Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (register, 8B)

Test 1: uops

Code:

  cmgt v0.8b, v0.8b, v1.8b
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037151386116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111785100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
100420371506116872510001000100026468012018203720371571318951000100020002037203711100110000073116111787100020382038203820382038
1004203715025116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116121785100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203721100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.8b, v0.8b, v1.8b
  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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000126071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100020071011611197910100001002003820038200382023020038
102042008415000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

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)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)9fa8c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150039919687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006403162219785010000102003820038200382003820038
100242003715008419687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150010319687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500109019687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003714906119687251001010100001010000502847680020018020037200371844431878810010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150052619687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010106402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmgt v0.8b, v1.8b, v0.8b
  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)0318191e3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd6inst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500001681968744101001001000010010000500284768012001820037200371842961874010100200100082002001620037200371110201100991001001000010000111718161198020100001002003820038200382003820038
1020420037150009611968725101001001000010010000500284768002001820037200371842961874010100200100082002001620037200371110201100991001001000010000111718161198020100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842961874110100200100082002001620037200371110201100991001001000010000111717161198010100001002003820038200382003820038
10204200371500103311968725101001001000010010000500284768012001820037200371842971874110100200100082002001620037200371110201100991001001000010000111717161198010100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842971874110100200100082002001620037200371110201100991001001000010000111718161198020100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842961874110100200100082002001620037200371110201100991001001000010000111717161198010100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842971874010100200100082002001620037200371110201100991001001000010000111718161198010100001002003820038200382003820038
10204200371500001561968725101001001000010010000500284768002001820037200371842971874110100200100082002001620037200371110201100991001001000010000111717161198010100001002003820038200382003820038
10204200371500001701968725101001001000010010000500284768012001820037200371842961874010100200100082002001620037200371110201100991001001000010000111718161198020100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842961874010100200100082002001620037200371110201100991001001000010000111717161198020100001002003820038200382003820038

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)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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715001701968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010002006402162219785010000102003820038200382003820038
100242003715001261968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10025200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500841968725100101010000101000050284768002001820037200371844431878510318201000020200002003720037111002110910101000010000006402162419853010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162319785010000102003820038200382003820038
10024200371500821968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500821968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmgt v0.8b, v8.8b, v9.8b
  cmgt v1.8b, v8.8b, v9.8b
  cmgt v2.8b, v8.8b, v9.8b
  cmgt v3.8b, v8.8b, v9.8b
  cmgt v4.8b, v8.8b, v9.8b
  cmgt v5.8b, v8.8b, v9.8b
  cmgt v6.8b, v8.8b, v9.8b
  cmgt v7.8b, v8.8b, v9.8b
  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)03091e3f51inst 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)9fa8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815020124258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
802042003815000230258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000151101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200190200382003899733999680100200800002001600002008920038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392008820039
80204200381500040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000051101161220035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3f51inst 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039151203925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020171611112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020131612112003580000102003920039200392003920039
8002420038150103925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020121612132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020111611132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020131612122003580000102003920039200392003920039
80024200381500010425800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020111613132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020111612132003580000102003920039200392003920039
8002420038150003925800101080000108010850640000120019200382003899963100188001020800002016000020038200381180021109101080000105020111612112003580000102003920039200392003920039
8002420038149003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020121611122003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000105020131613122003580000102003920039200392003920039