Apple M1 Microarchitecture Research by Dougall Johnson

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

SRHADD (vector, 4S)

Test 1: uops

Code:

  srhadd v0.4s, v0.4s, v1.4s
  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)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
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715661168725100010001000264680020182037203715723189510001000200020372073111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100001073116111787100020382038203820382038
1004203716061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  srhadd v0.4s, v0.4s, v1.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9facbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150002706119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500022206119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000010319687251010010010012100100005002847680120054200372003718422318745101002001000020020000200372003711102011009910010010000100307101161119827100001002018420038200382008520134

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001006404162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001066402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001006402162219785010000102003820038200382003820038
100242003715026461196872510010101000010100005028476802001820037200371844422187671001020100002020000200372003711100211091010100001006402162219785010000102008520038200382003820038

Test 3: Latency 1->3

Code:

  srhadd v0.4s, v1.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119854100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010008407101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001002007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100011407101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000010006404164319785010000102003820038200382003820038
1002420037150000000031019687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006404164419785010000102003820038200382003820038
1002420037150000000012419687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000306404164419785010000102003820038200382003820038
100242003715000000006119687251001012100121010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006403163219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020101622020000200372003711100211091010100001000000006403163319785010000102003820038200382003820038
1002420037150000000063119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000010306403164419785010000102003820038200382003820038
1002420037150000005706119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006404164319785010000102003820038200382003820038
10024200371500000092646119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006404163319785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476802001820037200371844417187671001020100002020000200372003711100211091010100001000000006404164319785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680201262003720037184443187671001020100002020000200372003711100211091010100001000000006403164319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  srhadd v0.4s, v8.4s, v9.4s
  srhadd v1.4s, v8.4s, v9.4s
  srhadd v2.4s, v8.4s, v9.4s
  srhadd v3.4s, v8.4s, v9.4s
  srhadd v4.4s, v8.4s, v9.4s
  srhadd v5.4s, v8.4s, v9.4s
  srhadd v6.4s, v8.4s, v9.4s
  srhadd v7.4s, v8.4s, v9.4s
  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)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)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
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010003451101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192023720038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150000103258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010020051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010030051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

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)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)9fa8acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815001582580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502000021620011200350080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010100502000011600011200350080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000011600011200350080000102003920039200392003920039
80024200381490392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502000011600011200350080000102003920039200392003920039
800242003815001902580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000011608022200350080000102003920039200392003920039
80024200381500832580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010100502000011600011200350080000102003920039200392003920039
80024200381500502580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502000021600022200350080000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502000011601011200350080000102003920039200392003920039
80024200381500392580010108000010800006164000012001920038200389996310018800102080000201600002003820038118002110910108000010000502000011600011200350080000102003920039200392003920039
800242003815005342580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502000011600011200350080000102003920039200392003920039