OV - exec - Function hypre_CSRMatrixMultiply._omp

	Function: hypre_CSRMatrixMultiply._omp_fn.0	Module: exec	Source: csr_matop.c:185-302 [...]	Coverage (incl. loops): 0.99% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c: 185 - 302

--------------------------------------------------------------------------------

185: #pragma omp parallel private(ia, ib, ic, ja, jb, num_nonzeros, row_start, counter, a_entry, b_entry)

[...]

192:     ii = hypre_GetThreadNum();

193:     num_threads = hypre_NumActiveThreads();

194:

195:    size = nrows_A/num_threads;

196:    rest = nrows_A - size*num_threads;

197:     if (ii < rest)

198:     {

199:        ns = ii*size+ii;

200:        ne = (ii+1)*size+ii+1;

201:     }

202:     else

203:     {

204:        ns = ii*size+rest;

205:        ne = (ii+1)*size+rest;

206:     }

207:

208:     B_marker = hypre_CTAlloc(HYPRE_Int, ncols_B);

209:

210:     for (ib = 0; ib < ncols_B; ib++)

211:       B_marker[ib] = -1;

212:

213:     num_nonzeros = 0;

214:     for (ic = ns; ic < ne; ic++)

215:     {

216:         C_i[ic] = num_nonzeros;

217: 	if (allsquare)

218:         {

219:            B_marker[ic] = ic;

220:            num_nonzeros++;

221:         }

222: 	for (ia = A_i[ic]; ia < A_i[ic+1]; ia++)

223: 	{

224: 	   ja = A_j[ia];

225: 	   for (ib = B_i[ja]; ib < B_i[ja+1]; ib++)

226: 	   {

227: 	      jb = B_j[ib];

228: 	      if (B_marker[jb] != ic)

229: 	      {

230: 	 	 B_marker[jb] = ic;

231: 		 num_nonzeros++;

232: 	      }

233: 	   }

234:    	}

235:    }

236:    jj_count[ii] = num_nonzeros;

237:

238: #ifdef HYPRE_USING_OPENMP

239: #pragma omp barrier

240: #endif

241:

242:     if (ii)

243:     {

244:        jj = jj_count[0];

245:        for (i1 = 1; i1 < ii; i1++)

246:           jj += jj_count[i1];

247:

248:        for (i1 = ns; i1 < ne; i1++)

249:           C_i[i1] += jj;

250:     }

251:     else

252:     {

253:        C_i[nrows_A] = 0;

254:        for (i1 = 0; i1 < num_threads; i1++)

255:           C_i[nrows_A] += jj_count[i1];

256:

257:        C = hypre_CSRMatrixCreate(nrows_A, ncols_B, C_i[nrows_A]);

258:        hypre_CSRMatrixI(C) = C_i;

259:        hypre_CSRMatrixInitialize(C);

260:        C_j = hypre_CSRMatrixJ(C);

261:        C_data = hypre_CSRMatrixData(C);

262:     }

263:

264: #ifdef HYPRE_USING_OPENMP

265: #pragma omp barrier

266: #endif

267:

268:    for (ib = 0; ib < ncols_B; ib++)

269:       B_marker[ib] = -1;

270:

271:    counter = C_i[ns];

272:    for (ic = ns; ic < ne; ic++)

273:    {

274:       row_start = C_i[ic];

275:       if (allsquare)

276:       {

277:          B_marker[ic] = counter;

278:          C_data[counter] = 0;

279:          C_j[counter] = ic;

280:          counter++;

281:       }

282:       for (ia = A_i[ic]; ia < A_i[ic+1]; ia++)

283:       {

284: 	 ja = A_j[ia];

285: 	 a_entry = A_data[ia];

286: 	 for (ib = B_i[ja]; ib < B_i[ja+1]; ib++)

287: 	 {

288: 	    jb = B_j[ib];

289: 	    b_entry = B_data[ib];

290: 	    if (B_marker[jb] < row_start)

291: 	    {

292: 		B_marker[jb] = counter;

293: 		C_j[B_marker[jb]] = jb;

294: 		C_data[B_marker[jb]] = a_entry*b_entry;

295: 		counter++;

296: 	    }

297: 	    else

298: 		C_data[B_marker[jb]] += a_entry*b_entry;

299: 	}

300:       }

301:    }

302:    hypre_TFree(B_marker);

0x53e9c0 PUSH	%RBP

0x53e9c1 MOV	%RSP,%RBP

0x53e9c4 PUSH	%R15

0x53e9c6 PUSH	%R14

0x53e9c8 PUSH	%R13

0x53e9ca PUSH	%R12

0x53e9cc PUSH	%RBX

0x53e9cd MOV	%RDI,%RBX

0x53e9d0 SUB	$0x78,%RSP

0x53e9d4 MOV	0x60(%RDI),%RDX

0x53e9d8 MOV	0x50(%RDI),%R11

0x53e9dc MOV	0x38(%RDI),%RCX

0x53e9e0 MOV	0x28(%RDI),%RSI

0x53e9e4 MOV	0x18(%RDI),%R8

0x53e9e8 MOV	0x68(%RDI),%RAX

0x53e9ec MOV	%RDI,-0x88(%RBP)

0x53e9f3 MOV	0x30(%RDI),%R12

0x53e9f7 MOV	0x20(%RDI),%R13

0x53e9fb MOV	0x10(%RDI),%R15

0x53e9ff MOV	0x8(%RDI),%RDI

0x53ea03 MOV	%RDX,-0x68(%RBP)

0x53ea07 MOV	%R11,-0x38(%RBP)

0x53ea0b MOV	%RCX,-0x70(%RBP)

0x53ea0f MOV	%RSI,-0x40(%RBP)

0x53ea13 MOV	%R8,-0x80(%RBP)

0x53ea17 MOV	%RDI,-0x48(%RBP)

0x53ea1b MOV	%RAX,-0x78(%RBP)

0x53ea1f MOV	(%RBX),%R9

0x53ea22 MOV	%R9,-0x50(%RBP)

0x53ea26 CALL	555090 <hypre_GetThreadNum>

0x53ea2b MOV	%RAX,%R14

0x53ea2e CALL	555080 <hypre_NumActiveThreads>

0x53ea33 MOV	%RAX,%R10

0x53ea36 MOV	%RAX,-0x90(%RBP)

0x53ea3d MOV	-0x80(%RBP),%RAX

0x53ea41 MOV	%R14,%RBX

0x53ea44 CQTO

0x53ea46 IDIV	%R10

0x53ea49 MOV	-0x38(%RBP),%R11

0x53ea4d IMUL	%RAX,%RBX

0x53ea51 ADD	%RBX,%RAX

0x53ea54 CMP	%RDX,%R14

0x53ea57 JGE	53efcf

0x53ea5d LEA	(%R14,%RBX,1),%RSI

0x53ea61 LEA	0x1(%R14,%RAX,1),%R8

0x53ea66 MOV	%RSI,-0x38(%RBP)

0x53ea6a MOV	%R8,-0x60(%RBP)

0x53ea6e MOV	-0x70(%RBP),%RDI

0x53ea72 MOV	$0x8,%ESI

0x53ea77 MOV	%R11,-0x58(%RBP)

0x53ea7b CALL	5523b0 <hypre_CAlloc>

0x53ea80 CMPQ	$0,-0x70(%RBP)

0x53ea85 MOV	-0x58(%RBP),%R9

0x53ea89 MOV	%RAX,%RBX

0x53ea8c JLE	53eaaf

0x53ea8e MOV	-0x70(%RBP),%RDI

0x53ea92 MOV	$0xff,%ESI

0x53ea97 LEA	(,%RDI,8),%RDX

0x53ea9f MOV	%RAX,%RDI

0x53eaa2 MOV	%R9,-0x58(%RBP)

0x53eaa6 CALL	4110a0 <memset@plt>

0x53eaab MOV	-0x58(%RBP),%R9

0x53eaaf MOV	-0x38(%RBP),%R10

0x53eab3 MOV	-0x60(%RBP),%RAX

0x53eab7 MOV	%R10,%RSI

0x53eaba XOR	%EDI,%EDI

0x53eabc CMP	%RAX,%R10

0x53eabf JGE	53eb5f

0x53eac5 MOV	%R9,-0x58(%RBP)

0x53eac9 MOV	%R13,%R8

0x53eacc MOV	-0x40(%RBP),%R10

0x53ead0 MOV	-0x48(%RBP),%R13

0x53ead4 NOPL	(%RAX)

(2831) 0x53ead8 MOV	-0x58(%RBP),%RDX

(2831) 0x53eadc CMPQ	$0,-0x68(%RBP)

(2831) 0x53eae1 MOV	%RDI,(%RDX,%RSI,8)

(2831) 0x53eae5 JE	53eaee

(2831) 0x53eae7 MOV	%RSI,(%RBX,%RSI,8)

(2831) 0x53eaeb INC	%RDI

(2831) 0x53eaee MOV	(%R13,%RSI,8),%R9

(2831) 0x53eaf3 MOV	0x8(%R13,%RSI,8),%RDX

(2831) 0x53eaf8 CMP	%RDX,%R9

(2831) 0x53eafb JGE	53eb4f

(2831) 0x53eafd NOPL	(%RAX)

  (2832) 0x53eb00 MOV	(%R15,%R9,8),%R11

  (2832) 0x53eb04 MOV	(%R10,%R11,8),%RAX

  (2832) 0x53eb08 LEA	0x8(%R10,%R11,8),%R11

  (2832) 0x53eb0d MOV	(%R11),%RCX

  (2832) 0x53eb10 CMP	%RCX,%RAX

  (2832) 0x53eb13 JGE	53eb47

  (2832) 0x53eb15 NOPW	%CS:(%RAX,%RAX,1)

    (2833) 0x53eb20 MOV	(%R12,%RAX,8),%RDX

    (2833) 0x53eb24 LEA	(%RBX,%RDX,8),%RDX

    (2833) 0x53eb28 CMP	%RSI,(%RDX)

    (2833) 0x53eb2b JE	53ee28

    (2833) 0x53eb31 MOV	%RSI,(%RDX)

    (2833) 0x53eb34 INC	%RAX

    (2833) 0x53eb37 INC	%RDI

    (2833) 0x53eb3a MOV	(%R11),%RCX

    (2833) 0x53eb3d CMP	%RAX,%RCX

    (2833) 0x53eb40 JG	53eb20

  (2832) 0x53eb42 MOV	0x8(%R13,%RSI,8),%RDX

  (2832) 0x53eb47 INC	%R9

  (2832) 0x53eb4a CMP	%RDX,%R9

  (2832) 0x53eb4d JL	53eb00

(2831) 0x53eb4f INC	%RSI

(2831) 0x53eb52 CMP	%RSI,-0x60(%RBP)

(2831) 0x53eb56 JNE	53ead8

0x53eb58 MOV	-0x58(%RBP),%R9

0x53eb5c MOV	%R8,%R13

0x53eb5f MOV	-0x78(%RBP),%R10

0x53eb63 LEA	(,%R14,8),%RSI

0x53eb6b MOV	%RDI,(%R10,%R14,8)

0x53eb6f MOV	%R9,-0x98(%RBP)

0x53eb76 MOV	%RSI,-0x58(%RBP)

0x53eb7a CALL	411290 <GOMP_barrier@plt>

0x53eb7f TEST	%R14,%R14

0x53eb82 MOV	-0x98(%RBP),%R8

0x53eb89 JE	53ee88

0x53eb8f MOV	-0x78(%RBP),%R9

0x53eb93 MOV	-0x58(%RBP),%RDX

0x53eb97 MOV	(%R9),%R11

0x53eb9a LEA	0x8(%R9),%RAX

0x53eb9e ADD	%R9,%RDX

0x53eba1 CMP	$0x1,%R14

0x53eba5 JLE	53ec47

0x53ebab MOV	%RDX,%RCX

0x53ebae SUB	%RAX,%RCX

0x53ebb1 SUB	$0x8,%RCX

0x53ebb5 SHR	$0x3,%RCX

0x53ebb9 INC	%RCX

0x53ebbc AND	$0x7,%ECX

0x53ebbf JE	53ec1f

0x53ebc1 CMP	$0x1,%RCX

0x53ebc5 JE	53ec13

0x53ebc7 CMP	$0x2,%RCX

0x53ebcb JE	53ec0c

0x53ebcd CMP	$0x3,%RCX

0x53ebd1 JE	53ec05

0x53ebd3 CMP	$0x4,%RCX

0x53ebd7 JE	53ebfe

0x53ebd9 CMP	$0x5,%RCX

0x53ebdd JE	53ebf7

0x53ebdf CMP	$0x6,%RCX

0x53ebe3 JE	53ebf0

0x53ebe5 ADD	(%RAX),%R11

0x53ebe8 MOV	-0x78(%RBP),%RAX

0x53ebec ADD	$0x10,%RAX

0x53ebf0 ADD	(%RAX),%R11

0x53ebf3 ADD	$0x8,%RAX

0x53ebf7 ADD	(%RAX),%R11

0x53ebfa ADD	$0x8,%RAX

0x53ebfe ADD	(%RAX),%R11

0x53ec01 ADD	$0x8,%RAX

0x53ec05 ADD	(%RAX),%R11

0x53ec08 ADD	$0x8,%RAX

0x53ec0c ADD	(%RAX),%R11

0x53ec0f ADD	$0x8,%RAX

0x53ec13 ADD	(%RAX),%R11

0x53ec16 ADD	$0x8,%RAX

0x53ec1a CMP	%RAX,%RDX

0x53ec1d JE	53ec47

(2830) 0x53ec1f ADD	(%RAX),%R11

(2830) 0x53ec22 ADD	0x8(%RAX),%R11

(2830) 0x53ec26 ADD	0x10(%RAX),%R11

(2830) 0x53ec2a ADD	0x18(%RAX),%R11

(2830) 0x53ec2e ADD	0x20(%RAX),%R11

(2830) 0x53ec32 ADD	0x28(%RAX),%R11

(2830) 0x53ec36 ADD	0x30(%RAX),%R11

(2830) 0x53ec3a ADD	0x38(%RAX),%R11

(2830) 0x53ec3e ADD	$0x40,%RAX

(2830) 0x53ec42 CMP	%RAX,%RDX

(2830) 0x53ec45 JNE	53ec1f

0x53ec47 MOV	-0x38(%RBP),%R14

0x53ec4b MOV	-0x60(%RBP),%RSI

0x53ec4f CMP	%RSI,%R14

0x53ec52 JGE	53ee5a

0x53ec58 LEA	(%R8,%RSI,8),%RDI

0x53ec5c LEA	(%R8,%R14,8),%R10

0x53ec60 MOV	%RDI,%R9

0x53ec63 SUB	%R10,%R9

0x53ec66 SUB	$0x8,%R9

0x53ec6a SHR	$0x3,%R9

0x53ec6e INC	%R9

0x53ec71 AND	$0x7,%R9D

0x53ec75 JE	53ecd1

0x53ec77 CMP	$0x1,%R9

0x53ec7b JE	53ecc5

0x53ec7d CMP	$0x2,%R9

0x53ec81 JE	53ecbe

0x53ec83 CMP	$0x3,%R9

0x53ec87 JE	53ecb7

0x53ec89 CMP	$0x4,%R9

0x53ec8d JE	53ecb0

0x53ec8f CMP	$0x5,%R9

0x53ec93 JE	53eca9

0x53ec95 CMP	$0x6,%R9

0x53ec99 JE	53eca2

0x53ec9b ADD	%R11,(%R10)

0x53ec9e ADD	$0x8,%R10

0x53eca2 ADD	%R11,(%R10)

0x53eca5 ADD	$0x8,%R10

0x53eca9 ADD	%R11,(%R10)

0x53ecac ADD	$0x8,%R10

0x53ecb0 ADD	%R11,(%R10)

0x53ecb3 ADD	$0x8,%R10

0x53ecb7 ADD	%R11,(%R10)

0x53ecba ADD	$0x8,%R10

0x53ecbe ADD	%R11,(%R10)

0x53ecc1 ADD	$0x8,%R10

0x53ecc5 ADD	%R11,(%R10)

0x53ecc8 ADD	$0x8,%R10

0x53eccc CMP	%RDI,%R10

0x53eccf JE	53ecf9

(2829) 0x53ecd1 ADD	%R11,(%R10)

(2829) 0x53ecd4 ADD	%R11,0x8(%R10)

(2829) 0x53ecd8 ADD	%R11,0x10(%R10)

(2829) 0x53ecdc ADD	%R11,0x18(%R10)

(2829) 0x53ece0 ADD	%R11,0x20(%R10)

(2829) 0x53ece4 ADD	%R11,0x28(%R10)

(2829) 0x53ece8 ADD	%R11,0x30(%R10)

(2829) 0x53ecec ADD	%R11,0x38(%R10)

(2829) 0x53ecf0 ADD	$0x40,%R10

(2829) 0x53ecf4 CMP	%RDI,%R10

(2829) 0x53ecf7 JNE	53ecd1

0x53ecf9 MOV	%R8,-0x58(%RBP)

0x53ecfd CALL	411290 <GOMP_barrier@plt>

0x53ed02 CMPQ	$0,-0x70(%RBP)

0x53ed07 MOV	-0x58(%RBP),%R8

0x53ed0b JLE	53efe3

0x53ed11 MOV	-0x70(%RBP),%RDX

0x53ed15 MOV	$0xff,%ESI

0x53ed1a SAL	$0x3,%RDX

0x53ed1e MOV	%RBX,%RDI

0x53ed21 MOV	%R8,-0x58(%RBP)

0x53ed25 CALL	4110a0 <memset@plt>

0x53ed2a MOV	-0x58(%RBP),%R8

0x53ed2e MOV	-0x38(%RBP),%RDX

0x53ed32 MOV	-0x60(%RBP),%RCX

0x53ed36 MOV	(%R8,%RDX,8),%RDI

0x53ed3a CMP	%RCX,%RDX

0x53ed3d JGE	53ee72

0x53ed43 MOV	-0x88(%RBP),%RAX

0x53ed4a MOV	%R8,-0x70(%RBP)

0x53ed4e MOV	%R15,-0x58(%RBP)

0x53ed52 MOV	0x48(%RAX),%R10

0x53ed56 MOV	0x58(%RAX),%R14

0x53ed5a MOV	%RDI,%R9

0x53ed5d NOPL	(%RAX)

(2825) 0x53ed60 CMPQ	$0,-0x68(%RBP)

(2825) 0x53ed65 JE	53ed7e

(2825) 0x53ed67 MOV	-0x38(%RBP),%R15

(2825) 0x53ed6b MOV	%RDI,(%RBX,%R15,8)

(2825) 0x53ed6f MOVQ	$0,(%R10,%RDI,8)

(2825) 0x53ed77 MOV	%R15,(%R14,%RDI,8)

(2825) 0x53ed7b INC	%RDI

(2825) 0x53ed7e MOV	-0x48(%RBP),%R8

(2825) 0x53ed82 MOV	-0x38(%RBP),%RSI

(2825) 0x53ed86 MOV	(%R8,%RSI,8),%RCX

(2825) 0x53ed8a MOV	0x8(%R8,%RSI,8),%RDX

(2825) 0x53ed8f CMP	%RDX,%RCX

(2825) 0x53ed92 JGE	53ee0a

(2825) 0x53ed94 NOPL	(%RAX)

  (2826) 0x53ed98 MOV	-0x58(%RBP),%RAX

  (2826) 0x53ed9c MOV	-0x40(%RBP),%R8

  (2826) 0x53eda0 MOV	(%RAX,%RCX,8),%R15

  (2826) 0x53eda4 MOV	-0x50(%RBP),%R11

  (2826) 0x53eda8 MOV	(%R8,%R15,8),%RAX

  (2826) 0x53edac LEA	0x8(%R8,%R15,8),%R15

  (2826) 0x53edb1 VMOVSD	(%R11,%RCX,8),%XMM1

  (2826) 0x53edb7 MOV	(%R15),%R11

  (2826) 0x53edba CMP	%R11,%RAX

  (2826) 0x53edbd JGE	53ee02

  (2826) 0x53edbf NOP

    (2827) 0x53edc0 MOV	(%R12,%RAX,8),%RSI

    (2827) 0x53edc4 VMULSD	(%R13,%RAX,8),%XMM1,%XMM0

    (2827) 0x53edcb LEA	(%RBX,%RSI,8),%RDX

    (2827) 0x53edcf MOV	(%RDX),%R8

    (2827) 0x53edd2 CMP	%R9,%R8

    (2827) 0x53edd5 JGE	53ee40

    (2827) 0x53edd7 MOV	%RDI,(%RDX)

    (2827) 0x53edda MOV	%RSI,(%R14,%RDI,8)

    (2827) 0x53edde INC	%RAX

    (2827) 0x53ede1 INC	%RDI

    (2827) 0x53ede4 MOV	(%RDX),%R11

    (2827) 0x53ede7 VMOVSD	%XMM0,(%R10,%R11,8)

    (2827) 0x53eded MOV	(%R15),%R11

    (2827) 0x53edf0 CMP	%R11,%RAX

    (2827) 0x53edf3 JL	53edc0

  (2826) 0x53edf5 MOV	-0x48(%RBP),%RAX

  (2826) 0x53edf9 MOV	-0x38(%RBP),%R15

  (2826) 0x53edfd MOV	0x8(%RAX,%R15,8),%RDX

  (2826) 0x53ee02 INC	%RCX

  (2826) 0x53ee05 CMP	%RDX,%RCX

  (2826) 0x53ee08 JL	53ed98

(2825) 0x53ee0a INCQ	-0x38(%RBP)

(2825) 0x53ee0e MOV	-0x38(%RBP),%R8

(2825) 0x53ee12 CMP	%R8,-0x60(%RBP)

(2825) 0x53ee16 JE	53ee72

(2825) 0x53ee18 MOV	-0x70(%RBP),%RSI

(2825) 0x53ee1c MOV	(%RSI,%R8,8),%R9

(2825) 0x53ee20 JMP	53ed60

0x53ee25 NOPL	(%RAX)

    (2833) 0x53ee28 INC	%RAX

    (2833) 0x53ee2b CMP	%RCX,%RAX

    (2833) 0x53ee2e JL	53eb20

  (2832) 0x53ee34 JMP	53eb42

0x53ee39 NOPL	(%RAX)

    (2827) 0x53ee40 LEA	(%R10,%R8,8),%RSI

    (2827) 0x53ee44 VADDSD	(%RSI),%XMM0,%XMM2

    (2827) 0x53ee48 INC	%RAX

    (2827) 0x53ee4b VMOVSD	%XMM2,(%RSI)

    (2827) 0x53ee4f CMP	%R11,%RAX

    (2827) 0x53ee52 JL	53edc0

  (2826) 0x53ee58 JMP	53edf5

0x53ee5a MOV	%R8,-0x58(%RBP)

0x53ee5e CALL	411290 <GOMP_barrier@plt>

0x53ee63 CMPQ	$0,-0x70(%RBP)

0x53ee68 MOV	-0x58(%RBP),%R8

0x53ee6c JG	53ed11

0x53ee72 ADD	$0x78,%RSP

0x53ee76 MOV	%RBX,%RDI

0x53ee79 POP	%RBX

0x53ee7a POP	%R12

0x53ee7c POP	%R13

0x53ee7e POP	%R14

0x53ee80 POP	%R15

0x53ee82 POP	%RBP

0x53ee83 JMP	552440

0x53ee88 MOV	-0x80(%RBP),%RDI

0x53ee8c MOV	-0x78(%RBP),%RAX

0x53ee90 MOV	-0x90(%RBP),%R11

0x53ee97 LEA	(%R8,%RDI,8),%R9

0x53ee9b MOVQ	$0,(%R9)

0x53eea2 LEA	(%RAX,%R11,8),%RCX

0x53eea6 TEST	%R11,%R11

0x53eea9 JLE	53ef74

0x53eeaf MOV	%RCX,%RDX

0x53eeb2 SUB	%RAX,%RDX

0x53eeb5 SUB	$0x8,%RDX

0x53eeb9 SHR	$0x3,%RDX

0x53eebd INC	%RDX

0x53eec0 AND	$0x7,%EDX

0x53eec3 JE	53ef34

0x53eec5 CMP	$0x1,%RDX

0x53eec9 JE	53ef25

0x53eecb CMP	$0x2,%RDX

0x53eecf JE	53ef1b

0x53eed1 CMP	$0x3,%RDX

0x53eed5 JE	53ef11

0x53eed7 CMP	$0x4,%RDX

0x53eedb JE	53ef07

0x53eedd CMP	$0x5,%RDX

0x53eee1 JE	53eefd

0x53eee3 CMP	$0x6,%RDX

0x53eee7 JE	53eef3

0x53eee9 MOV	(%RAX),%R14

0x53eeec ADD	$0x8,%RAX

0x53eef0 MOV	%R14,(%R9)

0x53eef3 ADD	(%RAX),%R14

0x53eef6 MOV	%R14,(%R9)

0x53eef9 ADD	$0x8,%RAX

0x53eefd ADD	(%RAX),%R14

0x53ef00 MOV	%R14,(%R9)

0x53ef03 ADD	$0x8,%RAX

0x53ef07 ADD	(%RAX),%R14

0x53ef0a MOV	%R14,(%R9)

0x53ef0d ADD	$0x8,%RAX

0x53ef11 ADD	(%RAX),%R14

0x53ef14 MOV	%R14,(%R9)

0x53ef17 ADD	$0x8,%RAX

0x53ef1b ADD	(%RAX),%R14

0x53ef1e MOV	%R14,(%R9)

0x53ef21 ADD	$0x8,%RAX

0x53ef25 ADD	(%RAX),%R14

0x53ef28 ADD	$0x8,%RAX

0x53ef2c MOV	%R14,(%R9)

0x53ef2f CMP	%RAX,%RCX

0x53ef32 JE	53ef74

(2828) 0x53ef34 ADD	(%RAX),%R14

(2828) 0x53ef37 MOV	%R14,(%R9)

(2828) 0x53ef3a ADD	$0x40,%RAX

(2828) 0x53ef3e ADD	-0x38(%RAX),%R14

(2828) 0x53ef42 MOV	%R14,(%R9)

(2828) 0x53ef45 ADD	-0x30(%RAX),%R14

(2828) 0x53ef49 MOV	%R14,(%R9)

(2828) 0x53ef4c ADD	-0x28(%RAX),%R14

(2828) 0x53ef50 MOV	%R14,(%R9)

(2828) 0x53ef53 ADD	-0x20(%RAX),%R14

(2828) 0x53ef57 MOV	%R14,(%R9)

(2828) 0x53ef5a ADD	-0x18(%RAX),%R14

(2828) 0x53ef5e MOV	%R14,(%R9)

(2828) 0x53ef61 ADD	-0x10(%RAX),%R14

(2828) 0x53ef65 MOV	%R14,(%R9)

(2828) 0x53ef68 ADD	-0x8(%RAX),%R14

(2828) 0x53ef6c MOV	%R14,(%R9)

(2828) 0x53ef6f CMP	%RAX,%RCX

(2828) 0x53ef72 JNE	53ef34

0x53ef74 MOV	-0x70(%RBP),%RSI

0x53ef78 MOV	-0x80(%RBP),%RDI

0x53ef7c MOV	%R14,%RDX

0x53ef7f MOV	%R8,-0x58(%RBP)

0x53ef83 CALL	540d30 <hypre_CSRMatrixCreate>

0x53ef88 MOV	-0x88(%RBP),%R14

0x53ef8f MOV	-0x58(%RBP),%RSI

0x53ef93 MOV	%RAX,0x40(%R14)

0x53ef97 MOV	%RSI,(%RAX)

0x53ef9a MOV	%RAX,%RDI

0x53ef9d CALL	540e40 <hypre_CSRMatrixInitialize>

0x53efa2 MOV	0x40(%R14),%R10

0x53efa6 MOV	0x8(%R10),%R8

0x53efaa MOV	0x30(%R10),%RDI

0x53efae MOV	%R8,0x58(%R14)

0x53efb2 MOV	%RDI,0x48(%R14)

0x53efb6 CALL	411290 <GOMP_barrier@plt>

0x53efbb CMPQ	$0,-0x70(%RBP)

0x53efc0 MOV	-0x58(%RBP),%R8

0x53efc4 JG	53ed11

0x53efca JMP	53ed2e

0x53efcf LEA	(%RDX,%RBX,1),%RCX

0x53efd3 ADD	%RDX,%RAX

0x53efd6 MOV	%RCX,-0x38(%RBP)

0x53efda MOV	%RAX,-0x60(%RBP)

0x53efde JMP	53ea6e

0x53efe3 MOV	-0x38(%RBP),%R11

0x53efe7 MOV	(%R8,%R11,8),%RDI

0x53efeb JMP	53ed43

Coverage (%)	Name	Source Location	Module
○97.99	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○2.01	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0

Path /

Average path: Display a virtual path defined by average values of all real paths

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run gcc_5

Source file and lines	csr_matop.c:185-302
Module	exec

The function is defined in /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:185,192-302.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 12% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 51.50 to 5.00 cycles (10.30x speedup).

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

GOMP_barrier@plt: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:239
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:265
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:265
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:265
hypre_CAlloc: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:208
hypre_CSRMatrixCreate: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:257
hypre_CSRMatrixInitialize: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:259
hypre_GetThreadNum: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:192
hypre_NumActiveThreads: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:193
memset@plt: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:269

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

ADD: 7 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
IDIV: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:204

Conversion instructions

Detected expensive conversion instructions.

Details

CQTO: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:204

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

Matching between your function (in the source code) and the binary function

The binary function does not contain any FP arithmetical operations. The binary function is loading 624 bytes. The binary function is storing 360 bytes.

General properties

nb instructions	287
nb uops	309
loop length	1072
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	13

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	51.50 cycles
front end	51.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	21.80	21.80	28.00	28.00	31.00	21.80	21.80	31.00	31.00	31.00	21.80	28.00
cycles	21.80	21.80	28.00	28.00	31.00	21.80	21.80	31.00	31.00	31.00	21.80	28.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

10.00

Cycles summary

Front-end	51.50
Dispatch	31.00
DIV/SQRT	10.00
Overall L1	51.50

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	0%

Vector efficiency ratios

all	12%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 51.50 cycles. At this rate:

6% of peak load performance is reached (12.12 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (6.99 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 51.50 to 31.00 cycles (1.66x speedup).

ASM code

In the binary file, the address of the function is: 53e9c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB $0x78,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x60(%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x50(%RDI),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x38(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x28(%RDI),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RDI),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x68(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x30(%RDI),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x20(%RDI),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%RDI),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x8(%RDI),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDX,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R11,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RCX,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDI,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RBX),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 555090 <hypre_GetThreadNum>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 555080 <hypre_NumActiveThreads>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x80(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CQTO	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (12.5%)
IDIV %R10	5	0	3	0	0	0	0	0	0	0	0	0	0	11-16	10	scal (12.5%)
MOV -0x38(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RAX,%RBX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RBX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP %RDX,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 53efcf <hypre_CSRMatrixMultiply._omp_fn.0+0x60f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%R14,%RBX,1),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x1(%R14,%RAX,1),%R8	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RSI,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x70(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x8,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 5523b0 <hypre_CAlloc>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x70(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JLE 53eaaf <hypre_CSRMatrixMultiply._omp_fn.0+0xef>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0xff,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (,%RDI,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R9,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4110a0 <memset@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x38(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R10,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 53eb5f <hypre_CSRMatrixMultiply._omp_fn.0+0x19f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R9,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R13,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x40(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x48(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R8,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x78(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R14,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,(%R10,%R14,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R9,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 411290 <GOMP_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
TEST %R14,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
MOV -0x98(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JE 53ee88 <hypre_CSRMatrixMultiply._omp_fn.0+0x4c8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x78(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R9),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x8(%R9),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R9,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x1,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JLE 53ec47 <hypre_CSRMatrixMultiply._omp_fn.0+0x287>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RDX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SUB %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
SUB $0x8,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SHR $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
INC %RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
AND $0x7,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (6.3%)
JE 53ec1f <hypre_CSRMatrixMultiply._omp_fn.0+0x25f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ec13 <hypre_CSRMatrixMultiply._omp_fn.0+0x253>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ec0c <hypre_CSRMatrixMultiply._omp_fn.0+0x24c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ec05 <hypre_CSRMatrixMultiply._omp_fn.0+0x245>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ebfe <hypre_CSRMatrixMultiply._omp_fn.0+0x23e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ebf7 <hypre_CSRMatrixMultiply._omp_fn.0+0x237>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ebf0 <hypre_CSRMatrixMultiply._omp_fn.0+0x230>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x10,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ec47 <hypre_CSRMatrixMultiply._omp_fn.0+0x287>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x38(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RSI,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 53ee5a <hypre_CSRMatrixMultiply._omp_fn.0+0x49a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%R8,%RSI,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R8,%R14,8),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %R10,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB $0x8,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x7,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 53ecd1 <hypre_CSRMatrixMultiply._omp_fn.0+0x311>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecc5 <hypre_CSRMatrixMultiply._omp_fn.0+0x305>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecbe <hypre_CSRMatrixMultiply._omp_fn.0+0x2fe>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecb7 <hypre_CSRMatrixMultiply._omp_fn.0+0x2f7>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecb0 <hypre_CSRMatrixMultiply._omp_fn.0+0x2f0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53eca9 <hypre_CSRMatrixMultiply._omp_fn.0+0x2e9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53eca2 <hypre_CSRMatrixMultiply._omp_fn.0+0x2e2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RDI,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecf9 <hypre_CSRMatrixMultiply._omp_fn.0+0x339>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R8,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 411290 <GOMP_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x70(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JLE 53efe3 <hypre_CSRMatrixMultiply._omp_fn.0+0x623>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0xff,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAL $0x3,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R8,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4110a0 <memset@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x58(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x38(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV (%R8,%RDX,8),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 53ee72 <hypre_CSRMatrixMultiply._omp_fn.0+0x4b2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R8,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R15,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x48(%RAX),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x58(%RAX),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R8,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 411290 <GOMP_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x70(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JG 53ed11 <hypre_CSRMatrixMultiply._omp_fn.0+0x351>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD $0x78,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
JMP 552440 <hypre_Free>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x90(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%R8,%RDI,8),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ $0,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
LEA (%RAX,%R11,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R11,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 53ef74 <hypre_CSRMatrixMultiply._omp_fn.0+0x5b4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB $0x8,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x7,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 53ef34 <hypre_CSRMatrixMultiply._omp_fn.0+0x574>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef25 <hypre_CSRMatrixMultiply._omp_fn.0+0x565>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef1b <hypre_CSRMatrixMultiply._omp_fn.0+0x55b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef11 <hypre_CSRMatrixMultiply._omp_fn.0+0x551>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef07 <hypre_CSRMatrixMultiply._omp_fn.0+0x547>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53eefd <hypre_CSRMatrixMultiply._omp_fn.0+0x53d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53eef3 <hypre_CSRMatrixMultiply._omp_fn.0+0x533>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV (%RAX),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef74 <hypre_CSRMatrixMultiply._omp_fn.0+0x5b4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R8,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 540d30 <hypre_CSRMatrixCreate>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x88(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,0x40(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,(%RAX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 540e40 <hypre_CSRMatrixInitialize>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x40(%R14),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%R10),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%R10),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R8,0x58(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDI,0x48(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 411290 <GOMP_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x70(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JG 53ed11 <hypre_CSRMatrixMultiply._omp_fn.0+0x351>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 53ed2e <hypre_CSRMatrixMultiply._omp_fn.0+0x36e>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
LEA (%RDX,%RBX,1),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 53ea6e <hypre_CSRMatrixMultiply._omp_fn.0+0xae>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV -0x38(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R8,%R11,8),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JMP 53ed43 <hypre_CSRMatrixMultiply._omp_fn.0+0x383>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run gcc_5

Source file and lines	csr_matop.c:185-302
Module	exec

The function is defined in /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:185,192-302.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Details

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

CALL instructions

Detected function call instructions.

Details

GOMP_barrier@plt: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:239
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:265
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:265
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:265
hypre_CAlloc: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:208
hypre_CSRMatrixCreate: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:257
hypre_CSRMatrixInitialize: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:259
hypre_GetThreadNum: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:192
hypre_NumActiveThreads: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:193
memset@plt: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:269

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

ADD: 7 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:249
IDIV: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:204

Conversion instructions

Detected expensive conversion instructions.

Details

CQTO: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c:204

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

Matching between your function (in the source code) and the binary function

The binary function does not contain any FP arithmetical operations. The binary function is loading 624 bytes. The binary function is storing 360 bytes.

General properties

nb instructions	287
nb uops	309
loop length	1072
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	13

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	51.50 cycles
front end	51.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	21.80	21.80	28.00	28.00	31.00	21.80	21.80	31.00	31.00	31.00	21.80	28.00
cycles	21.80	21.80	28.00	28.00	31.00	21.80	21.80	31.00	31.00	31.00	21.80	28.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

10.00

Cycles summary

Front-end	51.50
Dispatch	31.00
DIV/SQRT	10.00
Overall L1	51.50

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	0%

Vector efficiency ratios

all	12%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 51.50 cycles. At this rate:

6% of peak load performance is reached (12.12 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (6.99 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 53e9c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB $0x78,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x60(%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x50(%RDI),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x38(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x28(%RDI),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RDI),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x68(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x30(%RDI),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x20(%RDI),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%RDI),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x8(%RDI),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDX,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R11,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RCX,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDI,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RBX),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 555090 <hypre_GetThreadNum>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 555080 <hypre_NumActiveThreads>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x80(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CQTO	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (12.5%)
IDIV %R10	5	0	3	0	0	0	0	0	0	0	0	0	0	11-16	10	scal (12.5%)
MOV -0x38(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RAX,%RBX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RBX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP %RDX,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 53efcf <hypre_CSRMatrixMultiply._omp_fn.0+0x60f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%R14,%RBX,1),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x1(%R14,%RAX,1),%R8	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RSI,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x70(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x8,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 5523b0 <hypre_CAlloc>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x70(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JLE 53eaaf <hypre_CSRMatrixMultiply._omp_fn.0+0xef>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0xff,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (,%RDI,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R9,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4110a0 <memset@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x38(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R10,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 53eb5f <hypre_CSRMatrixMultiply._omp_fn.0+0x19f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R9,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R13,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x40(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x48(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R8,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x78(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R14,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,(%R10,%R14,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R9,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 411290 <GOMP_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
TEST %R14,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
MOV -0x98(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JE 53ee88 <hypre_CSRMatrixMultiply._omp_fn.0+0x4c8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x78(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R9),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x8(%R9),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R9,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x1,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JLE 53ec47 <hypre_CSRMatrixMultiply._omp_fn.0+0x287>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RDX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SUB %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
SUB $0x8,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SHR $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
INC %RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
AND $0x7,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (6.3%)
JE 53ec1f <hypre_CSRMatrixMultiply._omp_fn.0+0x25f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ec13 <hypre_CSRMatrixMultiply._omp_fn.0+0x253>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ec0c <hypre_CSRMatrixMultiply._omp_fn.0+0x24c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ec05 <hypre_CSRMatrixMultiply._omp_fn.0+0x245>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ebfe <hypre_CSRMatrixMultiply._omp_fn.0+0x23e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ebf7 <hypre_CSRMatrixMultiply._omp_fn.0+0x237>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ebf0 <hypre_CSRMatrixMultiply._omp_fn.0+0x230>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x10,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R11	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ec47 <hypre_CSRMatrixMultiply._omp_fn.0+0x287>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x38(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RSI,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 53ee5a <hypre_CSRMatrixMultiply._omp_fn.0+0x49a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%R8,%RSI,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R8,%R14,8),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %R10,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB $0x8,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x7,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 53ecd1 <hypre_CSRMatrixMultiply._omp_fn.0+0x311>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecc5 <hypre_CSRMatrixMultiply._omp_fn.0+0x305>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecbe <hypre_CSRMatrixMultiply._omp_fn.0+0x2fe>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecb7 <hypre_CSRMatrixMultiply._omp_fn.0+0x2f7>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecb0 <hypre_CSRMatrixMultiply._omp_fn.0+0x2f0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53eca9 <hypre_CSRMatrixMultiply._omp_fn.0+0x2e9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53eca2 <hypre_CSRMatrixMultiply._omp_fn.0+0x2e2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %R11,(%R10)	2	0.20	0.20	0.33	0.33	0.50	0.20	0.20	0.50	0.50	0.50	0.20	0.33	1	0.50	scal (12.5%)
ADD $0x8,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RDI,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ecf9 <hypre_CSRMatrixMultiply._omp_fn.0+0x339>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R8,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 411290 <GOMP_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x70(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JLE 53efe3 <hypre_CSRMatrixMultiply._omp_fn.0+0x623>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0xff,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAL $0x3,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R8,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4110a0 <memset@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x58(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x38(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV (%R8,%RDX,8),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 53ee72 <hypre_CSRMatrixMultiply._omp_fn.0+0x4b2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R8,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R15,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x48(%RAX),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x58(%RAX),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R8,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 411290 <GOMP_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x70(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JG 53ed11 <hypre_CSRMatrixMultiply._omp_fn.0+0x351>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD $0x78,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
JMP 552440 <hypre_Free>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x90(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%R8,%RDI,8),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ $0,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
LEA (%RAX,%R11,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R11,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 53ef74 <hypre_CSRMatrixMultiply._omp_fn.0+0x5b4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB $0x8,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x7,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 53ef34 <hypre_CSRMatrixMultiply._omp_fn.0+0x574>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef25 <hypre_CSRMatrixMultiply._omp_fn.0+0x565>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef1b <hypre_CSRMatrixMultiply._omp_fn.0+0x55b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef11 <hypre_CSRMatrixMultiply._omp_fn.0+0x551>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef07 <hypre_CSRMatrixMultiply._omp_fn.0+0x547>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53eefd <hypre_CSRMatrixMultiply._omp_fn.0+0x53d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53eef3 <hypre_CSRMatrixMultiply._omp_fn.0+0x533>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV (%RAX),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD (%RAX),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 53ef74 <hypre_CSRMatrixMultiply._omp_fn.0+0x5b4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R8,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 540d30 <hypre_CSRMatrixCreate>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x88(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,0x40(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,(%RAX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 540e40 <hypre_CSRMatrixInitialize>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x40(%R14),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%R10),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%R10),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R8,0x58(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDI,0x48(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 411290 <GOMP_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x70(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JG 53ed11 <hypre_CSRMatrixMultiply._omp_fn.0+0x351>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 53ed2e <hypre_CSRMatrixMultiply._omp_fn.0+0x36e>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
LEA (%RDX,%RBX,1),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 53ea6e <hypre_CSRMatrixMultiply._omp_fn.0+0xae>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV -0x38(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R8,%R11,8),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JMP 53ed43 <hypre_CSRMatrixMultiply._omp_fn.0+0x383>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A

Name	Coverage (%)	Time (s)
▼hypre_CSRMatrixMultiply._omp_fn.0–	0.99	0.43
▼Loop 2825 - csr_matop.c:272-298 - exec–	0.00	0.01
▼Loop 2826 - csr_matop.c:282-298 - exec–	0.14	0.05
○Loop 2827 - csr_matop.c:286-298 - exec	0.46	0.17
○Loop 2829 - csr_matop.c:248-249 - exec	0.00	0.00
▼Loop 2831 - csr_matop.c:214-231 - exec–	0.00	0.00
▼Loop 2832 - csr_matop.c:222-231 - exec–	0.12	0.05
○Loop 2833 - csr_matop.c:225-231 - exec	0.26	0.10
○Loop 2830 - csr_matop.c:245-246 - exec	0.00	0.00
○Loop 2828 - csr_matop.c:254-255 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code