Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAU (scalar, H to H)

Test 1: uops

Code:

  fcvtau h0, h0
  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)03181e1f3f4e51inst 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)a0a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724000612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230906125472510001000100039816013018303730372414328951000100010003037303711100110000004573116112629100030383038303830383038
1004303724000752547251000100010003981601301830373037241432895100010001000303730371110011000003373116112629100030383038303830383038
100430372301802512547251000100010003981600301830373037241432895100010001000303730371110011000000673116112629100030383038303830383038
1004303724060612547251000100010003981600301830373037241432895100010001000303730371110011000005073116112629100030383038303830383038
1004303724000612547251000100010003981600301830373037241432895100010001000303730371110011000008073116112629100030383038303830383038
1004303724000612547251000100010003981600301830373037241432895100010001000303730371110011000000373116112629100030383038303830383038
10043037240006125472510001000100039816003018303730372414328951000100010003037303711100110000001873116112629100030383038303830383038
1004303724000612547251000100010003981600301830373037241432895100010001000303730371110011000200373116112629100030383038303830383038
1004303724000612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtau h0, h0
  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)0307191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200006129547251010010010000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010020007101161129633100001003003830038300383003830038
1020430037232001206129547251010010010000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
1020430037233000034029547251010010010000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010001007101161129633100001003003830038300383003830038
102043003723300006129547251010010010000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000027101161229633100001003003830038300383003830038
1020430037233001206129547251010010010000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723300008429547251010010010000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007103161129633100001003003830038300383003830038
1020430037232001206129547251010010010000010010000500427716003001830037300372826432874410100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723200006129547251010010010000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723200006129547251010010010000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723310006129547251010012510000010010000500427716013001830037300372826432874510100200103292001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240049729547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316222962910000103003830038300383003830038
10024300372250038229547251001010100001010000504277160130018300373008528286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372240014529547251001010100001010000504277160130018301813003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722509316629547251001010100001010000504277160130018300373003728286328805100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225063223329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103008430038300383003830038
1002430037225008429547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250014929547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225006129547251001012100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250017029547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtau h0, h8
  fcvtau h1, h8
  fcvtau h2, h8
  fcvtau h3, h8
  fcvtau h4, h8
  fcvtau h5, h8
  fcvtau h6, h8
  fcvtau h7, h8
  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)03071e3f51inst 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)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591550060025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
80204200391610022625801081008000810080024500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
8020420039155003025801081008010810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511837020036800001002004020040200402004020040
8020420039155063025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
8020420039155037225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
8020420039155103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502009316112003680000102004020040200402004020040
800242003915500166258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020011216112003680000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020011116112003680000102004020040200402004020040
8002420039155012705258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020011116112003680000102004020040200402004020040
80024200871550640258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010035020010216112003680000102004020040200402004020040
80024200391610040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010035020010216112003680000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020010116112003680000102004020040200402004020040
800242003915501240258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020010316112003680000102004020040200402004020040
80024200391550040258001010800001080000506407561200202003920039999631001980010208000020800002003920039118002110910108000010005020010116222003680000102004020040200402004020040
80024200391550082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020010116112003680000102004020040200402004020040