Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMU (scalar, D to D)

Test 1: uops

Code:

  fcvtmu d0, d0
  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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372406125472510001000100039816030183037303724143289510001000100030373037111001100021073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110005073116112629100030383038303830383038
10043037240982547251000100010003981603018303730372414328951000100010003037303711100110004073116112629100030383038303830383038
100430372401032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372301382547251000100010003981603018303730372414328951000100010003037303711100110002073116112629100030383038303830383038
100430372301032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372315612547251000100010003981603018303730372414328951000100010003037303711100110000373116112631100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112701100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtmu d0, d0
  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)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)696d6edispatch 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330822954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129780100001003003830038300753013430038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372320612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037233127262954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100200007101161129633100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100100007101161129633100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723307262954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e1f3f4e51inst 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)6061696d6edispatch 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)9fa8acbranch mispredict (cb)cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723300011742954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003723300010532954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
10024300372330009592954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003723200011152954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003723300017062954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
10024300372330005952954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
10024300372320004432954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003723301208052954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
10024300372250008762954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
10024300372240008282954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtmu d0, d8
  fcvtmu d1, d8
  fcvtmu d2, d8
  fcvtmu d3, d8
  fcvtmu d4, d8
  fcvtmu d5, d8
  fcvtmu d6, d8
  fcvtmu d7, d8
  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)031e3f51inst 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)9fa8a9acc2c5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058156153025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016020036800001002004020040200402004020040
802042003915607225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016020036800001002004020040200402004020040
802042003915505825801081008000810080020500640132020042200392003999776999080120200800322008003220039200391180201100991001008000010030001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016020036800001002004020040200402004020040
802042003916103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000301115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa8accfd2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391550040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001003502000116112003680000102004020040200402004020040
80024200391555713240258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391550040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391550040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391560040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116112003680000102004020040200402004020040
80024200391560040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502000116312003680000102004020040200402004020040
80024200391550040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001010502000116112003680000102004020040200402004020040
80024200391550040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001010502000116112003680000102004020040200402004020040
80024200391550082258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001013502000216112003680000102004020040200402004020040