OV - exec - Function hypre_ParMatmul_RowSizes.omp

	Function: hypre_ParMatmul_RowSizes.omp_outlined	Module: exec	Source: par_csr_matop.c:102-276 [...]	Coverage (incl. loops): 0.68% \| (excl. loops): 0.00%

/home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 102 - 276

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

102: #pragma omp parallel private(ii, i1, jj_row_begin_diag, jj_row_begin_offd, jj_count_diag, jj_count_offd, jj2, i2, jj3, i3)

[...]

108:     ii = hypre_GetThreadNum();

109:     if (ii < rest)

110:     {

111:        ns = ii*size+ii;

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

113:     }

114:     else

115:     {

116:        ns = ii*size+rest;

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

118:     }

119:     jj_count_diag = start_indexing;

120:     jj_count_offd = start_indexing;

121:

122:     if (num_cols_diag_B || num_cols_offd_C)

123:     B_marker = hypre_CTAlloc(HYPRE_Int, num_cols_diag_B+num_cols_offd_C);

124:     for (i1 = 0; i1 < num_cols_diag_B+num_cols_offd_C; i1++)

125:       B_marker[i1] = -1;

126:

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

[...]

135:       if ( allsquare ) {

136:          B_marker[i1] = jj_count_diag;

137:          jj_count_diag++;

[...]

144:       if (num_cols_offd_A)

145:       {

146:          for (jj2 = A_offd_i[i1]; jj2 < A_offd_i[i1+1]; jj2++)

147:          {

148:             i2 = A_offd_j[jj2];

[...]

154:             for (jj3 = B_ext_offd_i[i2]; jj3 < B_ext_offd_i[i2+1]; jj3++)

155:             {

156:                i3 = num_cols_diag_B+B_ext_offd_j[jj3];

[...]

164:                if (B_marker[i3] < jj_row_begin_offd)

165:                {

166:                   B_marker[i3] = jj_count_offd;

167:                   jj_count_offd++;

168:                }

169:             }

170:             for (jj3 = B_ext_diag_i[i2]; jj3 < B_ext_diag_i[i2+1]; jj3++)

171:             {

172:                i3 = B_ext_diag_j[jj3];

173:

174:                if (B_marker[i3] < jj_row_begin_diag)

175:                {

176:                   B_marker[i3] = jj_count_diag;

177:                   jj_count_diag++;

[...]

187:       for (jj2 = A_diag_i[i1]; jj2 < A_diag_i[i1+1]; jj2++)

188:       {

189:          i2 = A_diag_j[jj2];

[...]

195:          for (jj3 = B_diag_i[i2]; jj3 < B_diag_i[i2+1]; jj3++)

196:          {

197:             i3 = B_diag_j[jj3];

[...]

205:             if (B_marker[i3] < jj_row_begin_diag)

206:             {

207:                B_marker[i3] = jj_count_diag;

208:                jj_count_diag++;

[...]

216:          if (num_cols_offd_B)

217:          {

218:             for (jj3 = B_offd_i[i2]; jj3 < B_offd_i[i2+1]; jj3++)

219:             {

220:                i3 = num_cols_diag_B+map_B_to_C[B_offd_j[jj3]];

[...]

228:                if (B_marker[i3] < jj_row_begin_offd)

229:                {

230:                   B_marker[i3] = jj_count_offd;

231:                   jj_count_offd++;

[...]

241:       (*C_diag_i)[i1] = jj_row_begin_diag;

242:       (*C_offd_i)[i1] = jj_row_begin_offd;

243:

244:     }

245:     jj_count_diag_array[ii] = jj_count_diag;

246:     jj_count_offd_array[ii] = jj_count_offd;

247:

248:     hypre_TFree(B_marker);

249: #ifdef HYPRE_USING_OPENMP

250: #pragma omp barrier

251: #endif

252:

253:     if (ii)

254:     {

255:        jj_count_diag = jj_count_diag_array[0];

256:        jj_count_offd = jj_count_offd_array[0];

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

258:        {

259:           jj_count_diag += jj_count_diag_array[i1];

260:           jj_count_offd += jj_count_offd_array[i1];

261:        }

262:

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

264:        {

265:           (*C_diag_i)[i1] += jj_count_diag;

266:           (*C_offd_i)[i1] += jj_count_offd;

267:        }

268:     }

269:     else

270:     {

271:        (*C_diag_i)[num_rows_diag_A] = 0;

272:        (*C_offd_i)[num_rows_diag_A] = 0;

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

274:        {

275:           (*C_diag_i)[num_rows_diag_A] += jj_count_diag_array[i1];

276:           (*C_offd_i)[num_rows_diag_A] += jj_count_offd_array[i1];

0x486100 SUB	SP, SP, #240

0x486104 STP	X29, X30, [SP, #144]

0x486108 STP	X28, X27, [SP, #160]

0x48610c STP	X26, X25, [SP, #176]

0x486110 STP	X24, X23, [SP, #192]

0x486114 STP	X22, X21, [SP, #208]

0x486118 STP	X20, X19, [SP, #224]

0x48611c ADD	X29, SP, #144

0x486120 LDR	X8, [X29, #240]

0x486124 STUR	X7, [X29, #496]

0x486128 ORR	X23, XZR, X6

0x48612c ORR	X22, XZR, X5

0x486130 ORR	X24, XZR, X4

0x486134 ORR	X25, XZR, X3

0x486138 ORR	X26, XZR, X2

0x48613c STR	X0, [SP, #24]

0x486140 STR	X8, [SP, #40]

0x486144 LDR	X8, [X29, #232]

0x486148 STR	X8, [SP, #32]

0x48614c LDP	X8, X21, [X29, #216]

0x486150 STR	X8, [SP, #64]

0x486154 BL	4ae1b0

0x486158 LDR	X13, [X26]

0x48615c LDR	X11, [X25]

0x486160 ADD	X8, X0, #1

0x486164 LDR	X20, [X24]

0x486168 MADD	X9, X11, X0, X13

0x48616c MADD	X10, X11, X8, X13

0x486170 STP	X11, X13, [SP]

0x486174 ADD	X11, X11, #1

0x486178 STR	X0, [SP, #48]

0x48617c MUL	X12, X11, X0

0x486180 MUL	X8, X8, X11

0x486184 CMP	X0, X13

0x486188 CSEL	X26, X9, X12, #10

0x48618c CSEL	X19, X10, X8, #10

0x486190 LDR	X8, [X22]

0x486194 LDR	X9, [X23]

0x486198 ORR	X10, X8, X9

0x48619c CBNZ	X10, 4861a8

0x4861a0 ORR	X0, XZR, XZR

0x4861a4 B	4861fc

0x4861a8 ADD	X0, X9, X8

0x4861ac MOVZ	W1, #8

0x4861b0 BL	4ac4b0

0x4861b4 LDR	X8, [X22]

0x4861b8 LDR	X9, [X23]

0x4861bc ADD	X8, X9, X8

0x4861c0 CMP	X8, #1

0x4861c4 B.LT	4861fc

0x4861c8 MOVN	X9, #0

0x4861cc ORR	X8, XZR, XZR

0x4861d0 HINT	#0

0x4861d4 HINT	#0

0x4861d8 HINT	#0

0x4861dc HINT	#0

(2923) 0x4861e0 STR	X9, [X0, X8,LSL #3]

(2923) 0x4861e4 ADD	X8, X8, #1

(2923) 0x4861e8 LDR	X10, [X22]

(2923) 0x4861ec LDR	X11, [X23]

(2923) 0x4861f0 ADD	X10, X11, X10

(2923) 0x4861f4 CMP	X8, X10

(2923) 0x4861f8 B.LT	4861e0

0x4861fc CMP	X26, X19

0x486200 STR	X21, [SP, #56]

0x486204 STR	X26, [SP, #16]

0x486208 B.GE	486498

0x48620c LDP	X8, X9, [X29, #200]

0x486210 LDP	X12, X13, [X29, #136]

0x486214 ORR	X23, XZR, X20

0x486218 ORR	X6, XZR, X20

0x48621c STP	X8, X9, [X29, #984]

0x486220 LDP	X8, X10, [X29, #168]

0x486224 LDP	X11, X9, [X29, #184]

0x486228 STUR	X13, [X29, #448]

0x48622c LDR	X13, [X29, #128]

0x486230 LDR	X1, [X12]

0x486234 LDP	X15, X16, [X29, #96]

0x486238 LDR	X16, [X16]

0x48623c LDR	X4, [X8]

0x486240 LDR	X8, [SP, #64]

0x486244 STP	X10, X9, [X29, #968]

0x486248 LDR	X8, [X8]

0x48624c LDP	X10, X9, [X29, #152]

0x486250 STR	X13, [SP, #72]

0x486254 LDP	X14, X13, [X29, #112]

0x486258 LDR	X17, [X14]

0x48625c LDR	X18, [X13]

0x486260 LDR	X2, [X10]

0x486264 LDR	X3, [X9]

0x486268 STUR	X16, [X29, #488]

0x48626c LDR	X5, [X8]

0x486270 LDR	X8, [X21]

0x486274 ORR	X21, XZR, X19

0x486278 LDR	X7, [X8]

0x48627c B	4862a0

      (2915) 0x486280 CMP	X30, X21

      (2915) 0x486284 STR	X23, [X5, X26,LSL #3]

      (2915) 0x486288 STR	X20, [X7, X26,LSL #3]

      (2915) 0x48628c ORR	X19, XZR, X21

      (2915) 0x486290 ORR	X20, XZR, X24

      (2915) 0x486294 ORR	X23, XZR, X6

      (2915) 0x486298 ORR	X26, XZR, X30

      (2915) 0x48629c B.EQ	4864a0

      (2915) 0x4862a0 LDUR	X8, [X29, #496]

      (2915) 0x4862a4 LDR	X8, [X8]

      (2915) 0x4862a8 CBZ	X8, 4862b4

      (2915) 0x4862ac ADD	X6, X23, #1

      (2915) 0x4862b0 STR	X23, [X0, X26,LSL #3]

      (2915) 0x4862b4 LDR	X8, [X15]

      (2915) 0x4862b8 CBZ	X8, 486380

      (2915) 0x4862bc LDUR	X8, [X29, #488]

      (2915) 0x4862c0 ADD	X13, X8, X26,LSL #3

      (2915) 0x4862c4 LDP	X14, X8, [X13]

      (2915) 0x4862c8 CMP	X14, X8

      (2915) 0x4862cc B.GE	4863a0

      (2915) 0x4862d0 LDR	X8, [SP, #72]

      (2915) 0x4862d4 ORR	X24, XZR, X20

      (2915) 0x4862d8 LDR	X19, [X8]

      (2915) 0x4862dc LDUR	X8, [X29, #448]

      (2915) 0x4862e0 LDR	X27, [X8]

      (2915) 0x4862e4 B	4862f8

        (2919) 0x4862e8 LDR	X8, [X13, #8]

        (2919) 0x4862ec ADD	X14, X14, #1

        (2919) 0x4862f0 CMP	X14, X8

        (2919) 0x4862f4 B.GE	486384

        (2919) 0x4862f8 LDR	X28, [X17, X14,LSL #3]

        (2919) 0x4862fc ADD	X8, X28, #1

        (2919) 0x486300 LDR	X9, [X18, X28,LSL #3]

        (2919) 0x486304 LDR	X10, [X18, X8,LSL #3]

        (2919) 0x486308 B	486310

          (2921) 0x48630c ADD	X9, X9, #1

          (2921) 0x486310 CMP	X9, X10

          (2921) 0x486314 B.GE	486340

          (2921) 0x486318 LDR	X25, [X22]

          (2921) 0x48631c LDR	X12, [X19, X9,LSL #3]

          (2921) 0x486320 ADD	X30, X0, X25,LSL #3

          (2921) 0x486324 LDR	X25, [X30, X12,LSL #3]

          (2921) 0x486328 CMP	X25, X20

          (2921) 0x48632c B.GE	48630c

          (2921) 0x486330 STR	X24, [X30, X12,LSL #3]

          (2921) 0x486334 ADD	X24, X24, #1

          (2921) 0x486338 LDR	X10, [X18, X8,LSL #3]

          (2921) 0x48633c B	48630c

        (2919) 0x486340 LDR	X9, [X1, X28,LSL #3]

        (2919) 0x486344 LDR	X10, [X1, X8,LSL #3]

        (2919) 0x486348 B	486350

          (2920) 0x48634c ADD	X9, X9, #1

          (2920) 0x486350 CMP	X9, X10

          (2920) 0x486354 B.GE	4862e8

          (2920) 0x486358 LDR	X12, [X27, X9,LSL #3]

          (2920) 0x48635c LDR	X25, [X0, X12,LSL #3]

          (2920) 0x486360 CMP	X25, X23

          (2920) 0x486364 B.GE	48634c

          (2920) 0x486368 STR	X6, [X0, X12,LSL #3]

          (2920) 0x48636c ADD	X6, X6, #1

          (2920) 0x486370 LDR	X10, [X1, X8,LSL #3]

          (2920) 0x486374 B	48634c

0x486378 HINT	#0

0x48637c HINT	#0

      (2915) 0x486380 ORR	X24, XZR, X20

      (2915) 0x486384 ADD	X30, X26, #1

      (2915) 0x486388 LDR	X28, [X2, X26,LSL #3]

      (2915) 0x48638c LDR	X8, [X2, X30,LSL #3]

      (2915) 0x486390 CMP	X28, X8

      (2915) 0x486394 B.GE	486280

    (2916) 0x486398 B	4863b8

0x48639c HINT	#0

      (2915) 0x4863a0 ORR	X24, XZR, X20

      (2915) 0x4863a4 ADD	X30, X26, #1

      (2915) 0x4863a8 LDR	X28, [X2, X26,LSL #3]

      (2915) 0x4863ac LDR	X8, [X2, X30,LSL #3]

      (2915) 0x4863b0 CMP	X28, X8

      (2915) 0x4863b4 B.GE	486280

    (2916) 0x4863b8 LDP	X9, X8, [X29, #968]

    (2916) 0x4863bc LDR	X27, [X9]

    (2916) 0x4863c0 LDR	X13, [X8]

    (2916) 0x4863c4 LDP	X9, X8, [X29, #984]

    (2916) 0x4863c8 LDR	X14, [X9]

    (2916) 0x4863cc LDR	X19, [X8]

    (2916) 0x4863d0 B	4863f0

0x4863d4 HINT	#0

0x4863d8 HINT	#0

0x4863dc HINT	#0

    (2916) 0x4863e0 LDR	X8, [X2, X30,LSL #3]

    (2916) 0x4863e4 ADD	X28, X28, #1

    (2916) 0x4863e8 CMP	X28, X8

    (2916) 0x4863ec B.GE	486280

    (2916) 0x4863f0 LDR	X9, [X3, X28,LSL #3]

    (2916) 0x4863f4 ADD	X8, X9, #1

    (2916) 0x4863f8 LDR	X10, [X4, X9,LSL #3]

    (2916) 0x4863fc LDR	X12, [X4, X8,LSL #3]

    (2916) 0x486400 B	486408

      (2918) 0x486404 ADD	X10, X10, #1

      (2918) 0x486408 CMP	X10, X12

      (2918) 0x48640c B.GE	486440

      (2918) 0x486410 LDR	X25, [X27, X10,LSL #3]

      (2918) 0x486414 LDR	X16, [X0, X25,LSL #3]

      (2918) 0x486418 CMP	X16, X23

      (2918) 0x48641c B.GE	486404

      (2918) 0x486420 STR	X6, [X0, X25,LSL #3]

      (2918) 0x486424 ADD	X6, X6, #1

      (2918) 0x486428 LDR	X12, [X4, X8,LSL #3]

      (2918) 0x48642c B	486404

0x486430 HINT	#0

0x486434 HINT	#0

0x486438 HINT	#0

0x48643c HINT	#0

    (2916) 0x486440 LDR	X10, [X11]

    (2916) 0x486444 CBZ	X10, 4863e0

  (2917) 0x486448 LDR	X9, [X13, X9,LSL #3]

  (2917) 0x48644c LDR	X10, [X13, X8,LSL #3]

  (2917) 0x486450 B	486464

0x486454 HINT	#0

0x486458 HINT	#0

0x48645c HINT	#0

(2922) 0x486460 ADD	X9, X9, #1

  (2917) 0x486464 CMP	X9, X10

  (2917) 0x486468 B.GE	4863e0

(2922) 0x48646c LDR	X12, [X19, X9,LSL #3]

(2922) 0x486470 LDR	X16, [X22]

(2922) 0x486474 LDR	X12, [X14, X12,LSL #3]

(2922) 0x486478 ADD	X25, X0, X16,LSL #3

(2922) 0x48647c LDR	X16, [X25, X12,LSL #3]

(2922) 0x486480 CMP	X16, X20

(2922) 0x486484 B.GE	486460

(2922) 0x486488 STR	X24, [X25, X12,LSL #3]

(2922) 0x48648c ADD	X24, X24, #1

(2922) 0x486490 LDR	X10, [X13, X8,LSL #3]

(2922) 0x486494 B	486460

0x486498 ORR	X6, XZR, X20

0x48649c ORR	X24, XZR, X20

0x4864a0 LDP	X22, X21, [SP, #32]

0x4864a4 LDR	X20, [SP, #48]

0x4864a8 LDR	X8, [X22]

0x4864ac STR	X6, [X8, X20,LSL #3]

0x4864b0 LDR	X8, [X21]

0x4864b4 STR	X24, [X8, X20,LSL #3]

0x4864b8 BL	4ac5b0

0x4864bc LDR	X8, [SP, #24]

0x4864c0 ADRP	X0,

0x4864c4 ADD	X0, X0, #2712

0x4864c8 LDR	W1, [X8]

0x4864cc BL	410070

0x4864d0 CBZ	X20, 486504

0x4864d4 LDR	X10, [X22]

0x4864d8 LDR	X11, [X21]

0x4864dc LDR	X16, [SP, #56]

0x4864e0 CMP	X20, #2

0x4864e4 LDR	X8, [X10]

0x4864e8 LDR	X9, [X11]

0x4864ec B.LT	486584

0x4864f0 LDR	X17, [SP, #16]

0x4864f4 CMP	X20, #5

0x4864f8 B.CS	48658c

0x4864fc MOVZ	W12, #1

0x486500 B	486608

0x486504 LDP	X11, X9, [SP, #56]

0x486508 LDR	X8, [X29, #248]

0x48650c LDR	X9, [X9]

0x486510 LDR	X10, [X8]

0x486514 LDR	X11, [X11]

0x486518 LDR	X9, [X9]

0x48651c LDR	X11, [X11]

0x486520 STR	XZR, [X9, X10,LSL #3]

0x486524 LDR	X10, [X29, #256]

0x486528 LDR	X12, [X8]

0x48652c STR	XZR, [X11, X12,LSL #3]

0x486530 LDR	X12, [X10]

0x486534 CMP	X12, #1

0x486538 B.LT	48677c

0x48653c LDR	X13, [X22]

0x486540 LDR	X14, [X21]

0x486544 ORR	X12, XZR, XZR

(2910) 0x486548 LDR	X16, [X8]

(2910) 0x48654c LDR	X15, [X13, X12,LSL #3]

(2910) 0x486550 LDR	X17, [X9, X16,LSL #3]

(2910) 0x486554 ADD	X15, X17, X15

(2910) 0x486558 STR	X15, [X9, X16,LSL #3]

(2910) 0x48655c LDR	X16, [X8]

(2910) 0x486560 LDR	X15, [X14, X12,LSL #3]

(2910) 0x486564 ADD	X12, X12, #1

(2910) 0x486568 LDR	X17, [X11, X16,LSL #3]

(2910) 0x48656c ADD	X15, X17, X15

(2910) 0x486570 STR	X15, [X11, X16,LSL #3]

(2910) 0x486574 LDR	X15, [X10]

(2910) 0x486578 CMP	X12, X15

(2910) 0x48657c B.LT	486548

0x486580 B	48677c

0x486584 LDR	X17, [SP, #16]

0x486588 B	486638

0x48658c MOVI	V2.2D, #0

0x486590 MOVI	V1.2D, #0

0x486594 SUB	X13, X20, #1

0x486598 MOVI	V0.2D, #0

0x48659c MOVI	V3.2D, #0

0x4865a0 AND	X14, X13, #0x0

0x4865a4 AND	X15, X13, #0x0

0x4865a8 ORR	X12, X14, #0x1

0x4865ac MOV	V2.D[0], X9

0x4865b0 MOV	V1.D[0], X8

0x4865b4 ADD	X8, X10, #24

0x4865b8 ADD	X9, X11, #24

0x4865bc HINT	#0

(2913) 0x4865c0 LDP	Q4, Q5, [X8, #2032]

(2913) 0x4865c4 ADD	X8, X8, #32

(2913) 0x4865c8 SUBS	X15, X15, #4

(2913) 0x4865cc ADD	V0.2D, V5.2D, V0.2D

(2913) 0x4865d0 ADD	V1.2D, V4.2D, V1.2D

(2913) 0x4865d4 LDP	Q4, Q5, [X9, #2032]

(2913) 0x4865d8 ADD	X9, X9, #32

(2913) 0x4865dc ADD	V3.2D, V5.2D, V3.2D

(2913) 0x4865e0 ADD	V2.2D, V4.2D, V2.2D

(2913) 0x4865e4 B.NE	4865c0

0x4865e8 ADD	V2.2D, V3.2D, V2.2D

0x4865ec ADD	V0.2D, V0.2D, V1.2D

0x4865f0 CMP	X13, X14

0x4865f4 ADDP	D2, V2.2D

0x4865f8 ADDP	D0, V0.2D

0x4865fc FMOV	X9, D2

0x486600 FMOV	X8, D0

0x486604 B.EQ	486638

0x486608 ADD	X10, X10, X12,LSL #3

0x48660c ADD	X11, X11, X12,LSL #3

0x486610 SUB	X12, X20, X12

0x486614 HINT	#0

0x486618 HINT	#0

0x48661c HINT	#0

(2914) 0x486620 LDR	X13, [X10], #8

(2914) 0x486624 SUBS	X12, X12, #1

(2914) 0x486628 ADD	X8, X13, X8

(2914) 0x48662c LDR	X13, [X11], #8

(2914) 0x486630 ADD	X9, X13, X9

(2914) 0x486634 B.NE	486620

0x486638 CMP	X17, X19

0x48663c B.GE	48677c

0x486640 LDR	X10, [SP, #64]

0x486644 LDP	X13, X12, [SP]

0x486648 CMP	X20, X12

0x48664c CSEL	X12, X20, X12, #11

0x486650 LDR	X10, [X10]

0x486654 LDR	X11, [X16]

0x486658 LDR	X11, [X11]

0x48665c MADD	X12, X20, X13, X12

0x486660 SUB	X13, X19, X12

0x486664 LDR	X10, [X10]

0x486668 CMP	X13, #6

0x48666c B.CC	4866fc

0x486670 ADD	X12, X10, X17,LSL #3

0x486674 ADD	X16, X11, X19,LSL #3

0x486678 ADD	X14, X10, X19,LSL #3

0x48667c ADD	X15, X11, X17,LSL #3

0x486680 CMP	X12, X16

0x486684 CCMP	X15, X14, #2, #3

0x486688 B.CC	4866fc

0x48668c DUP	V0.2D, X8

0x486690 UBFM	X15, X17, #61, #60

0x486694 AND	X14, X13, #0x0

0x486698 ADD	X16, X15, #16

0x48669c DUP	V1.2D, X9

0x4866a0 ADD	X12, X17, X14

0x4866a4 AND	X17, X13, #0x0

0x4866a8 ADD	X15, X10, X16

0x4866ac ADD	X16, X11, X16

0x4866b0 HINT	#0

0x4866b4 HINT	#0

0x4866b8 HINT	#0

0x4866bc HINT	#0

(2912) 0x4866c0 LDP	Q2, Q3, [X15, #2032]

(2912) 0x4866c4 LDP	Q4, Q5, [X16, #2032]

(2912) 0x4866c8 SUBS	X17, X17, #4

(2912) 0x4866cc ADD	V3.2D, V3.2D, V0.2D

(2912) 0x4866d0 ADD	V2.2D, V2.2D, V0.2D

(2912) 0x4866d4 ADD	V4.2D, V4.2D, V1.2D

(2912) 0x4866d8 STP	Q2, Q3, [X15, #2032]

(2912) 0x4866dc ADD	V2.2D, V5.2D, V1.2D

(2912) 0x4866e0 ADD	X15, X15, #32

(2912) 0x4866e4 STP	Q4, Q2, [X16, #2032]

(2912) 0x4866e8 ADD	X16, X16, #32

(2912) 0x4866ec B.NE	4866c0

0x4866f0 CMP	X13, X14

0x4866f4 B.NE	486700

0x4866f8 B	48677c

0x4866fc ORR	X12, XZR, X17

0x486700 SUB	W14, W19, W12

0x486704 ADD	X13, X12, #1

0x486708 TBZ	W14, #0, 486728

0x48670c LDR	X14, [X10, X12,LSL #3]

0x486710 ADD	X14, X14, X8

0x486714 STR	X14, [X10, X12,LSL #3]

0x486718 LDR	X14, [X11, X12,LSL #3]

0x48671c ADD	X14, X14, X9

0x486720 STR	X14, [X11, X12,LSL #3]

0x486724 ORR	X12, XZR, X13

0x486728 CMP	X19, X13

0x48672c B.EQ	48677c

0x486730 SUB	X13, X19, X12

0x486734 UBFM	X12, X12, #61, #60

0x486738 ADD	X12, X12, #8

0x48673c ADD	X10, X10, X12

0x486740 ADD	X11, X11, X12

(2911) 0x486744 LDUR	X12, [X10, #504]

(2911) 0x486748 SUBS	X13, X13, #2

(2911) 0x48674c ADD	X12, X12, X8

(2911) 0x486750 STUR	X12, [X10, #504]

(2911) 0x486754 LDUR	X12, [X11, #504]

(2911) 0x486758 ADD	X12, X12, X9

(2911) 0x48675c STUR	X12, [X11, #504]

(2911) 0x486760 LDR	X12, [X10]

(2911) 0x486764 ADD	X12, X12, X8

(2911) 0x486768 STR	X12, [X10], #16

(2911) 0x48676c LDR	X12, [X11]

(2911) 0x486770 ADD	X12, X12, X9

(2911) 0x486774 STR	X12, [X11], #16

(2911) 0x486778 B.NE	486744

0x48677c LDP	X20, X19, [SP, #224]

0x486780 LDP	X22, X21, [SP, #208]

0x486784 LDP	X24, X23, [SP, #192]

0x486788 LDP	X26, X25, [SP, #176]

0x48678c LDP	X28, X27, [SP, #160]

0x486790 LDP	X29, X30, [SP, #144]

0x486794 ADD	SP, SP, #240

0x486798 RET

0x48679c HINT	#0

Coverage (%)	Name	Source Location	Module
►98.70+	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.30+	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	hypre_ParMatmul_RowSizes	par_csr_matop.c:286	exec
○	hypre_ParMatmul	par_csr_matop.c:811	exec
○	hypre_BoomerAMGSetup	par_amg_setup.c:1226	exec
○	hypre_PCGSetup	pcg.c:234	exec
○	main	amg.c:398	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start		exec

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

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 armclang_4

Source file and lines	par_csr_matop.c:102-276
Module	exec

The function is defined in /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:102,108-127,135-137,144-148,154-156,164-177,187-189,195-197,205-208,216-220,228-231,241-276.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 31.67 to 4.00 cycles (7.92x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your function is not vectorized. Only 29% of vector register length is used (average across all VPU instructions). By fully vectorizing your function, you can lower the cost of an iteration from 31.67 to 6.33 cycles (5.00x speedup).

Details

2% of VPU instructions are used in vector version (process two or more data elements in vector registers):

0% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
22% of VPU addition or subtraction instructions are used in vector version.
0% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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)

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.

hypre_CAlloc: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:123
hypre_Free: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:248
hypre_GetThreadNum: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:108
unknown: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:250

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 3 bytes.

General properties

nb instructions	240
nb uops	214
loop length	960
used w registers	4
used x registers	32
used b registers	0
used h registers	0
used s registers	1
used d registers	2
used q registers	0
used v registers	4
used z registers	0
nb stack references	31

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	26.75 cycles
front end	26.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	12.50	12.50	22.00	22.00	22.00	22.00	3.00	3.00	3.00	3.00	31.67	31.67	31.67	13.00	13.00
cycles	12.50	12.50	22.00	22.00	22.00	22.00	3.00	3.00	3.00	3.00	31.67	31.67	31.67	13.00	13.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	26.75
Dispatch	31.67
Overall L1	31.67

Vectorization ratios

INT

all	2%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	22%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	0%
load	NA (no load vectorizable/vectorized instructions)
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	0%

INT+FP

all	2%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	22%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

INT

all	29%
load	26%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	36%
fma	NA (no fma vectorizable/vectorized instructions)
other	24%

all	25%
load	NA (no load vectorizable/vectorized instructions)
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	25%

INT+FP

all	29%
load	26%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	36%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	24%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 31.67 cycles. At this rate:

0% of peak load performance is reached (0.09 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 486100

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
SUB SP, SP, #240	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STP X29, X30, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X28, X27, [SP, #160]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X26, X25, [SP, #176]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X24, X23, [SP, #192]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X22, X21, [SP, #208]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X20, X19, [SP, #224]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X29, SP, #144	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X8, [X29, #240]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STUR X7, [X29, #496]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ORR X23, XZR, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X22, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X24, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X25, XZR, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X26, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X0, [SP, #24]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR X8, [SP, #40]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X8, [X29, #232]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR X8, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDP X8, X21, [X29, #216]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
STR X8, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
BL 4ae1b0 <hypre_GetThreadNum>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X13, [X26]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X25]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X20, [X24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
MADD X9, X11, X0, X13	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
MADD X10, X11, X8, X13	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
STP X11, X13, [SP]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X11, X11, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X0, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
MUL X12, X11, X0	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
MUL X8, X8, X11	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
CMP X0, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CSEL X26, X9, X12, #10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CSEL X19, X10, X8, #10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X8, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X23]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X10, X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CBNZ X10, 4861a8 <hypre_ParMatmul_RowSizes.omp_outlined+0xa8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X0, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 4861fc <hypre_ParMatmul_RowSizes.omp_outlined+0xfc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X0, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
MOVZ W1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
BL 4ac4b0 <hypre_CAlloc>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X23]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LT 4861fc <hypre_ParMatmul_RowSizes.omp_outlined+0xfc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVN X9, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X8, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
CMP X26, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
STR X21, [SP, #56]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR X26, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
B.GE 486498 <hypre_ParMatmul_RowSizes.omp_outlined+0x398>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X8, X9, [X29, #200]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X12, X13, [X29, #136]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ORR X23, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X6, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
STP X8, X9, [X29, #984]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
LDP X8, X10, [X29, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X11, X9, [X29, #184]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
STUR X13, [X29, #448]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X13, [X29, #128]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X1, [X12]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDP X15, X16, [X29, #96]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X16, [X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X4, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X8, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STP X10, X9, [X29, #968]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
LDR X8, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDP X10, X9, [X29, #152]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
STR X13, [SP, #72]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDP X14, X13, [X29, #112]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X17, [X14]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X18, [X13]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X2, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X3, [X9]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
STUR X16, [X29, #488]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X5, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X8, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X21, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X7, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
B 4862a0 <hypre_ParMatmul_RowSizes.omp_outlined+0x1a0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
ORR X6, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X24, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDP X22, X21, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X20, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X8, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR X6, [X8, X20,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X8, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR X24, [X8, X20,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
BL 4ac5b0 <hypre_Free>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [SP, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADRP X0, <4fe4c0>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #2712	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR W1, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
BL 410070 <@plt_start@+0x50>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CBZ X20, 486504 <hypre_ParMatmul_RowSizes.omp_outlined+0x404>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X10, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X16, [SP, #56]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CMP X20, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
LDR X8, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X11]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
B.LT 486584 <hypre_ParMatmul_RowSizes.omp_outlined+0x484>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X17, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CMP X20, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CS 48658c <hypre_ParMatmul_RowSizes.omp_outlined+0x48c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVZ W12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
B 486608 <hypre_ParMatmul_RowSizes.omp_outlined+0x508>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X11, X9, [SP, #56]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X8, [X29, #248]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X9]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X10, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X11]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X9]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X11]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR XZR, [X9, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X10, [X29, #256]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X12, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR XZR, [X11, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X12, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CMP X12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LT 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X13, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X14, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X12, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
B 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X17, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
B 486638 <hypre_ParMatmul_RowSizes.omp_outlined+0x538>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVI V2.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
MOVI V1.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
SUB X13, X20, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVI V0.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
MOVI V3.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
AND X14, X13, #0x0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
AND X15, X13, #0x0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X12, X14, #0x1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV V2.D[0], X9	1	0	0	0	0	1	0	0.25	0.25	0.25	0.25	0	0	0	0	0	5	1	scal (25.0%)
MOV V1.D[0], X8	1	0	0	0	0	1	0	0.25	0.25	0.25	0.25	0	0	0	0	0	5	1	scal (25.0%)
ADD X8, X10, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X9, X11, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
ADD V2.2D, V3.2D, V2.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (50.0%)
ADD V0.2D, V0.2D, V1.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (50.0%)
CMP X13, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
ADDP D2, V2.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
ADDP D0, V0.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FMOV X9, D2	1	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	2	1	scal (25.0%)
FMOV X8, D0	1	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	2	1	scal (25.0%)
B.EQ 486638 <hypre_ParMatmul_RowSizes.omp_outlined+0x538>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X10, X10, X12,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X11, X11, X12,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SUB X12, X20, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
CMP X17, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.GE 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X10, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDP X13, X12, [SP]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
CMP X20, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CSEL X12, X20, X12, #11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X10, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X11]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
MADD X12, X20, X13, X12	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
SUB X13, X19, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X10, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CMP X13, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CC 4866fc <hypre_ParMatmul_RowSizes.omp_outlined+0x5fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X12, X10, X17,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X16, X11, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X14, X10, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X15, X11, X17,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CMP X12, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X15, X14, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B.CC 4866fc <hypre_ParMatmul_RowSizes.omp_outlined+0x5fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
DUP V0.2D, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (25.0%)
UBFM X15, X17, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
AND X14, X13, #0x0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X16, X15, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
DUP V1.2D, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (25.0%)
ADD X12, X17, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
AND X17, X13, #0x0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X15, X10, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X16, X11, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
CMP X13, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.NE 486700 <hypre_ParMatmul_RowSizes.omp_outlined+0x600>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X12, XZR, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SUB W14, W19, W12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X13, X12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
TBZ W14, #0, 486728 <hypre_ParMatmul_RowSizes.omp_outlined+0x628>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X14, [X10, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X14, X14, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X14, [X10, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X14, [X11, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X14, X14, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X14, [X11, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ORR X12, XZR, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X19, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB X13, X19, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
UBFM X12, X12, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X12, X12, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X10, X10, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X11, X11, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDP X20, X19, [SP, #224]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X22, X21, [SP, #208]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X24, X23, [SP, #192]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X26, X25, [SP, #176]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X28, X27, [SP, #160]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDP X29, X30, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADD SP, SP, #240	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																			N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run armclang_4

Source file and lines	par_csr_matop.c:102-276
Module	exec

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 31.67 to 4.00 cycles (7.92x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Details

2% of VPU instructions are used in vector version (process two or more data elements in vector registers):

0% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
22% of VPU addition or subtraction instructions are used in vector version.
0% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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)

No data for this section

CALL instructions

Detected function call instructions.

Details

hypre_CAlloc: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:123
hypre_Free: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:248
hypre_GetThreadNum: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:108
unknown: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-188-3659/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c:250

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 3 bytes.

General properties

nb instructions	240
nb uops	214
loop length	960
used w registers	4
used x registers	32
used b registers	0
used h registers	0
used s registers	1
used d registers	2
used q registers	0
used v registers	4
used z registers	0
nb stack references	31

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	26.75 cycles
front end	26.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	12.50	12.50	22.00	22.00	22.00	22.00	3.00	3.00	3.00	3.00	31.67	31.67	31.67	13.00	13.00
cycles	12.50	12.50	22.00	22.00	22.00	22.00	3.00	3.00	3.00	3.00	31.67	31.67	31.67	13.00	13.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	26.75
Dispatch	31.67
Overall L1	31.67

Vectorization ratios

INT

all	2%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	22%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	0%
load	NA (no load vectorizable/vectorized instructions)
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	0%

INT+FP

all	2%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	22%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

INT

all	29%
load	26%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	36%
fma	NA (no fma vectorizable/vectorized instructions)
other	24%

all	25%
load	NA (no load vectorizable/vectorized instructions)
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	25%

INT+FP

all	29%
load	26%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	36%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	24%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 31.67 cycles. At this rate:

0% of peak load performance is reached (0.09 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 486100

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
SUB SP, SP, #240	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STP X29, X30, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X28, X27, [SP, #160]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X26, X25, [SP, #176]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X24, X23, [SP, #192]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X22, X21, [SP, #208]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X20, X19, [SP, #224]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X29, SP, #144	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X8, [X29, #240]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STUR X7, [X29, #496]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ORR X23, XZR, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X22, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X24, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X25, XZR, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X26, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X0, [SP, #24]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR X8, [SP, #40]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X8, [X29, #232]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR X8, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDP X8, X21, [X29, #216]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
STR X8, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
BL 4ae1b0 <hypre_GetThreadNum>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X13, [X26]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X25]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X20, [X24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
MADD X9, X11, X0, X13	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
MADD X10, X11, X8, X13	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
STP X11, X13, [SP]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X11, X11, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X0, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
MUL X12, X11, X0	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
MUL X8, X8, X11	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
CMP X0, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CSEL X26, X9, X12, #10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CSEL X19, X10, X8, #10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X8, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X23]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X10, X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CBNZ X10, 4861a8 <hypre_ParMatmul_RowSizes.omp_outlined+0xa8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X0, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 4861fc <hypre_ParMatmul_RowSizes.omp_outlined+0xfc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X0, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
MOVZ W1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
BL 4ac4b0 <hypre_CAlloc>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X23]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LT 4861fc <hypre_ParMatmul_RowSizes.omp_outlined+0xfc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVN X9, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X8, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
CMP X26, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
STR X21, [SP, #56]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR X26, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
B.GE 486498 <hypre_ParMatmul_RowSizes.omp_outlined+0x398>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X8, X9, [X29, #200]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X12, X13, [X29, #136]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ORR X23, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ORR X6, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
STP X8, X9, [X29, #984]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
LDP X8, X10, [X29, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X11, X9, [X29, #184]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
STUR X13, [X29, #448]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X13, [X29, #128]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X1, [X12]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDP X15, X16, [X29, #96]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X16, [X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X4, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X8, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STP X10, X9, [X29, #968]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
LDR X8, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDP X10, X9, [X29, #152]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
STR X13, [SP, #72]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDP X14, X13, [X29, #112]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X17, [X14]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X18, [X13]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X2, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X3, [X9]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
STUR X16, [X29, #488]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X5, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X8, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X21, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X7, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
B 4862a0 <hypre_ParMatmul_RowSizes.omp_outlined+0x1a0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
ORR X6, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X24, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDP X22, X21, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X20, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X8, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR X6, [X8, X20,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X8, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR X24, [X8, X20,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
BL 4ac5b0 <hypre_Free>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [SP, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADRP X0, <4fe4c0>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #2712	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR W1, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
BL 410070 <@plt_start@+0x50>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CBZ X20, 486504 <hypre_ParMatmul_RowSizes.omp_outlined+0x404>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X10, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X16, [SP, #56]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CMP X20, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
LDR X8, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X11]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
B.LT 486584 <hypre_ParMatmul_RowSizes.omp_outlined+0x484>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X17, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CMP X20, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CS 48658c <hypre_ParMatmul_RowSizes.omp_outlined+0x48c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVZ W12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
B 486608 <hypre_ParMatmul_RowSizes.omp_outlined+0x508>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X11, X9, [SP, #56]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X8, [X29, #248]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X9]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X10, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X11]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X9, [X9]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X11]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR XZR, [X9, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X10, [X29, #256]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X12, [X8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR XZR, [X11, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X12, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CMP X12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LT 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X13, [X22]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X14, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X12, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
B 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X17, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
B 486638 <hypre_ParMatmul_RowSizes.omp_outlined+0x538>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVI V2.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
MOVI V1.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
SUB X13, X20, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVI V0.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
MOVI V3.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
AND X14, X13, #0x0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
AND X15, X13, #0x0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X12, X14, #0x1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV V2.D[0], X9	1	0	0	0	0	1	0	0.25	0.25	0.25	0.25	0	0	0	0	0	5	1	scal (25.0%)
MOV V1.D[0], X8	1	0	0	0	0	1	0	0.25	0.25	0.25	0.25	0	0	0	0	0	5	1	scal (25.0%)
ADD X8, X10, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X9, X11, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
ADD V2.2D, V3.2D, V2.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (50.0%)
ADD V0.2D, V0.2D, V1.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (50.0%)
CMP X13, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
ADDP D2, V2.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
ADDP D0, V0.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FMOV X9, D2	1	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	2	1	scal (25.0%)
FMOV X8, D0	1	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	2	1	scal (25.0%)
B.EQ 486638 <hypre_ParMatmul_RowSizes.omp_outlined+0x538>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X10, X10, X12,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X11, X11, X12,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SUB X12, X20, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
CMP X17, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.GE 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X10, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDP X13, X12, [SP]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
CMP X20, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CSEL X12, X20, X12, #11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X10, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X11]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
MADD X12, X20, X13, X12	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
SUB X13, X19, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X10, [X10]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CMP X13, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CC 4866fc <hypre_ParMatmul_RowSizes.omp_outlined+0x5fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X12, X10, X17,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X16, X11, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X14, X10, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X15, X11, X17,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CMP X12, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X15, X14, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B.CC 4866fc <hypre_ParMatmul_RowSizes.omp_outlined+0x5fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
DUP V0.2D, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (25.0%)
UBFM X15, X17, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
AND X14, X13, #0x0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X16, X15, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
DUP V1.2D, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (25.0%)
ADD X12, X17, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
AND X17, X13, #0x0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X15, X10, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X16, X11, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
CMP X13, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.NE 486700 <hypre_ParMatmul_RowSizes.omp_outlined+0x600>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X12, XZR, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SUB W14, W19, W12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X13, X12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
TBZ W14, #0, 486728 <hypre_ParMatmul_RowSizes.omp_outlined+0x628>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X14, [X10, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X14, X14, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X14, [X10, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X14, [X11, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X14, X14, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X14, [X11, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ORR X12, XZR, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X19, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 48677c <hypre_ParMatmul_RowSizes.omp_outlined+0x67c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB X13, X19, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
UBFM X12, X12, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X12, X12, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X10, X10, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X11, X11, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDP X20, X19, [SP, #224]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X22, X21, [SP, #208]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X24, X23, [SP, #192]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X26, X25, [SP, #176]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X28, X27, [SP, #160]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDP X29, X30, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADD SP, SP, #240	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																			N/A

Name	Coverage (%)	Time (s)
▼hypre_ParMatmul_RowSizes.omp_outlined–	0.68	0.33
○Loop 2912 - par_csr_matop.c:263-266 - exec	0.03	0.01
○Loop 2923 - par_csr_matop.c:124-125 - exec	0.00	0.00
○Loop 2911 - par_csr_matop.c:263-266 - exec	0.00	0.00
○Loop 2910 - par_csr_matop.c:273-276 - exec	0.00	0.00
○Loop 2913 - par_csr_matop.c:257-260 - exec	0.00	0.00
▼Loop 2922 - par_csr_matop.c:127-242 - exec–	0.00	0.00
▼Loop 2917 - par_csr_matop.c:127-242 - exec–	0.00	0.00
▼Loop 2916 - par_csr_matop.c:127-242 - exec–	0.20	0.07
○Loop 2918 - par_csr_matop.c:195-208 - exec	0.43	0.15
▼Loop 2915 - par_csr_matop.c:127-242 - exec–	0.02	0.01
▼Loop 2919 - par_csr_matop.c:146-177 - exec–	0.00	0.00
○Loop 2921 - par_csr_matop.c:154-167 - exec	0.00	0.00
○Loop 2920 - par_csr_matop.c:170-177 - exec	0.00	0.00
○Loop 2914 - par_csr_matop.c:257-260 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

CALL instructions

Details

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

Code clean check

Workaround

Vectorization

Details

Workaround

CALL instructions

Details

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