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];

0x483e40 SUB	SP, SP, #240

0x483e44 STP	X29, X30, [SP, #144]

0x483e48 STP	X28, X27, [SP, #160]

0x483e4c STP	X26, X25, [SP, #176]

0x483e50 STP	X24, X23, [SP, #192]

0x483e54 STP	X22, X21, [SP, #208]

0x483e58 STP	X20, X19, [SP, #224]

0x483e5c ADD	X29, SP, #144

0x483e60 LDR	X8, [X29, #240]

0x483e64 STUR	X7, [X29, #496]

0x483e68 ORR	X23, XZR, X6

0x483e6c ORR	X22, XZR, X5

0x483e70 ORR	X24, XZR, X4

0x483e74 ORR	X25, XZR, X3

0x483e78 ORR	X26, XZR, X2

0x483e7c STR	X0, [SP, #24]

0x483e80 STR	X8, [SP, #40]

0x483e84 LDR	X8, [X29, #232]

0x483e88 STR	X8, [SP, #32]

0x483e8c LDP	X8, X21, [X29, #216]

0x483e90 STR	X8, [SP, #64]

0x483e94 BL	4acc50

0x483e98 LDR	X13, [X26]

0x483e9c LDR	X11, [X25]

0x483ea0 ADD	X8, X0, #1

0x483ea4 LDR	X20, [X24]

0x483ea8 MADD	X9, X11, X0, X13

0x483eac MADD	X10, X11, X8, X13

0x483eb0 STP	X11, X13, [SP]

0x483eb4 ADD	X11, X11, #1

0x483eb8 STR	X0, [SP, #48]

0x483ebc MUL	X12, X11, X0

0x483ec0 MUL	X8, X8, X11

0x483ec4 CMP	X0, X13

0x483ec8 CSEL	X26, X9, X12, #10

0x483ecc CSEL	X19, X10, X8, #10

0x483ed0 LDR	X8, [X22]

0x483ed4 LDR	X9, [X23]

0x483ed8 ORR	X10, X8, X9

0x483edc CBNZ	X10, 483ee8

0x483ee0 ORR	X0, XZR, XZR

0x483ee4 B	483f3c

0x483ee8 ADD	X0, X9, X8

0x483eec MOVZ	W1, #8

0x483ef0 BL	4aaf00

0x483ef4 LDR	X8, [X22]

0x483ef8 LDR	X9, [X23]

0x483efc ADD	X8, X9, X8

0x483f00 CMP	X8, #1

0x483f04 B.LT	483f3c

0x483f08 MOVN	X9, #0

0x483f0c ORR	X8, XZR, XZR

0x483f10 HINT	#0

0x483f14 HINT	#0

0x483f18 HINT	#0

0x483f1c HINT	#0

(2763) 0x483f20 STR	X9, [X0, X8,LSL #3]

(2763) 0x483f24 ADD	X8, X8, #1

(2763) 0x483f28 LDR	X10, [X22]

(2763) 0x483f2c LDR	X11, [X23]

(2763) 0x483f30 ADD	X10, X11, X10

(2763) 0x483f34 CMP	X8, X10

(2763) 0x483f38 B.LT	483f20

0x483f3c CMP	X26, X19

0x483f40 STR	X26, [SP, #16]

0x483f44 STR	X21, [SP, #56]

0x483f48 B.GE	4841d8

0x483f4c LDP	X8, X9, [X29, #200]

0x483f50 LDP	X12, X13, [X29, #136]

0x483f54 ORR	X23, XZR, X20

0x483f58 ORR	X6, XZR, X20

0x483f5c STP	X8, X9, [X29, #984]

0x483f60 LDP	X8, X10, [X29, #168]

0x483f64 LDP	X11, X9, [X29, #184]

0x483f68 STUR	X13, [X29, #448]

0x483f6c LDR	X13, [X29, #128]

0x483f70 LDR	X1, [X12]

0x483f74 LDP	X15, X16, [X29, #96]

0x483f78 LDR	X16, [X16]

0x483f7c LDR	X4, [X8]

0x483f80 LDR	X8, [SP, #64]

0x483f84 STP	X10, X9, [X29, #968]

0x483f88 LDR	X8, [X8]

0x483f8c LDP	X10, X9, [X29, #152]

0x483f90 STR	X13, [SP, #72]

0x483f94 LDP	X14, X13, [X29, #112]

0x483f98 LDR	X17, [X14]

0x483f9c LDR	X18, [X13]

0x483fa0 LDR	X2, [X10]

0x483fa4 LDR	X3, [X9]

0x483fa8 STUR	X16, [X29, #488]

0x483fac LDR	X5, [X8]

0x483fb0 LDR	X8, [X21]

0x483fb4 ORR	X21, XZR, X19

0x483fb8 LDR	X7, [X8]

0x483fbc B	483fe0

      (2755) 0x483fc0 CMP	X30, X21

      (2755) 0x483fc4 STR	X23, [X5, X26,LSL #3]

      (2755) 0x483fc8 STR	X20, [X7, X26,LSL #3]

      (2755) 0x483fcc ORR	X19, XZR, X21

      (2755) 0x483fd0 ORR	X20, XZR, X24

      (2755) 0x483fd4 ORR	X23, XZR, X6

      (2755) 0x483fd8 ORR	X26, XZR, X30

      (2755) 0x483fdc B.EQ	4841e0

      (2755) 0x483fe0 LDUR	X8, [X29, #496]

      (2755) 0x483fe4 LDR	X8, [X8]

      (2755) 0x483fe8 CBZ	X8, 483ff4

      (2755) 0x483fec ADD	X6, X23, #1

      (2755) 0x483ff0 STR	X23, [X0, X26,LSL #3]

      (2755) 0x483ff4 LDR	X8, [X15]

      (2755) 0x483ff8 CBZ	X8, 4840c0

      (2755) 0x483ffc LDUR	X8, [X29, #488]

      (2755) 0x484000 ADD	X13, X8, X26,LSL #3

      (2755) 0x484004 LDP	X14, X8, [X13]

      (2755) 0x484008 CMP	X14, X8

      (2755) 0x48400c B.GE	4840e0

      (2755) 0x484010 LDR	X8, [SP, #72]

      (2755) 0x484014 ORR	X24, XZR, X20

      (2755) 0x484018 LDR	X19, [X8]

      (2755) 0x48401c LDUR	X8, [X29, #448]

      (2755) 0x484020 LDR	X27, [X8]

      (2755) 0x484024 B	484038

        (2759) 0x484028 LDR	X8, [X13, #8]

        (2759) 0x48402c ADD	X14, X14, #1

        (2759) 0x484030 CMP	X14, X8

        (2759) 0x484034 B.GE	4840c4

        (2759) 0x484038 LDR	X28, [X17, X14,LSL #3]

        (2759) 0x48403c ADD	X8, X28, #1

        (2759) 0x484040 LDR	X9, [X18, X28,LSL #3]

        (2759) 0x484044 LDR	X10, [X18, X8,LSL #3]

        (2759) 0x484048 B	484050

          (2761) 0x48404c ADD	X9, X9, #1

          (2761) 0x484050 CMP	X9, X10

          (2761) 0x484054 B.GE	484080

          (2761) 0x484058 LDR	X25, [X22]

          (2761) 0x48405c LDR	X12, [X19, X9,LSL #3]

          (2761) 0x484060 ADD	X30, X0, X25,LSL #3

          (2761) 0x484064 LDR	X25, [X30, X12,LSL #3]

          (2761) 0x484068 CMP	X25, X20

          (2761) 0x48406c B.GE	48404c

          (2761) 0x484070 STR	X24, [X30, X12,LSL #3]

          (2761) 0x484074 ADD	X24, X24, #1

          (2761) 0x484078 LDR	X10, [X18, X8,LSL #3]

          (2761) 0x48407c B	48404c

        (2759) 0x484080 LDR	X9, [X1, X28,LSL #3]

        (2759) 0x484084 LDR	X10, [X1, X8,LSL #3]

        (2759) 0x484088 B	484090

          (2760) 0x48408c ADD	X9, X9, #1

          (2760) 0x484090 CMP	X9, X10

          (2760) 0x484094 B.GE	484028

          (2760) 0x484098 LDR	X12, [X27, X9,LSL #3]

          (2760) 0x48409c LDR	X25, [X0, X12,LSL #3]

          (2760) 0x4840a0 CMP	X25, X23

          (2760) 0x4840a4 B.GE	48408c

          (2760) 0x4840a8 STR	X6, [X0, X12,LSL #3]

          (2760) 0x4840ac ADD	X6, X6, #1

          (2760) 0x4840b0 LDR	X10, [X1, X8,LSL #3]

          (2760) 0x4840b4 B	48408c

0x4840b8 HINT	#0

0x4840bc HINT	#0

      (2755) 0x4840c0 ORR	X24, XZR, X20

      (2755) 0x4840c4 ADD	X30, X26, #1

      (2755) 0x4840c8 LDR	X28, [X2, X26,LSL #3]

      (2755) 0x4840cc LDR	X8, [X2, X30,LSL #3]

      (2755) 0x4840d0 CMP	X28, X8

      (2755) 0x4840d4 B.GE	483fc0

    (2756) 0x4840d8 B	4840f8

0x4840dc HINT	#0

      (2755) 0x4840e0 ORR	X24, XZR, X20

      (2755) 0x4840e4 ADD	X30, X26, #1

      (2755) 0x4840e8 LDR	X28, [X2, X26,LSL #3]

      (2755) 0x4840ec LDR	X8, [X2, X30,LSL #3]

      (2755) 0x4840f0 CMP	X28, X8

      (2755) 0x4840f4 B.GE	483fc0

    (2756) 0x4840f8 LDP	X9, X8, [X29, #968]

    (2756) 0x4840fc LDR	X27, [X9]

    (2756) 0x484100 LDR	X13, [X8]

    (2756) 0x484104 LDP	X9, X8, [X29, #984]

    (2756) 0x484108 LDR	X14, [X9]

    (2756) 0x48410c LDR	X19, [X8]

    (2756) 0x484110 B	484130

0x484114 HINT	#0

0x484118 HINT	#0

0x48411c HINT	#0

    (2756) 0x484120 LDR	X8, [X2, X30,LSL #3]

    (2756) 0x484124 ADD	X28, X28, #1

    (2756) 0x484128 CMP	X28, X8

    (2756) 0x48412c B.GE	483fc0

    (2756) 0x484130 LDR	X9, [X3, X28,LSL #3]

    (2756) 0x484134 ADD	X8, X9, #1

    (2756) 0x484138 LDR	X10, [X4, X9,LSL #3]

    (2756) 0x48413c LDR	X12, [X4, X8,LSL #3]

    (2756) 0x484140 B	484148

      (2758) 0x484144 ADD	X10, X10, #1

      (2758) 0x484148 CMP	X10, X12

      (2758) 0x48414c B.GE	484180

      (2758) 0x484150 LDR	X25, [X27, X10,LSL #3]

      (2758) 0x484154 LDR	X16, [X0, X25,LSL #3]

      (2758) 0x484158 CMP	X16, X23

      (2758) 0x48415c B.GE	484144

      (2758) 0x484160 STR	X6, [X0, X25,LSL #3]

      (2758) 0x484164 ADD	X6, X6, #1

      (2758) 0x484168 LDR	X12, [X4, X8,LSL #3]

      (2758) 0x48416c B	484144

0x484170 HINT	#0

0x484174 HINT	#0

0x484178 HINT	#0

0x48417c HINT	#0

    (2756) 0x484180 LDR	X10, [X11]

    (2756) 0x484184 CBZ	X10, 484120

  (2757) 0x484188 LDR	X9, [X13, X9,LSL #3]

  (2757) 0x48418c LDR	X10, [X13, X8,LSL #3]

  (2757) 0x484190 B	4841a4

0x484194 HINT	#0

0x484198 HINT	#0

0x48419c HINT	#0

(2762) 0x4841a0 ADD	X9, X9, #1

  (2757) 0x4841a4 CMP	X9, X10

  (2757) 0x4841a8 B.GE	484120

(2762) 0x4841ac LDR	X12, [X19, X9,LSL #3]

(2762) 0x4841b0 LDR	X16, [X22]

(2762) 0x4841b4 LDR	X12, [X14, X12,LSL #3]

(2762) 0x4841b8 ADD	X25, X0, X16,LSL #3

(2762) 0x4841bc LDR	X16, [X25, X12,LSL #3]

(2762) 0x4841c0 CMP	X16, X20

(2762) 0x4841c4 B.GE	4841a0

(2762) 0x4841c8 STR	X24, [X25, X12,LSL #3]

(2762) 0x4841cc ADD	X24, X24, #1

(2762) 0x4841d0 LDR	X10, [X13, X8,LSL #3]

(2762) 0x4841d4 B	4841a0

0x4841d8 ORR	X6, XZR, X20

0x4841dc ORR	X24, XZR, X20

0x4841e0 LDP	X22, X21, [SP, #32]

0x4841e4 LDR	X20, [SP, #48]

0x4841e8 LDR	X8, [X22]

0x4841ec STR	X6, [X8, X20,LSL #3]

0x4841f0 LDR	X8, [X21]

0x4841f4 STR	X24, [X8, X20,LSL #3]

0x4841f8 BL	4ab000

0x4841fc LDR	X8, [SP, #24]

0x484200 ADRP	X0,

0x484204 ADD	X0, X0, #2760

0x484208 LDR	W1, [X8]

0x48420c BL	4104c0

0x484210 CBZ	X20, 48424c

0x484214 LDR	X11, [X22]

0x484218 LDR	X12, [X21]

0x48421c LDR	X18, [SP, #56]

0x484220 CNTW	X10, ALL

0x484224 CMP	X20, #2

0x484228 LDR	X8, [X11]

0x48422c LDR	X9, [X12]

0x484230 B.LT	4842dc

0x484234 LDR	X1, [SP, #16]

0x484238 SUB	X14, X20, #1

0x48423c CMP	X14, X10

0x484240 B.CS	4842e4

0x484244 MOVZ	W13, #1

0x484248 B	484374

0x48424c LDP	X11, X9, [SP, #56]

0x484250 LDR	X8, [X29, #248]

0x484254 LDR	X9, [X9]

0x484258 LDR	X10, [X8]

0x48425c LDR	X11, [X11]

0x484260 LDR	X9, [X9]

0x484264 LDR	X11, [X11]

0x484268 STR	XZR, [X9, X10,LSL #3]

0x48426c LDR	X10, [X29, #256]

0x484270 LDR	X12, [X8]

0x484274 STR	XZR, [X11, X12,LSL #3]

0x484278 LDR	X12, [X10]

0x48427c CMP	X12, #1

0x484280 B.LT	4844f8

0x484284 LDR	X13, [X22]

0x484288 LDR	X14, [X21]

0x48428c ORR	X12, XZR, XZR

0x484290 HINT	#0

0x484294 HINT	#0

0x484298 HINT	#0

0x48429c HINT	#0

(2750) 0x4842a0 LDR	X16, [X8]

(2750) 0x4842a4 LDR	X15, [X13, X12,LSL #3]

(2750) 0x4842a8 LDR	X17, [X9, X16,LSL #3]

(2750) 0x4842ac ADD	X15, X17, X15

(2750) 0x4842b0 STR	X15, [X9, X16,LSL #3]

(2750) 0x4842b4 LDR	X16, [X8]

(2750) 0x4842b8 LDR	X15, [X14, X12,LSL #3]

(2750) 0x4842bc ADD	X12, X12, #1

(2750) 0x4842c0 LDR	X17, [X11, X16,LSL #3]

(2750) 0x4842c4 ADD	X15, X17, X15

(2750) 0x4842c8 STR	X15, [X11, X16,LSL #3]

(2750) 0x4842cc LDR	X15, [X10]

(2750) 0x4842d0 CMP	X12, X15

(2750) 0x4842d4 B.LT	4842a0

0x4842d8 B	4844f8

0x4842dc LDR	X1, [SP, #16]

0x4842e0 B	484398

0x4842e4 PTRUE	P0.D, VL1

0x4842e8 MOVI	V2.2D, #0

0x4842ec MOVI	V1.2D, #0

0x4842f0 SUB	X13, XZR, X10

0x4842f4 MOVI	V0.2D, #0

0x4842f8 MOVI	V3.2D, #0

0x4842fc AND	X15, X14, X13

0x484300 RDVL	X17, #2

0x484304 ORR	X13, X15, #0x1

0x484308 CPY	Z2.D, P0/M, X9

0x48430c ADD	X9, X12, #8

0x484310 ORR	X16, XZR, X15

0x484314 CPY	Z1.D, P0/M, X8

0x484318 ADD	X8, X11, #8

0x48431c HINT	#0

(2753) 0x484320 LDR	Z4, [X8, MUL VL]

(2753) 0x484324 LDR	Z5, [X8, #1, MUL VL]

(2753) 0x484328 ADD	X8, X8, X17

(2753) 0x48432c SUBS	X16, X16, X10

(2753) 0x484330 ADD	Z1.D, Z4.D, Z1.D

(2753) 0x484334 ADD	Z0.D, Z5.D, Z0.D

(2753) 0x484338 LDR	Z4, [X9, MUL VL]

(2753) 0x48433c LDR	Z5, [X9, #1, MUL VL]

(2753) 0x484340 ADD	X9, X9, X17

(2753) 0x484344 ADD	Z2.D, Z4.D, Z2.D

(2753) 0x484348 ADD	Z3.D, Z5.D, Z3.D

(2753) 0x48434c B.NE	484320

0x484350 ADD	Z2.D, Z3.D, Z2.D

0x484354 PTRUE	P0.D, ALL

0x484358 ADD	Z0.D, Z0.D, Z1.D

0x48435c CMP	X14, X15

0x484360 UADDV	D2, P0, Z2.D

0x484364 UADDV	D0, P0, Z0.D

0x484368 FMOV	X9, D2

0x48436c FMOV	X8, D0

0x484370 B.EQ	484398

0x484374 ADD	X11, X11, X13,LSL #3

0x484378 ADD	X12, X12, X13,LSL #3

0x48437c SUB	X13, X20, X13

(2754) 0x484380 LDR	X14, [X11], #8

(2754) 0x484384 SUBS	X13, X13, #1

(2754) 0x484388 ADD	X8, X14, X8

(2754) 0x48438c LDR	X14, [X12], #8

(2754) 0x484390 ADD	X9, X14, X9

(2754) 0x484394 B.NE	484380

0x484398 CMP	X1, X19

0x48439c B.GE	4844f8

0x4843a0 LDR	X11, [SP, #64]

0x4843a4 LDP	X14, X13, [SP]

0x4843a8 CMP	X20, X13

0x4843ac CSEL	X13, X20, X13, #11

0x4843b0 LDR	X11, [X11]

0x4843b4 LDR	X12, [X18]

0x4843b8 LDR	X12, [X12]

0x4843bc MADD	X13, X20, X14, X13

0x4843c0 SUB	X14, X19, X13

0x4843c4 MOVZ	W13, #8

0x4843c8 CMP	X10, #8

0x4843cc CSEL	X13, X10, X13, #8

0x4843d0 LDR	X11, [X11]

0x4843d4 CMP	X14, X13

0x4843d8 B.CC	48446c

0x4843dc ADD	X15, X11, X1,LSL #3

0x4843e0 ADD	X17, X12, X19,LSL #3

0x4843e4 ADD	X13, X11, X19,LSL #3

0x4843e8 ADD	X16, X12, X1,LSL #3

0x4843ec CMP	X15, X17

0x4843f0 CCMP	X16, X13, #2, #3

0x4843f4 B.CC	48446c

0x4843f8 SUB	X13, XZR, X10

0x4843fc RDVL	X0, #1

0x484400 ORR	X17, XZR, XZR

0x484404 AND	X18, X14, X13

0x484408 DUP	Z0.D, X8

0x48440c ADD	X13, X1, X18

0x484410 DUP	Z1.D, X9

0x484414 ADD	X1, X0, X1,LSL #3

0x484418 ADD	X0, X12, X1

0x48441c PTRUE	P0.D, ALL

0x484420 ADD	X1, X11, X1

(2752) 0x484424 LD1D	{Z2.D}, P0/Z, [X15, X17,LSL #3]

(2752) 0x484428 LD1D	{Z3.D}, P0/Z, [X1, X17,LSL #3]

(2752) 0x48442c ADD	Z2.D, Z2.D, Z0.D

(2752) 0x484430 ADD	Z3.D, Z3.D, Z0.D

(2752) 0x484434 ST1D	{Z2.D}, P0, [X15, X17,LSL #3]

(2752) 0x484438 ST1D	{Z3.D}, P0, [X1, X17,LSL #3]

(2752) 0x48443c LD1D	{Z2.D}, P0/Z, [X16, X17,LSL #3]

(2752) 0x484440 LD1D	{Z3.D}, P0/Z, [X0, X17,LSL #3]

(2752) 0x484444 ADD	Z2.D, Z2.D, Z1.D

(2752) 0x484448 ADD	Z3.D, Z3.D, Z1.D

(2752) 0x48444c ST1D	{Z2.D}, P0, [X16, X17,LSL #3]

(2752) 0x484450 ST1D	{Z3.D}, P0, [X0, X17,LSL #3]

(2752) 0x484454 ADD	X17, X17, X10

(2752) 0x484458 CMP	X18, X17

(2752) 0x48445c B.NE	484424

0x484460 CMP	X14, X18

0x484464 B.NE	484470

0x484468 B	4844f8

0x48446c ORR	X13, XZR, X1

0x484470 SUB	W14, W19, W13

0x484474 ADD	X10, X13, #1

0x484478 TBZ	W14, #0, 484498

0x48447c LDR	X14, [X11, X13,LSL #3]

0x484480 ADD	X14, X14, X8

0x484484 STR	X14, [X11, X13,LSL #3]

0x484488 LDR	X14, [X12, X13,LSL #3]

0x48448c ADD	X14, X14, X9

0x484490 STR	X14, [X12, X13,LSL #3]

0x484494 ORR	X13, XZR, X10

0x484498 CMP	X19, X10

0x48449c B.EQ	4844f8

0x4844a0 SUB	X10, X19, X13

0x4844a4 UBFM	X13, X13, #61, #60

0x4844a8 ADD	X13, X13, #8

0x4844ac ADD	X11, X11, X13

0x4844b0 ADD	X12, X12, X13

0x4844b4 HINT	#0

0x4844b8 HINT	#0

0x4844bc HINT	#0

(2751) 0x4844c0 LDUR	X13, [X11, #504]

(2751) 0x4844c4 SUBS	X10, X10, #2

(2751) 0x4844c8 ADD	X13, X13, X8

(2751) 0x4844cc STUR	X13, [X11, #504]

(2751) 0x4844d0 LDUR	X13, [X12, #504]

(2751) 0x4844d4 ADD	X13, X13, X9

(2751) 0x4844d8 STUR	X13, [X12, #504]

(2751) 0x4844dc LDR	X13, [X11]

(2751) 0x4844e0 ADD	X13, X13, X8

(2751) 0x4844e4 STR	X13, [X11], #16

(2751) 0x4844e8 LDR	X13, [X12]

(2751) 0x4844ec ADD	X13, X13, X9

(2751) 0x4844f0 STR	X13, [X12], #16

(2751) 0x4844f4 B.NE	4844c0

0x4844f8 LDP	X20, X19, [SP, #224]

0x4844fc LDP	X22, X21, [SP, #208]

0x484500 LDP	X24, X23, [SP, #192]

0x484504 LDP	X26, X25, [SP, #176]

0x484508 LDP	X28, X27, [SP, #160]

0x48450c LDP	X29, X30, [SP, #144]

0x484510 ADD	SP, SP, #240

0x484514 RET

0x484518 HINT	#0

0x48451c HINT	#0

Coverage (%)	Name	Source Location	Module
►98.66+	__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
►1.34+	__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 orig_0

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 7.00 cycles (4.52x 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 33% 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 23.21 cycles (1.36x speedup).

Details

4% 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.
33% 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	251
nb uops	222
loop length	1004
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	4
nb stack references	31

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	27.75 cycles
front end	27.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	12.50	12.50	24.50	24.50	24.50	24.50	3.00	3.00	2.00	2.00	31.67	31.67	31.67	13.00	13.00
cycles	12.50	12.50	24.50	24.50	24.50	24.50	3.00	3.00	2.00	2.00	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	27.75
Dispatch	31.67
Overall L1	31.67

Vectorization ratios

INT

all	4%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	33%
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	4%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	33%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

INT

all	33%
load	26%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
other	31%

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	33%
load	26%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	30%

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: 483e40

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 4acc50 <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, 483ee8 <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 483f3c <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 4aaf00 <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 483f3c <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 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%)
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%)
B.GE 4841d8 <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	N/A
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 483fe0 <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 4ab000 <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, <4ee200>	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, #2760	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 4104c0 <@plt_start@+0x4a0>	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, 48424c <hypre_ParMatmul_RowSizes.omp_outlined+0x40c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [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 X12, [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 X18, [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
CNTW X10, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	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, [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, [X12]	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 4842dc <hypre_ParMatmul_RowSizes.omp_outlined+0x49c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X1, [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%)
SUB X14, 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
CMP X14, X10	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 4842e4 <hypre_ParMatmul_RowSizes.omp_outlined+0x4a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVZ W13, #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 484374 <hypre_ParMatmul_RowSizes.omp_outlined+0x534>	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 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	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
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
B 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X1, [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 484398 <hypre_ParMatmul_RowSizes.omp_outlined+0x558>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PTRUE P0.D, VL1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
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, XZR, X10	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 X15, X14, X13	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%)
RDVL X17, #2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ORR X13, X15, #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
CPY Z2.D, P0/M, X9	1	0	0	0	0	1	0	0.50	0.50	0	0	0	0	0	0	0	5	1	scal (25.0%)
ADD X9, 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
ORR X16, XZR, X15	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
CPY Z1.D, P0/M, X8	1	0	0	0	0	1	0	0.50	0.50	0	0	0	0	0	0	0	5	1	scal (25.0%)
ADD X8, X11, #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
HINT #0																			N/A
ADD Z2.D, Z3.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ADD Z0.D, Z0.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
CMP X14, X15	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%)
UADDV D2, P0, Z2.D																			vect (100.0%)
UADDV D0, P0, Z0.D																			vect (100.0%)
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 484398 <hypre_ParMatmul_RowSizes.omp_outlined+0x558>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X11, X11, X13,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 X12, X12, X13,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 X13, X20, 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 X1, 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 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [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 X14, X13, [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, 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 X13, X20, X13, #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 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 X12, [X18]	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, [X12]	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 X13, X20, X14, X13	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
SUB X14, X19, 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
MOVZ W13, #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
CMP X10, #8	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 X13, X10, X13, #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
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
CMP X14, 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.CC 48446c <hypre_ParMatmul_RowSizes.omp_outlined+0x62c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X15, X11, X1,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%)
ADD X17, X12, 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	scal (25.0%)
ADD X13, 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 X16, X12, X1,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
CMP X15, X17	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 X16, X13, #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 48446c <hypre_ParMatmul_RowSizes.omp_outlined+0x62c>	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, XZR, X10	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
RDVL X0, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ORR X17, 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%)
AND X18, X14, 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
DUP Z0.D, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (25.0%)
ADD X13, X1, X18	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 Z1.D, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (25.0%)
ADD X1, X0, X1,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%)
ADD X0, X12, X1	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%)
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ADD X1, X11, X1	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 X14, X18	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 484470 <hypre_ParMatmul_RowSizes.omp_outlined+0x630>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X13, XZR, X1	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, W13	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, X13, #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, 484498 <hypre_ParMatmul_RowSizes.omp_outlined+0x658>	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, [X11, X13,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, [X11, X13,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, [X12, X13,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, [X12, X13,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 X13, XZR, X10	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, X10	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 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB X10, X19, 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
UBFM X13, X13, #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 X13, X13, #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 X11, X11, 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
ADD X12, X12, 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
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			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
HINT #0																			N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

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 7.00 cycles (4.52x speedup).

Workaround

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

Vectorization

Details

4% 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.
33% 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	251
nb uops	222
loop length	1004
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	4
nb stack references	31

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	27.75 cycles
front end	27.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	12.50	12.50	24.50	24.50	24.50	24.50	3.00	3.00	2.00	2.00	31.67	31.67	31.67	13.00	13.00
cycles	12.50	12.50	24.50	24.50	24.50	24.50	3.00	3.00	2.00	2.00	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	27.75
Dispatch	31.67
Overall L1	31.67

Vectorization ratios

INT

all	4%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	33%
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	4%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	33%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

INT

all	33%
load	26%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
other	31%

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	33%
load	26%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	30%

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: 483e40

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 4acc50 <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, 483ee8 <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 483f3c <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 4aaf00 <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 483f3c <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 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%)
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%)
B.GE 4841d8 <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	N/A
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 483fe0 <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 4ab000 <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, <4ee200>	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, #2760	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 4104c0 <@plt_start@+0x4a0>	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, 48424c <hypre_ParMatmul_RowSizes.omp_outlined+0x40c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [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 X12, [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 X18, [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
CNTW X10, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	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, [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, [X12]	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 4842dc <hypre_ParMatmul_RowSizes.omp_outlined+0x49c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X1, [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%)
SUB X14, 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
CMP X14, X10	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 4842e4 <hypre_ParMatmul_RowSizes.omp_outlined+0x4a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVZ W13, #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 484374 <hypre_ParMatmul_RowSizes.omp_outlined+0x534>	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 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	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
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
B 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X1, [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 484398 <hypre_ParMatmul_RowSizes.omp_outlined+0x558>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PTRUE P0.D, VL1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
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, XZR, X10	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 X15, X14, X13	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%)
RDVL X17, #2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ORR X13, X15, #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
CPY Z2.D, P0/M, X9	1	0	0	0	0	1	0	0.50	0.50	0	0	0	0	0	0	0	5	1	scal (25.0%)
ADD X9, 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
ORR X16, XZR, X15	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
CPY Z1.D, P0/M, X8	1	0	0	0	0	1	0	0.50	0.50	0	0	0	0	0	0	0	5	1	scal (25.0%)
ADD X8, X11, #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
HINT #0																			N/A
ADD Z2.D, Z3.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ADD Z0.D, Z0.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
CMP X14, X15	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%)
UADDV D2, P0, Z2.D																			vect (100.0%)
UADDV D0, P0, Z0.D																			vect (100.0%)
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 484398 <hypre_ParMatmul_RowSizes.omp_outlined+0x558>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X11, X11, X13,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 X12, X12, X13,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 X13, X20, 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 X1, 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 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [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 X14, X13, [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, 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 X13, X20, X13, #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 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 X12, [X18]	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, [X12]	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 X13, X20, X14, X13	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
SUB X14, X19, 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
MOVZ W13, #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
CMP X10, #8	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 X13, X10, X13, #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
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
CMP X14, 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.CC 48446c <hypre_ParMatmul_RowSizes.omp_outlined+0x62c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X15, X11, X1,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%)
ADD X17, X12, 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	scal (25.0%)
ADD X13, 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 X16, X12, X1,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
CMP X15, X17	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 X16, X13, #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 48446c <hypre_ParMatmul_RowSizes.omp_outlined+0x62c>	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, XZR, X10	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
RDVL X0, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ORR X17, 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%)
AND X18, X14, 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
DUP Z0.D, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (25.0%)
ADD X13, X1, X18	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 Z1.D, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (25.0%)
ADD X1, X0, X1,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%)
ADD X0, X12, X1	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%)
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ADD X1, X11, X1	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 X14, X18	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 484470 <hypre_ParMatmul_RowSizes.omp_outlined+0x630>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X13, XZR, X1	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, W13	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, X13, #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, 484498 <hypre_ParMatmul_RowSizes.omp_outlined+0x658>	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, [X11, X13,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, [X11, X13,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, [X12, X13,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, [X12, X13,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 X13, XZR, X10	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, X10	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 4844f8 <hypre_ParMatmul_RowSizes.omp_outlined+0x6b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB X10, X19, 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
UBFM X13, X13, #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 X13, X13, #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 X11, X11, 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
ADD X12, X12, 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
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			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
HINT #0																			N/A

Name	Coverage (%)	Time (s)
▼hypre_ParMatmul_RowSizes.omp_outlined–	0.68	0.32
○Loop 2752 - par_csr_matop.c:263-266 - exec	0.03	0.01
○Loop 2763 - par_csr_matop.c:124-125 - exec	0.00	0.00
▼Loop 2762 - par_csr_matop.c:127-242 - exec–	0.00	0.00
▼Loop 2757 - par_csr_matop.c:127-242 - exec–	0.00	0.00
▼Loop 2756 - par_csr_matop.c:127-242 - exec–	0.19	0.07
○Loop 2758 - par_csr_matop.c:195-208 - exec	0.43	0.15
▼Loop 2755 - par_csr_matop.c:127-242 - exec–	0.02	0.01
▼Loop 2759 - par_csr_matop.c:146-177 - exec–	0.00	0.00
○Loop 2760 - par_csr_matop.c:170-177 - exec	0.00	0.00
○Loop 2761 - par_csr_matop.c:154-167 - exec	0.00	0.00
○Loop 2754 - par_csr_matop.c:257-260 - exec	0.00	0.00
○Loop 2751 - par_csr_matop.c:263-266 - exec	0.00	0.00
○Loop 2750 - par_csr_matop.c:273-276 - exec	0.00	0.00
○Loop 2753 - 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