Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FCVTNS (vector, 4S)

Test 1: uops

Code:

  fcvtns v0.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)0308191e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a0a8accfd5d6daddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372400002642547251000100010003981600301830373037241432895100010001000303730371110011000000731160112629100030383038303830383038
100430372400001032547251000100010003981601301830373037241432895100010001000303730371110011000000731160112629100030383038303830383038
100430372400003712547251000100010003981600301830373037241432895100010001000303730371110011000000731160112629100030383038303830383038
100430372400006262547251000100010003981600301830373037241432895100010001000303730371110011000000731160112629100030383038303830383038
10043037230000612547251000100010003981601301830373037241432895100010001000303730371110011000400731160112629100030383038303830383038
10043037230000612547251000100010003981601301830373037241432895100010001000303730371110011000000731160112629100030383038303830383038
10043037240000612547251000100010003981600301830373037241432895100010001000303730371110011000000731160112629100030383038303830383038
10043037240000612547251000100010003981601301830373037241432895100010001000303730371110011000000731160112629100030383038303830383038
1004303723001201032547251000100010003981601301830373037241432895100010001000303730371110011000000731160112629100030383038307430383038
10043037240000612547251000100010003981601301830373037241432895100010001000303730371110011000019731160112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtns v0.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e5051inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320442295470251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100107101161129777100001003003830038300383003830038
102043003723302512954730021251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038
10204300372330612954730021251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372330612954730021251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372320612954730021251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037233061295470251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129742100001003003830038300383003830038
1020430037233061295470251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037233061295470251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037233061295470251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037232061295470251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372330147295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000064041634296290010000103003830038300383003830038
10024300372330208295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000064041644296290010000103003830038300383003830038
1002430037233061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000064041634296290010000103003830038300383003830038
1002430037233061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064041643296290010000103003830038300383003830038
1002430037233061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001040064041643296290010000103003830038300383003830038
1002430037233084295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064031644296290010000103003830038300383003830038
10024300372320166295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000064041634296290010000103003830038300383003830038
1002430037232061295472510010101000010100005042771600300183003730037282863287671015820100002010000300373003711100211091010100001005570264031634296290010000103003830038300383003830038
1002430037232061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000064041622296290010000103003830038300383003830038
10024300372330189295472510010101000010100005042771601300183003730037282863287671016220100002010000300373003711100211091010100001003064041644296293010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtns v0.4s, v8.4s
  fcvtns v1.4s, v8.4s
  fcvtns v2.4s, v8.4s
  fcvtns v3.4s, v8.4s
  fcvtns v4.4s, v8.4s
  fcvtns v5.4s, v8.4s
  fcvtns v6.4s, v8.4s
  fcvtns v7.4s, v8.4s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155007225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039156003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391550030225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)03070a191e1f3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accdcfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511561100028951800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100015024000161614162003680000102004020040200402004020040
80024200391551100024725800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100005024000171616132003680000102004020040200402004020040
800242003915611022510824725800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100005024000161613152003680000102004020040200402004020040
80024200391561100024725800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005024000151615132003680000102004020040200402004020040
8002420039155110002472580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010230506200016168152003680000102004020040200402004020040
80024200391551100024725800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100005024000171616142003680000102004020040200402004020040
80024200391561100024725800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005024000171617132003680000102004020040200402004020040
80024200391551100024725800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100005024000151616142003680000102004020040200402004020040
80024200391551100024725800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005024000131615142003680000102004020040200402004020040
800242003915511000224525800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000101005024000231611122003680000102004020040200402004020040