Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTM (vector, 4H)

Test 1: uops

Code:

  frintm v0.4h, v0.4h
  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)030b181e3f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724000612547251000100010003981600301830373037241432895100010001000303730371110011000012073116112629100030383038303830383038
100430372400061254725100010001000398160030183037308424143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100009073116112629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723000103254725100010001000398160030183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
1004303723000612547251000100010003981600301830373037241432895100010001000303730371110011000001873116112629100030383038303830383038
100430372410061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372500061254725100010001000398160130543084303724143289510001000100030373084111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintm v0.4h, v0.4h
  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)03080b18191e1f3a3f4e51inst 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)9fa0a1a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037232000000028629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003723300000008429547251010010010000104100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003724100000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000003000071011611296330100001003003830038300383003830038
1020430037233000000019129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038
102043003723200000008429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000003000071011611296330100001003003830038300383003830038
1020430037232000000058429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000010071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500010942954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006406162229629010000103003830038300383003830038
10024300372250008902954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250009602954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250003842954725100101010008101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250003652954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500010402954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500010532954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250009432954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250004532954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250909232954725100101010000101000055427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintm v0.4h, v8.4h
  frintm v1.4h, v8.4h
  frintm v2.4h, v8.4h
  frintm v3.4h, v8.4h
  frintm v4.4h, v8.4h
  frintm v5.4h, v8.4h
  frintm v6.4h, v8.4h
  frintm v7.4h, v8.4h
  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)03080a18191e1f3a3f51inst 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)60696b6d6edispatch 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)9fa1a8c5branch mispredict (cb)cdcfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058156000000072258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010001111511800160020036800001002009420040200402004020040
8020420039161000000130258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040
8020420039156000000053258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040
8020420039156000000053258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200200200392010399776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040
8020420039161000000072258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040
8020420039155000000051258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040
80204200391550051150094258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000111511800160020036800001002004020040200402004020040

1000 unrolls and 10 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)72scheduler 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155126125800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100005020281619272003680000102004020040200402004020040
800242003915504025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100105020271627272003680000102004020040200402004020040
8002420039155012825800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100005020261627142003680000102004020040200402004020040
800242003915506125800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100105020271630292003680000102004020040200402004020040
800242003915508425800101080000108000050640000120020200392003999967310019800102080000208000020039200391180021109101080000100005020201628262003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020281613272003680000102004020040200402004020040
80024200391551214925800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100005020271627262003680000102004020040200402004020040
800242003915506325800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020271621272003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999960310019800102080000208000020039200391180021109101080000100005020261627272003680000102004020040200402004020040
800242003915504025800101080000108000050640000120020200392003999960310019800102080000208000020039200391180021109101080000100005020261627272003680000102004020040200402004020040