OV - exec - Loop 389

	Loop Id: 389	Module: exec	Source: TwoBodyJastrowRef.h:107-132 [...]	Coverage: 0.02%

0x422f40 LDR	X3, [X23, #24]

0x422f44 LDR	W24, [X19, #672]

0x422f48 LDRB	W2, [X22, #8]

0x422f4c LDR	D15, [X3, X24,SXTW #3]

0x422f50 SBFM	X28, X24, #0, #31

0x422f54 TBZ	W2, #0, 423488

0x422f58 ORR	X0, XZR, X19

0x422f5c LDR	X27, [X19, #656]

0x422f60 LDR	W1, [X26, #584]

0x422f64 BL	49180c

0x422f68 LDR	X5, [X0, #72]

0x422f6c ADD	X4, X25, X25,LSL #2

0x422f70 LDR	X7, [X27, #24]

0x422f74 LDR	X13, [X26, #160]

0x422f78 ADD	X6, X5, X4

0x422f7c LDR	X14, [X6, #24]

0x422f80 LDR	W8, [X7, X28,LSL #2]

0x422f84 MADD	W9, W8, W13, WZR

0x422f88 CBZ	X13, 423438

0x422f8c LDR	X11, [X27, #616]

0x422f90 MOVI	D2, #0

0x422f94 MOVZ	X8, #0

0x422f98 CNTW	X7, ALL

0x422f9c PTRUE	P7.B, ALL

0x422fa0 LDR	X4, [X26, #464]

0x422fa4 LDR	X10, [X26, #512]

0x422fa8 ADD	X12, X10, W9,SXTW #3

0x422fac LDR	X11, [X11, #24]

0x422fb0 ADDVL	X6, X4, #1

0x422fb4 HINT	#0

0x422fb8 HINT	#0

0x422fbc HINT	#0

  (390) 0x422fc0 LDR	X16, [X12, X8,LSL #3]

  (390) 0x422fc4 LDR	W17, [X11, X8,LSL #2]

  (390) 0x422fc8 ADD	X8, X8, #1

  (390) 0x422fcc LDR	W18, [X11, X8,LSL #2]

  (390) 0x422fd0 CMP	W18, W17

  (390) 0x422fd4 B.LE	42342c

  (390) 0x422fd8 SUB	W30, W18, W17

  (390) 0x422fdc SBFM	X15, X17, #61, #31

  (390) 0x422fe0 LDR	D31, [X16, #8]

  (390) 0x422fe4 ANDS	W28, W30, #128

  (390) 0x422fe8 MOVZ	W2, #0

  (390) 0x422fec ADD	X0, X14, X15

  (390) 0x422ff0 ORR	W30, WZR, W17

  (390) 0x422ff4 B.EQ	42312c

  (390) 0x422ff8 CMP	W28, #1

  (390) 0x422ffc B.EQ	423100

  (390) 0x423000 CMP	W28, #2

  (390) 0x423004 B.EQ	4230dc

  (390) 0x423008 CMP	W28, #3

  (390) 0x42300c B.EQ	4230b8

  (390) 0x423010 CMP	W28, #4

  (390) 0x423014 B.EQ	423094

  (390) 0x423018 CMP	W28, #5

  (390) 0x42301c B.EQ	423070

  (390) 0x423020 CMP	W28, #6

  (390) 0x423024 B.EQ	42304c

  (390) 0x423028 LDR	D30, [X14, X15]

  (390) 0x42302c FCMPE	D31, D30

  (390) 0x423030 B.LS	423044

  (390) 0x423034 CMP	W24, W17

  (390) 0x423038 B.EQ	423044

  (390) 0x42303c MOVZ	W2, #1

  (390) 0x423040 STR	D30, [X4]

  (390) 0x423044 ADD	X0, X0, #8

  (390) 0x423048 ADD	W30, W17, #1

  (390) 0x42304c LDR	D0, [X0]

  (390) 0x423050 FCMPE	D31, D0

  (390) 0x423054 B.LS	423068

  (390) 0x423058 CMP	W24, W30

  (390) 0x42305c B.EQ	423068

  (390) 0x423060 STR	D0, [X4, X2,UXTW #3]

  (390) 0x423064 ADD	W2, W2, #1

  (390) 0x423068 ADD	X0, X0, #8

  (390) 0x42306c ADD	W30, W30, #1

  (390) 0x423070 LDR	D1, [X0]

  (390) 0x423074 FCMPE	D31, D1

  (390) 0x423078 B.LS	42308c

  (390) 0x42307c CMP	W24, W30

  (390) 0x423080 B.EQ	42308c

  (390) 0x423084 STR	D1, [X4, X2,UXTW #3]

  (390) 0x423088 ADD	W2, W2, #1

  (390) 0x42308c ADD	X0, X0, #8

  (390) 0x423090 ADD	W30, W30, #1

  (390) 0x423094 LDR	D3, [X0]

  (390) 0x423098 FCMPE	D31, D3

  (390) 0x42309c B.LS	4230b0

  (390) 0x4230a0 CMP	W24, W30

  (390) 0x4230a4 B.EQ	4230b0

  (390) 0x4230a8 STR	D3, [X4, X2,UXTW #3]

  (390) 0x4230ac ADD	W2, W2, #1

  (390) 0x4230b0 ADD	X0, X0, #8

  (390) 0x4230b4 ADD	W30, W30, #1

  (390) 0x4230b8 LDR	D4, [X0]

  (390) 0x4230bc FCMPE	D31, D4

  (390) 0x4230c0 B.LS	4230d4

  (390) 0x4230c4 CMP	W24, W30

  (390) 0x4230c8 B.EQ	4230d4

  (390) 0x4230cc STR	D4, [X4, X2,UXTW #3]

  (390) 0x4230d0 ADD	W2, W2, #1

  (390) 0x4230d4 ADD	X0, X0, #8

  (390) 0x4230d8 ADD	W30, W30, #1

  (390) 0x4230dc LDR	D5, [X0]

  (390) 0x4230e0 FCMPE	D31, D5

  (390) 0x4230e4 B.LS	4230f8

  (390) 0x4230e8 CMP	W24, W30

  (390) 0x4230ec B.EQ	4230f8

  (390) 0x4230f0 STR	D5, [X4, X2,UXTW #3]

  (390) 0x4230f4 ADD	W2, W2, #1

  (390) 0x4230f8 ADD	X0, X0, #8

  (390) 0x4230fc ADD	W30, W30, #1

  (390) 0x423100 LDR	D6, [X0]

  (390) 0x423104 FCMPE	D31, D6

  (390) 0x423108 B.LS	42311c

  (390) 0x42310c CMP	W24, W30

  (390) 0x423110 B.EQ	42311c

  (390) 0x423114 STR	D6, [X4, X2,UXTW #3]

  (390) 0x423118 ADD	W2, W2, #1

  (390) 0x42311c ADD	W30, W30, #1

  (390) 0x423120 ADD	X0, X0, #8

  (390) 0x423124 CMP	W18, W30

  (390) 0x423128 B.EQ	42323c

    (391) 0x42312c LDR	D7, [X0]

    (391) 0x423130 FCMPE	D31, D7

    (391) 0x423134 B.LS	423148

    (391) 0x423138 CMP	W24, W30

    (391) 0x42313c B.EQ	423148

    (391) 0x423140 STR	D7, [X4, X2,UXTW #3]

    (391) 0x423144 ADD	W2, W2, #1

    (391) 0x423148 LDR	D8, [X0, #8]

    (391) 0x42314c ADD	W1, W30, #1

    (391) 0x423150 ADD	X0, X0, #8

    (391) 0x423154 FCMPE	D31, D8

    (391) 0x423158 B.LS	42316c

    (391) 0x42315c CMP	W24, W1

    (391) 0x423160 B.EQ	42316c

    (391) 0x423164 STR	D8, [X4, X2,UXTW #3]

    (391) 0x423168 ADD	W2, W2, #1

    (391) 0x42316c LDR	D9, [X0, #8]

    (391) 0x423170 ADD	W3, W1, #1

    (391) 0x423174 FCMPE	D31, D9

    (391) 0x423178 B.LS	42318c

    (391) 0x42317c CMP	W24, W3

    (391) 0x423180 B.EQ	42318c

    (391) 0x423184 STR	D9, [X4, X2,UXTW #3]

    (391) 0x423188 ADD	W2, W2, #1

    (391) 0x42318c LDR	D10, [X0, #16]

    (391) 0x423190 ADD	W27, W1, #2

    (391) 0x423194 FCMPE	D31, D10

    (391) 0x423198 B.LS	4231ac

    (391) 0x42319c CMP	W24, W27

    (391) 0x4231a0 B.EQ	4231ac

    (391) 0x4231a4 STR	D10, [X4, X2,UXTW #3]

    (391) 0x4231a8 ADD	W2, W2, #1

    (391) 0x4231ac LDR	D11, [X0, #24]

    (391) 0x4231b0 ADD	W5, W1, #3

    (391) 0x4231b4 FCMPE	D31, D11

    (391) 0x4231b8 B.LS	4231cc

    (391) 0x4231bc CMP	W24, W5

    (391) 0x4231c0 B.EQ	4231cc

    (391) 0x4231c4 STR	D11, [X4, X2,UXTW #3]

    (391) 0x4231c8 ADD	W2, W2, #1

    (391) 0x4231cc LDR	D12, [X0, #32]

    (391) 0x4231d0 ADD	W9, W1, #4

    (391) 0x4231d4 FCMPE	D31, D12

    (391) 0x4231d8 B.LS	4231ec

    (391) 0x4231dc CMP	W24, W9

    (391) 0x4231e0 B.EQ	4231ec

    (391) 0x4231e4 STR	D12, [X4, X2,UXTW #3]

    (391) 0x4231e8 ADD	W2, W2, #1

    (391) 0x4231ec LDR	D13, [X0, #40]

    (391) 0x4231f0 ADD	W10, W1, #5

    (391) 0x4231f4 FCMPE	D31, D13

    (391) 0x4231f8 B.LS	42320c

    (391) 0x4231fc CMP	W24, W10

    (391) 0x423200 B.EQ	42320c

    (391) 0x423204 STR	D13, [X4, X2,UXTW #3]

    (391) 0x423208 ADD	W2, W2, #1

    (391) 0x42320c LDR	D14, [X0, #48]

    (391) 0x423210 ADD	W17, W1, #6

    (391) 0x423214 FCMPE	D31, D14

    (391) 0x423218 B.LS	42322c

    (391) 0x42321c CMP	W24, W17

    (391) 0x423220 B.EQ	42322c

    (391) 0x423224 STR	D14, [X4, X2,UXTW #3]

    (391) 0x423228 ADD	W2, W2, #1

    (391) 0x42322c ADD	W30, W1, #7

    (391) 0x423230 ADD	X0, X0, #56

    (391) 0x423234 CMP	W18, W30

    (391) 0x423238 B.NE	42312c

  (390) 0x42323c CBZ	W2, 42342c

  (390) 0x423240 ADD	X18, X16, #568

  (390) 0x423244 LD1RD	{Z4.D}, P7/Z, [X16, #3]

  (390) 0x423248 LD1RD	{Z5.D}, P7/Z, [X16, #4]

  (390) 0x42324c LD1RD	{Z6.D}, P7/Z, [X16, #5]

  (390) 0x423250 LD1RD	{Z7.D}, P7/Z, [X16, #6]

  (390) 0x423254 LD1RD	{Z16.D}, P7/Z, [X16, #7]

  (390) 0x423258 LD1RD	{Z17.D}, P7/Z, [X16, #8]

  (390) 0x42325c LD1RD	{Z18.D}, P7/Z, [X16, #9]

  (390) 0x423260 LD1RD	{Z19.D}, P7/Z, [X16, #10]

  (390) 0x423264 LD1RD	{Z20.D}, P7/Z, [X16, #11]

  (390) 0x423268 LD1RD	{Z21.D}, P7/Z, [X16, #12]

  (390) 0x42326c LD1RD	{Z22.D}, P7/Z, [X16, #13]

  (390) 0x423270 LD1RD	{Z23.D}, P7/Z, [X16, #14]

  (390) 0x423274 LD1RD	{Z24.D}, P7/Z, [X16, #15]

  (390) 0x423278 LD1RD	{Z25.D}, P7/Z, [X16, #16]

  (390) 0x42327c LD1RD	{Z26.D}, P7/Z, [X16, #17]

  (390) 0x423280 LD1RD	{Z27.D}, P7/Z, [X16, #18]

  (390) 0x423284 LDR	X16, [X16, #536]

  (390) 0x423288 MOVZ	X28, #0

  (390) 0x42328c ORR	W15, WZR, W2

  (390) 0x423290 DUP	Z1.D, #0

  (390) 0x423294 UQDECD	W15, ALL

  (390) 0x423298 LD1RD	{Z3.D}, P7/Z, [X18]

  (390) 0x42329c WHILELO	P5.D, WZR, W15

  (390) 0x4232a0 ORR	Z28.D, Z1.D, Z1.D

  (390) 0x4232a4 WHILELO	P6.D, WZR, W2

    (392) 0x4232a8 LD1D	{Z29.D}, P5/Z, [X6, X28,LSL #3]

    (392) 0x4232ac LD1D	{Z30.D}, P6/Z, [X4, X28,LSL #3]

    (392) 0x4232b0 FMUL	Z31.D, Z3.D, Z29.D

    (392) 0x4232b4 FMUL	Z13.D, Z3.D, Z30.D

    (392) 0x4232b8 MOVPRFX	Z8, Z31

    (392) 0x4232bc FCVTZS	Z8.S, P7/M, Z31.D

    (392) 0x4232c0 MOVPRFX	Z9, Z13

    (392) 0x4232c4 FCVTZS	Z9.S, P7/M, Z13.D

    (392) 0x4232c8 MOVPRFX	Z0, Z31

    (392) 0x4232cc FRINTZ	Z0.D, P7/M, Z31.D

    (392) 0x4232d0 UZP1	Z30.S, Z9.S, Z8.S

    (392) 0x4232d4 FSUB	Z31.D, Z31.D, Z0.D

    (392) 0x4232d8 MOVPRFX	Z12, Z30

    (392) 0x4232dc ADD	Z12.S, Z12.S, #1

    (392) 0x4232e0 FMUL	Z29.D, Z31.D, Z31.D

    (392) 0x4232e4 SUNPKHI	Z8.D, Z12

    (392) 0x4232e8 FMUL	Z14.D, Z29.D, Z31.D

    (392) 0x4232ec LD1D	{Z9.D}, P5/Z, [X16, Z8.D,LSL #3]

    (392) 0x4232f0 FMUL	Z10.D, Z17.D, Z29.D

    (392) 0x4232f4 FMLA	Z10.D, P7/M, Z16.D, Z14.D

    (392) 0x4232f8 MOVPRFX	Z11, Z19

    (392) 0x4232fc FMLA	Z11.D, P7/M, Z18.D, Z31.D

    (392) 0x423300 FADD	Z0.D, Z10.D, Z11.D

    (392) 0x423304 FMUL	Z0.D, Z0.D, Z9.D

    (392) 0x423308 SUNPKHI	Z9.D, Z30

    (392) 0x42330c FMUL	Z10.D, Z5.D, Z29.D

    (392) 0x423310 LD1D	{Z8.D}, P5/Z, [X16, Z9.D,LSL #3]

    (392) 0x423314 FMLA	Z10.D, P7/M, Z4.D, Z14.D

    (392) 0x423318 MOVPRFX	Z11, Z7

    (392) 0x42331c FMLA	Z11.D, P7/M, Z6.D, Z31.D

    (392) 0x423320 FADD	Z11.D, Z11.D, Z10.D

    (392) 0x423324 FMUL	Z10.D, Z21.D, Z29.D

    (392) 0x423328 FMAD	Z11.D, P7/M, Z8.D, Z0.D

    (392) 0x42332c FMLA	Z10.D, P7/M, Z14.D, Z20.D

    (392) 0x423330 MOVPRFX	Z0, Z23

    (392) 0x423334 FMLA	Z0.D, P7/M, Z31.D, Z22.D

    (392) 0x423338 FMUL	Z29.D, Z29.D, Z25.D

    (392) 0x42333c FADD	Z8.D, Z10.D, Z0.D

    (392) 0x423340 FMAD	Z14.D, P7/M, Z24.D, Z29.D

    (392) 0x423344 MOVPRFX	Z10, Z30

    (392) 0x423348 ADD	Z10.S, Z10.S, #2

    (392) 0x42334c FADD	Z1.D, P5/M, Z1.D, Z11.D

    (392) 0x423350 FMAD	Z31.D, P7/M, Z26.D, Z27.D

    (392) 0x423354 MOVPRFX	Z11, Z30

    (392) 0x423358 ADD	Z11.S, Z11.S, #3

    (392) 0x42335c FADD	Z31.D, Z31.D, Z14.D

    (392) 0x423360 SUNPKHI	Z0.D, Z11

    (392) 0x423364 SUNPKHI	Z14.D, Z10

    (392) 0x423368 LD1D	{Z29.D}, P5/Z, [X16, Z0.D,LSL #3]

    (392) 0x42336c LD1D	{Z9.D}, P5/Z, [X16, Z14.D,LSL #3]

    (392) 0x423370 SUNPKLO	Z30.D, Z30

    (392) 0x423374 FMLA	Z1.D, P5/M, Z9.D, Z8.D

    (392) 0x423378 SUNPKLO	Z8.D, Z10

    (392) 0x42337c FMLA	Z1.D, P5/M, Z29.D, Z31.D

    (392) 0x423380 LD1D	{Z14.D}, P6/Z, [X16, Z8.D,LSL #3]

    (392) 0x423384 SUNPKLO	Z31.D, Z11

    (392) 0x423388 MOVPRFX	Z9, Z13

    (392) 0x42338c FRINTZ	Z9.D, P7/M, Z13.D

    (392) 0x423390 LD1D	{Z11.D}, P6/Z, [X16, Z30.D,LSL #3]

    (392) 0x423394 FSUB	Z8.D, Z13.D, Z9.D

    (392) 0x423398 SUNPKLO	Z12.D, Z12

    (392) 0x42339c FMUL	Z29.D, Z8.D, Z8.D

    (392) 0x4233a0 FMUL	Z30.D, Z29.D, Z8.D

    (392) 0x4233a4 FMUL	Z13.D, Z17.D, Z29.D

    (392) 0x4233a8 FMLA	Z13.D, P7/M, Z16.D, Z30.D

    (392) 0x4233ac LD1D	{Z10.D}, P6/Z, [X16, Z12.D,LSL #3]

    (392) 0x4233b0 ADD	X28, X28, X7

    (392) 0x4233b4 MOVPRFX	Z12, Z19

    (392) 0x4233b8 FMLA	Z12.D, P7/M, Z18.D, Z8.D

    (392) 0x4233bc WHILELO	P5.D, W28, W15

    (392) 0x4233c0 FADD	Z9.D, Z12.D, Z13.D

    (392) 0x4233c4 MOVPRFX	Z13, Z7

    (392) 0x4233c8 FMLA	Z13.D, P7/M, Z6.D, Z8.D

    (392) 0x4233cc LD1D	{Z0.D}, P6/Z, [X16, Z31.D,LSL #3]

    (392) 0x4233d0 FMUL	Z12.D, Z9.D, Z10.D

    (392) 0x4233d4 FMUL	Z31.D, Z5.D, Z29.D

    (392) 0x4233d8 FMUL	Z10.D, Z21.D, Z29.D

    (392) 0x4233dc FMLA	Z31.D, P7/M, Z4.D, Z30.D

    (392) 0x4233e0 MOVPRFX	Z9, Z23

    (392) 0x4233e4 FMLA	Z9.D, P7/M, Z8.D, Z22.D

    (392) 0x4233e8 FADD	Z31.D, Z13.D, Z31.D

    (392) 0x4233ec FMUL	Z29.D, Z29.D, Z25.D

    (392) 0x4233f0 FMAD	Z31.D, P7/M, Z11.D, Z12.D

    (392) 0x4233f4 FMAD	Z8.D, P7/M, Z26.D, Z27.D

    (392) 0x4233f8 MOVPRFX	Z11, Z10

    (392) 0x4233fc FMLA	Z11.D, P7/M, Z30.D, Z20.D

    (392) 0x423400 FADD	Z28.D, P6/M, Z28.D, Z31.D

    (392) 0x423404 FMAD	Z30.D, P7/M, Z24.D, Z29.D

    (392) 0x423408 FADD	Z13.D, Z9.D, Z11.D

    (392) 0x42340c FMLA	Z28.D, P6/M, Z14.D, Z13.D

    (392) 0x423410 FADD	Z14.D, Z30.D, Z8.D

    (392) 0x423414 FMLA	Z28.D, P6/M, Z0.D, Z14.D

    (392) 0x423418 WHILELO	P6.D, W28, W2

    (392) 0x42341c B.NE	4232a8

  (390) 0x423420 FADD	Z3.D, Z28.D, Z1.D

  (390) 0x423424 FADDV	D1, P7, Z3.D

  (390) 0x423428 FADD	D2, D2, D1

  (390) 0x42342c CMP	X13, X8

  (390) 0x423430 B.NE	422fc0

0x423434 FSUB	D15, D15, S2

0x423438 FMOV	D0, D15

0x42343c ADD	X20, X20, #1

0x423440 BL	403db0

0x423444 LDP	X1, X3, [X21]

0x423448 SUB	X27, X3, X1

0x42344c STR	D0, [X1, X25]

0x423450 ADD	X25, X25, #8

0x423454 CMP	X20, X27,ASR #3

0x423458 B.CC	422f40

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 993 - 1147

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

993:       { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); }

[...]

1147:       operator[](size_type __n) const _GLIBCXX_NOEXCEPT

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249

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

223:     return X[i];

[...]

249:   inline const_pointer data() const { return X; }

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 107 - 132

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

107:     for (int k = 0; k < ratios.size(); ++k)

108:       ratios[k] = std::exp(Uat[VP.refPtcl] - computeU(VP.getRefPS(), VP.refPtcl, VP.getDistTableAB(myTableID).getDistRow(k).data()));

[...]

125:     valT curUat(0);

126:     const int igt = P.GroupID[iat] * NumGroups;

127:     for (int jg = 0; jg < NumGroups; ++jg)

128:     {

129:       const FuncType& f2(*F[igt + jg]);

130:       int iStart = P.first(jg);

131:       int iEnd   = P.last(jg);

132:       curUat += f2.evaluateV(iat, iStart, iEnd, dist, DistCompressed.data());

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 313 - 316

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

313:   inline int first(int igroup) const { return (*group_offsets_)[igroup]; }

314:

315:   ///return the last index of a group i

316:   inline int last(int igroup) const { return (*group_offsets_)[igroup + 1]; }

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/optional: 991 - 991

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

991: 	if (this->_M_is_engaged())

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/refwrap.h: 351 - 351

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

351:       { return *_M_data; }

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 231 - 260

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

231:   ASSUME_ALIGNED(distArrayCompressed);

232:   int iCount       = 0;

233:   const int iLimit = iEnd - iStart;

234:

235: #pragma vector always

236:   for (int jat = 0; jat < iLimit; jat++)

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

240:     if (r < cutoff_radius && iStart + jat != iat)

241:       distArrayCompressed[iCount++] = distArray[jat];

242:   }

243:

244:   real_type d = 0.0;

245:   //#pragma omp simd reduction(+:d)

246:   for (int jat = 0; jat < iCount; jat++)

247:   {

248:     real_type r = distArrayCompressed[jat];

249:     r *= DeltaRInv;

250:     int i         = (int)r;

251:     real_type t   = r - real_type(i);

252:     real_type tp0 = t * t * t;

253:     real_type tp1 = t * t;

254:     real_type tp2 = t;

255:

256:     real_type d1 = SplineCoefs[i + 0] * (A[0] * tp0 + A[1] * tp1 + A[2] * tp2 + A[3]);

257:     real_type d2 = SplineCoefs[i + 1] * (A[4] * tp0 + A[5] * tp1 + A[6] * tp2 + A[7]);

258:     real_type d3 = SplineCoefs[i + 2] * (A[8] * tp0 + A[9] * tp1 + A[10] * tp2 + A[11]);

259:     real_type d4 = SplineCoefs[i + 3] * (A[12] * tp0 + A[13] * tp1 + A[14] * tp2 + A[15]);

260:     d += (d1 + d2 + d3 + d4);

Coverage (%)	Name	Source Location	Module
►98.88+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:992	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

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 /

Metric	Value
CQA speedup if no scalar integer	5.00
CQA speedup if FP arith vectorized	1.35
CQA speedup if fully vectorized	1.45
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.03
Bottlenecks	P12,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	stl_vector.h:993-993,OhmmsVector.h:223-223,OhmmsVector.h:249-249,TwoBodyJastrowRef.h:107-108,TwoBodyJastrowRef.h:125-127,optional:991-991,refwrap.h:351-351,BsplineFunctor.h:231-231,BsplineFunctor.h:246-246
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	5.83
CQA cycles if no scalar integer	1.17
CQA cycles if FP arith vectorized	4.33
CQA cycles if fully vectorized	4.01
Front-end cycles	4.88
P0 cycles	2.50
P1 cycles	2.50
P2 cycles	2.50
P3 cycles	2.50
P4 cycles	2.50
P5 cycles	2.50
P6 cycles	3.00
P7 cycles	3.00
P8 cycles	1.00
P9 cycles	1.00
P10 cycles	1.00
P11 cycles	1.00
P12 cycles	5.83
P13 cycles	5.50
P14 cycles	5.67
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	42.00
Nb uops	39.00
Nb loads	NA
Nb stores	1.00
Nb stack references	0.00
FLOP/cycle	0.17
Nb FLOP add-sub	1.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	21.43
Bytes prefetched	0.00
Bytes loaded	117.00
Bytes stored	8.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	0.00
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	47.43
Vector-efficiency ratio load	41.41
Vector-efficiency ratio store	50.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	50.00
Vector-efficiency ratio fma	25.00
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	62.50

Metric	Value
CQA speedup if no scalar integer	5.00
CQA speedup if FP arith vectorized	1.35
CQA speedup if fully vectorized	1.45
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.03
Bottlenecks	P12,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	stl_vector.h:993-993,OhmmsVector.h:223-223,OhmmsVector.h:249-249,TwoBodyJastrowRef.h:107-108,TwoBodyJastrowRef.h:125-127,optional:991-991,refwrap.h:351-351,BsplineFunctor.h:231-231,BsplineFunctor.h:246-246
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	5.83
CQA cycles if no scalar integer	1.17
CQA cycles if FP arith vectorized	4.33
CQA cycles if fully vectorized	4.01
Front-end cycles	4.88
P0 cycles	2.50
P1 cycles	2.50
P2 cycles	2.50
P3 cycles	2.50
P4 cycles	2.50
P5 cycles	2.50
P6 cycles	3.00
P7 cycles	3.00
P8 cycles	1.00
P9 cycles	1.00
P10 cycles	1.00
P11 cycles	1.00
P12 cycles	5.83
P13 cycles	5.50
P14 cycles	5.67
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	42.00
Nb uops	39.00
Nb loads	NA
Nb stores	1.00
Nb stack references	0.00
FLOP/cycle	0.17
Nb FLOP add-sub	1.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	21.43
Bytes prefetched	0.00
Bytes loaded	117.00
Bytes stored	8.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	0.00
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	47.43
Vector-efficiency ratio load	41.41
Vector-efficiency ratio store	50.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	50.00
Vector-efficiency ratio fma	25.00
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	62.50

Path /

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

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	TwoBodyJastrowRef.h:107-132
Module	exec

The loop is defined in:

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h:993,1147
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107-108,125-132
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/optional:991
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/refwrap.h:351
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:231-260

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths (too many, greater than internal limit = 100000)
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is very high. Force analysis with --force-loop-streams-analysis: expect potentially high RAM/CPU footprint

Try to simplify control.

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 5.83 to 1.17 cycles (5.00x speedup).

Workaround

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

Vectorization

Your loop is not vectorized. Only 47% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 5.83 to 4.01 cycles (1.45x speedup).

Details

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

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 5.83 to 1.00 cycles (5.83x speedup).

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

The binary loop is composed of 1 FP arithmetical operations:

1: addition or subtraction

The binary loop is loading 117 bytes. The binary loop is storing 8 bytes.

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	42
loop length	168
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

4.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	2.50	2.50	2.50	2.50	2.50	2.50	3.00	3.00	1.00	1.00	1.00	1.00	5.83	5.50	5.67	0.00	0.00
cycles	2.50	2.50	2.50	2.50	2.50	2.50	3.00	3.00	1.00	1.00	1.00	1.00	5.83	5.50	5.67	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	4.88
Overall L1	5.83

Vectorization ratios

INT

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

INT+FP

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 5.83 cycles. At this rate:

20% of peak load performance is reached (20.06 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (1.37 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 422f40

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
LDR X3, [X23, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR W24, [X19, #672]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDRB W2, [X22, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (6.3%)
LDR D15, [X3, X24,SXTW #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
SBFM X28, X24, #0, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TBZ W2, #0, 423488 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x5a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X0, XZR, X19	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDR X27, [X19, #656]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR W1, [X26, #584]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
BL 49180c <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X5, [X0, #72]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X4, X25, X25,LSL #2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
LDR X7, [X27, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X13, [X26, #160]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X6, X5, X4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDR X14, [X6, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR W8, [X7, X28,LSL #2]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
MADD W9, W8, W13, WZR	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
CBZ X13, 423438 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x558>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [X27, #616]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
MOVI D2, #0	1	0	0	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%)
MOVZ X8, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
CNTW X7, ALL	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
PTRUE P7.B, ALL	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (100.0%)
LDR X4, [X26, #464]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X10, [X26, #512]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X12, X10, W9,SXTW #3	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (50.0%)
LDR X11, [X11, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADDVL X6, X4, #1	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
FSUB D15, D15, S2	1	0	0	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 D0, D15	1	0	0	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%)
ADD X20, X20, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
BL 403db0 <@plt_start@+0xc0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X1, X3, [X21]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	N/A
SUB X27, X3, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STR D0, [X1, X25]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD X25, X25, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP X20, X27,ASR #3	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
B.CC 422f40 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x60>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	TwoBodyJastrowRef.h:107-132
Module	exec

The loop is defined in:

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h:993,1147
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107-108,125-132
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/optional:991
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/refwrap.h:351
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:231-260

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths (too many, greater than internal limit = 100000)
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is very high. Force analysis with --force-loop-streams-analysis: expect potentially high RAM/CPU footprint

Try to simplify control.

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 5.83 to 1.17 cycles (5.00x speedup).

Workaround

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

Vectorization

Details

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

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 5.83 to 1.00 cycles (5.83x speedup).

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

The binary loop is composed of 1 FP arithmetical operations:

1: addition or subtraction

The binary loop is loading 117 bytes. The binary loop is storing 8 bytes.

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	42
loop length	168
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

4.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	2.50	2.50	2.50	2.50	2.50	2.50	3.00	3.00	1.00	1.00	1.00	1.00	5.83	5.50	5.67	0.00	0.00
cycles	2.50	2.50	2.50	2.50	2.50	2.50	3.00	3.00	1.00	1.00	1.00	1.00	5.83	5.50	5.67	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	4.88
Overall L1	5.83

Vectorization ratios

INT

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

INT+FP

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 5.83 cycles. At this rate:

20% of peak load performance is reached (20.06 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (1.37 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 422f40

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
LDR X3, [X23, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR W24, [X19, #672]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDRB W2, [X22, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (6.3%)
LDR D15, [X3, X24,SXTW #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
SBFM X28, X24, #0, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TBZ W2, #0, 423488 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x5a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X0, XZR, X19	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDR X27, [X19, #656]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR W1, [X26, #584]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
BL 49180c <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X5, [X0, #72]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X4, X25, X25,LSL #2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
LDR X7, [X27, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X13, [X26, #160]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X6, X5, X4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDR X14, [X6, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR W8, [X7, X28,LSL #2]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
MADD W9, W8, W13, WZR	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
CBZ X13, 423438 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x558>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [X27, #616]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
MOVI D2, #0	1	0	0	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%)
MOVZ X8, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
CNTW X7, ALL	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
PTRUE P7.B, ALL	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (100.0%)
LDR X4, [X26, #464]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X10, [X26, #512]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X12, X10, W9,SXTW #3	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (50.0%)
LDR X11, [X11, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADDVL X6, X4, #1	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
FSUB D15, D15, S2	1	0	0	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 D0, D15	1	0	0	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%)
ADD X20, X20, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
BL 403db0 <@plt_start@+0xc0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X1, X3, [X21]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	N/A
SUB X27, X3, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STR D0, [X1, X25]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD X25, X25, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP X20, X27,ASR #3	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
B.CC 422f40 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x60>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code