Apple M1 Microarchitecture Research by Dougall Johnson

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

SQADD (vector, 2D)

Test 1: uops

Code:

  sqadd v0.2d, v0.2d, v1.2d
  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)031e3a3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372302622548251000100010003983130301830373037241532895100010002000303730371110011000077424442630100030383038303830383038
100430372202622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038
100430372302622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038
100430372302622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038
100430372302622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038
100430372302622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038
100430372302622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038
100430372302622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038
1004303722212622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038
100430372302622548251000100010003983130301830373037241532895100010002000303730371110011000077416442630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqadd v0.2d, v0.2d, v1.2d
  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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250346295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372251261295486410100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000237102482229704100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250103295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
10204300372250185295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000037102162229634100001003003830038300383008530038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000006404163329630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
10024300372250000021006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000206403164329630010000103003830085300383003830038
1002430037224000536721760404029485251001010100001211043614286812030018300373003728287328767100102210498222164230083301793110021109101010000100000000006403165529843410000103036930279300383003830320
1002430367228101671501251295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001004201016773206404163329630210000103003830038300383003830038
1002430037225000000005143295391771008313100561411192664288169130018300373003728287542897311488221147122226223046530085111100211091010100001020001422270007894735329994110000103036930510305143051230181
1002430037229111101013299680714629548251001010100001010000504277313130018300373003728287142876710010221131122226403032030370111100211091010100001002210027410008503884330014510000103022730509305563051030418
10024305092280011010146488006471294582191007514100881210000504277313130018300373003728287328767100102010172202000030179300371110021109101010000100000000016403163329630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000006403163329630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqadd v0.2d, v1.2d, v0.2d
  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)030b1e3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225063006129548451013510010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021624296340100001003003830038300383003830038
10204300372251006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
102043003722406906129539251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000100071021622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830180
102043003722500072629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038

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)9fa0a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225006129530251001010100071010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250013629548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000036402161229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqadd v0.2d, v8.2d, v9.2d
  sqadd v1.2d, v8.2d, v9.2d
  sqadd v2.2d, v8.2d, v9.2d
  sqadd v3.2d, v8.2d, v9.2d
  sqadd v4.2d, v8.2d, v9.2d
  sqadd v5.2d, v8.2d, v9.2d
  sqadd v6.2d, v8.2d, v9.2d
  sqadd v7.2d, v8.2d, v9.2d
  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)03080b18191e3f51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051102161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
8020420039149000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180202100991001008000010000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
802042003915000003154125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
802042003915000001984125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048151000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000050200007160008172003600080000102004020040200402004020040
80024200391500004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010046502000081600017172003600080000102004020040200402004020040
800242003915000040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100005020000171600017172003600080000102004020040200402004020040
8002420039150030304025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000017160001782003600080000102004020040200402004020040
80024200391500004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000061600017172003600080000102004020040200402004020040
800242003915000046258001010800001080000506400001120020200392003999963100198001020800002016000020039200391180021109101080000100005020000171600017172003600080000102004020040200402004020040
80024200391500004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000017160008172003600080000102004020040200402004020040
8002420039150000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000050200007160007172003600080000102004020040200402004020040
80024200391500004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010203502000017160001782003600080000102004020040200402004020040
80024200391500004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000017160008172003600080000102004020040200402004020040