Apple M1 Microarchitecture Research by Dougall Johnson

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

SMULL2 (by element, 2D)

Test 1: uops

Code:

  smull2 v0.2d, v0.4s, v1.s[1]
  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
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230822548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230822548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110001073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  smull2 v0.2d, v0.4s, v1.s[1]
  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)0318191e3a3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400285061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000549295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250015061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250030061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250015061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225006161295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500150251295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250015061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250057061295482510100100100161001000050042773131300183003730037282653287451010020010000200203323013230037111020110099100100100001001607102241229634100001003003830038300383008530038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000060612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000060662954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000180612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000540612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372240000180612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000060612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000060612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000360612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000360612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  smull2 v0.2d, v1.4s, v0.s[1]
  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)030a1e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722501861295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000027102162229634100001003003830038300383003830038
1020430037225039536295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500346295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500631295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500726295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001003007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722502161295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
102043003722500536295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa0a6a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731303002030037300372828732876710010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000001640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732879010010201000020200003003730037111002110910101000010000000640316332963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  smull2 v0.2d, v8.4s, v9.s[1]
  smull2 v1.2d, v8.4s, v9.s[1]
  smull2 v2.2d, v8.4s, v9.s[1]
  smull2 v3.2d, v8.4s, v9.s[1]
  smull2 v4.2d, v8.4s, v9.s[1]
  smull2 v5.2d, v8.4s, v9.s[1]
  smull2 v6.2d, v8.4s, v9.s[1]
  smull2 v7.2d, v8.4s, v9.s[1]
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150042412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051102161120036800001002004020040200402004020040
8020420039150001572580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080105200160000200392003911802011009910010080000100051101161120333800001002004020040200402004020118
8020420039150021412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
8020420039150015412580100100800001008000050064082002002020039200399973399978010020080000200160000200392003921802011009910010080000100051101161120036800001002004020040200402004020040
8020420039150015412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
8020420039150012412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000412580206100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040

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)696b6d6edispatch 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150244025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020616242003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020416422003680000102004020040200402004020040
80024200391501954025801111080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020216422003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020416422003680000102004020040200402004020040
800242003915034025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020416242003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020416242003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020216422003680000102004020040200402004020040
80024200391503034025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020416242003680000102004020040200402004020040
80024200391502854025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020216242003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020416242003680000102004020040200402004020040