47bd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD 0x20937(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV -0x38(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 4d48cd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RSI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R13D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d471b | 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 |
VUCOMISD 0x2153b(%RIP),%XMM5 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV -0x38(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 4d49bd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD 0x20831(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4acd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDDUP 0x212c4(%RIP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 4d481b | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD 0x2142b(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4bcd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RSI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R13D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d491b | 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 |
VUCOMISD 0x20643(%RIP),%XMM5 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4cbd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD 0x20635(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4dbd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4a1b | 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 |
VUCOMISD 0x2122b(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4ebd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4b1b | 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 |
CMP -0x30(%RBP),%RSI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R13D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4c0f | 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 |
VUCOMISD 0x20343(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4fad | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4d0b | 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 |
VUCOMISD 0x20f3b(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d50ad | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDDUP 0x20cd6(%RIP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 4d4e0b | 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 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDDUP 0x20be4(%RIP),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 4d4eff | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD 0x20d4b(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d518d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD 0x20af1(%RIP){1to2},%XMM5,%XMM0 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4ff9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d50e5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d51c4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
ADD $0x18,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
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 %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | csr_matvec.c:243-404 |
Module | exec |
nb instructions | 197 |
nb uops | 230 |
loop length | 845 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 57.50 cycles |
front end | 57.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 30.00 | 29.42 | 29.33 | 29.33 | 29.00 | 29.58 | 30.00 | 29.33 |
cycles | 30.00 | 29.42 | 29.33 | 29.33 | 29.00 | 29.58 | 30.00 | 29.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 54.91 |
Stall cycles | 0.00 |
Front-end | 57.50 |
Dispatch | 30.00 |
Overall L1 | 57.50 |
all | 1% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 1% |
all | 10% |
load | 5% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
all | 3% |
load | 1% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 4% |
all | 10% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 9% |
all | 13% |
load | 13% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
all | 10% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 10% |
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 %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
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 |
SUB $0x18,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4d3050 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4d30d0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %RAX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4d4628 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x585bf(%RIP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x505dec,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x507bbf,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4ddb80 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV $0x5084d1,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0xf8,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4dfac0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x18(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R13,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
TEST %R13,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JS 4d463b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP %RBX,-0x38(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 4d4669 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x5857e(%RIP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x505dec,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x50854a,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4ddb80 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV $0x5084d1,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0xf9,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4dfac0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD 0x38(%RBP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0,-0x30(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JS 4d467b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP %RBX,-0x30(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 4d46ae | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x5853e(%RIP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x505dec,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x50856c,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4ddb80 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV $0x5084d1,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0xfa,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4dfac0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD 0x38(%RBP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0x40(%RBP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD %XMM1,%XMM5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d47bd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD 0x20937(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV -0x38(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 4d48cd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RSI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R13D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d471b | 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 |
VUCOMISD 0x2153b(%RIP),%XMM5 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV -0x38(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 4d49bd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD 0x20831(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4acd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDDUP 0x212c4(%RIP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 4d481b | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD 0x2142b(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4bcd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RSI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R13D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d491b | 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 |
VUCOMISD 0x20643(%RIP),%XMM5 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4cbd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VUCOMISD 0x20635(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4dbd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4a1b | 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 |
VUCOMISD 0x2122b(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4ebd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4b1b | 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 |
CMP -0x30(%RBP),%RSI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R13D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4c0f | 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 |
VUCOMISD 0x20343(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d4fad | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4d0b | 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 |
VUCOMISD 0x20f3b(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d50ad | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDDUP 0x20cd6(%RIP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 4d4e0b | 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 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDDUP 0x20be4(%RIP),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 4d4eff | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD 0x20d4b(%RIP),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JNE 4d518d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD 0x20af1(%RIP){1to2},%XMM5,%XMM0 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d4ff9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d50e5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
CMP -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4d526d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOT %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,-0x30(%RBP) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d51c4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
ADD $0x18,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
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 %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼hypre_CSRMatrixMatvecOutOfPlace.extracted– | 58.13 | 21.3 |
▼Loop 3964 - csr_matvec.c:248-314 - exec– | 7.76 | 2.84 |
○Loop 3966 - csr_matvec.c:310-312 - exec | 33.66 | 12.33 |
○Loop 3965 - csr_matvec.c:310-312 - exec | 6.11 | 2.24 |
▼Loop 3976 - csr_matvec.c:248-263 - exec– | 0.98 | 0.36 |
○Loop 3978 - csr_matvec.c:259-261 - exec | 6.73 | 2.46 |
○Loop 3977 - csr_matvec.c:259-261 - exec | 0.97 | 0.35 |
▼Loop 3958 - csr_matvec.c:248-341 - exec– | 0.79 | 0.29 |
○Loop 3959 - csr_matvec.c:337-339 - exec | 1.02 | 0.37 |
○Loop 3960 - csr_matvec.c:337-339 - exec | 0.1 | 0.03 |
▼Loop 3961 - csr_matvec.c:248-326 - exec– | 0 | 0 |
○Loop 3963 - csr_matvec.c:322-324 - exec | 0 | 0 |
○Loop 3962 - csr_matvec.c:322-324 - exec | 0 | 0 |
▼Loop 3967 - csr_matvec.c:248-302 - exec– | 0 | 0 |
○Loop 3969 - csr_matvec.c:298-300 - exec | 0 | 0 |
○Loop 3968 - csr_matvec.c:298-300 - exec | 0 | 0 |
▼Loop 3943 - csr_matvec.c:248-404 - exec– | 0 | 0 |
○Loop 3945 - csr_matvec.c:400-402 - exec | 0 | 0 |
○Loop 3944 - csr_matvec.c:400-402 - exec | 0 | 0 |
▼Loop 3952 - csr_matvec.c:248-365 - exec– | 0 | 0 |
○Loop 3953 - csr_matvec.c:361-363 - exec | 0 | 0 |
○Loop 3954 - csr_matvec.c:361-363 - exec | 0 | 0 |
▼Loop 3946 - csr_matvec.c:248-392 - exec– | 0 | 0 |
○Loop 3947 - csr_matvec.c:388-390 - exec | 0 | 0 |
○Loop 3948 - csr_matvec.c:388-390 - exec | 0 | 0 |
▼Loop 3949 - csr_matvec.c:248-380 - exec– | 0 | 0 |
○Loop 3950 - csr_matvec.c:376-378 - exec | 0 | 0 |
○Loop 3951 - csr_matvec.c:376-378 - exec | 0 | 0 |
▼Loop 3973 - csr_matvec.c:248-275 - exec– | 0 | 0 |
○Loop 3974 - csr_matvec.c:271-273 - exec | 0 | 0 |
○Loop 3975 - csr_matvec.c:271-273 - exec | 0 | 0 |
▼Loop 3955 - csr_matvec.c:248-353 - exec– | 0 | 0 |
○Loop 3956 - csr_matvec.c:349-351 - exec | 0 | 0 |
○Loop 3957 - csr_matvec.c:349-351 - exec | 0 | 0 |
▼Loop 3970 - csr_matvec.c:248-287 - exec– | 0 | 0 |
○Loop 3972 - csr_matvec.c:283-285 - exec | 0 | 0 |
○Loop 3971 - csr_matvec.c:283-285 - exec | 0 | 0 |