mpw-003 / NPCM Nitride Poly Cut

the NPCM shapes of all of mpw-003

40 of 40 dies rendered.

17,799,660 shapes in total, each die at 0.125 µm per pixel.

result.json · job.json · reticle overview PNG

1234567
A A1 A2 A3 A4 A5 A6
B B1 B2 B3 B4 B5 B6 B7
C C1 C2 C3 C4 C6 C7
D D1 D2 D3 D4 D5 D6 D7
E E1 E2 E3 E4 E5 E6 E7
F F1 F2 F3 F4 F5 F6 F7

Downloading the full-resolution image

The stitched reticle is 53,432×65,056 pixels — 3.48 gigapixels. The file itself is small, but decoding it needs about 3.5 GB of memory however small the file is, and most viewers refuse it outright. So it is also published as 42 tiles of about 7576×10776 px (72.5 MB in total, largest 4.5 MB), cut in the gaps between dies so that every tile holds whole projects and none is split.

To put the full-resolution PNG back together from them, byte for byte, with nothing installed but Python itself:

python3 reconstruct_reticle.py

Run it in a directory holding the tiles and mpw-003_NPCM_tiles.json and it finds them itself, checks every tile against its checksum as it reads it, and checks the finished file against the manifest. It works because the tiles and the full image are written with PNG's Up filter, which never looks at the pixel to its left — so a row of tiles' scanlines laid end to end is the full image's scanline, and rebuilding moves bytes rather than doing pixel arithmetic.

Whole-reticle files

FileSizeMD5SHA-1SHA-256
mpw-003_NPCM_reticle.png
the stitched reticle, full resolution
39.9 MB c844a144c0afe490fb4ce3bc1945bfaa062a815803d0454c5b45418145a39f5b638718ce ae9c5584c2931141497f9ab309aa70fa8b9c01d4d79a728795b4c85f91ac42bf
mpw-003_NPCM_reticle_overview.png
the same image scaled to fit 4096 px
1.6 MB a9f28e4b3ae1b59d38722d991eed36f3b4f1aca2d847418eae6b8d6f84cdc63ade9083be aaea3547c6d87351b38014a9d64086df7c205abbf1188f0b1ecb3d0b1f1c114b
mpw-003_NPCM_tiles.json
where every tile belongs, and its checksum
13.5 kB 2cca04ea9eca8495eeb0c336a0f902c67e5745f1e5d3ece68e245a812055428b96673edf 15dee1b379f8657246e120117d195b99bf9ec550ba1f0d1a3f9d03a29f5982b5
reconstruct_reticle.py
rebuilds the reticle from the tiles, standard library only
11.9 kB 4406f1f3db8a4a85756610b7c432c47a294714566ceb084187594ced0020f9260faac32a d2e72bf4b2541f1a8acb11eb758917c5b5fa080b41b3a7118487c03f8af2a769

Every file in this directory is listed in MD5SUMS · SHA1SUMS · SHA256SUMS, in the format the standard tools read:

sha256sum -c SHA256SUMS

The 42 tiles

FrameProjectPixelsPositionSizeSHA-256
A1 stdcelllib 7576×107760, 0 1.4 MB4930115bdf3b9b60ef255abc5968ad02e2b271e58f6283e03a2ba34100cf1b8d
A2 1v8_ldo_design_in_skywaters_130nm 7576×107767576, 0 1.3 MB52d886ab18f7c3aac0d88ef29763bb493b3399f7316e977c6a15d46ab2cba65e
A3 openram_test 7576×1077615152, 0 1.5 MB9021fc77e26bb2185775c77c08a4c8643518feb4ae1874f532afc9581b7dfe00
A4 zero_to_asic_course_group_submission_mpw3 7576×1077622728, 0 1.8 MB7845b11131858f562aca3cb9ef1004cdcdfe19237f8ead893a7d2a18bd9ab78a
A5 crypto_accelerator_v2 7576×1077630304, 0 2.3 MB715f53c8baa645dc98194f29adefb17e4c784443f6e3d496489e1bb1b66037eb
A6 picorf0 7576×1077637880, 0 1.8 MBb06b7350969a24cb153cd11b172e533c04813a26f0fe24eaa6536f9e4501b5a5
A7 SkyWater test structures 7976×1077645456, 0 106.8 kB56c5b78f9b86a53fdb64304acc12fba53d045b0526cc20ac1552594029f8a19a
B1 randsack 7576×107760, 10776 1.6 MB470548156f41dd8e6b5e4d2f0bcdfe1f144a7e8e254c128742b50d87685a90e5
B2 yonga-100m_ethernet 7576×107767576, 10776 1.8 MB2e6408c1b3cb30d5472a274460e7fbb9e3279f642f547cea7c7cc74c9757087b
B3 approximate_multiplier 7576×1077615152, 10776 1.4 MB67cb2ebbfea96bced9602b009e996da19c84708b7e387f660bd93e91f89f6ca9
B4 vsd 7576×1077622728, 10776 1.4 MBab8aaa4cc4bb0391384359fff6c598485aeb219a8285d8bbc70c0b612dfa888f
B5 asic_key_value_store 7576×1077630304, 10776 1.4 MB4930115bdf3b9b60ef255abc5968ad02e2b271e58f6283e03a2ba34100cf1b8d
B6 mbist_controller 7576×1077637880, 10776 2.1 MBa62417676d8179e092cd8c9b02919203ad23ce428cdf605c1bd09c167c6c95ff
B7 riscduino 7976×1077645456, 10776 2.8 MB4c02293299343224268b6349289df8011651f3698a503f8dee3b745bec4aea91
C1 caravel_peripheral_extender 7576×107760, 21552 1.9 MBf3df80f4039b2a28021fbd3672591c055418fa050ad9db37335bf2016ea84dbc
C2 ucsc_openram_test_chip_v2 7576×107767576, 21552 2.3 MB3e210afdd3345e7a4f1517df8915ff9db810e6cea2d3aa4d7c4b42a42c89ebcd
C3 class-d_audio_amplifier 7576×1077615152, 21552 1.4 MB89858d7c05c7a441fb146ed7317baeef63f459fa6c87fa0f7e559bcbb6d6d794
C4 efabless_processor 7576×1077622728, 21552 1.4 MB6bf0df60657e8d52037ec69c5926f4032f43dc5c529386018e2a51ff506c08f6
C5 SkyWater test structures 7576×1077630304, 21552 102.7 kB404d2b68827b8f64404c8d26b19179b934888b57260a33a16e25162769e85650
C6 tooltest 7576×1077637880, 21552 1.4 MB5da30ed5aea39ee10d94abca3ad8da64e1cb932dda37b0e6bdbf2b6da12dae82
C7 comparator_and_mixed_signal_test 7976×1077645456, 21552 1.3 MB89f13cc5acfddc0a9e62fe8d1cd924d996eabe666daa941c7034dbc02835c5d5
D1 current_starved_voltage_controlled_oscillator 7576×107760, 32328 1.3 MBc0e05a7c9cb180b5990aba72626e5d52d81a80cc5426c72d5615c670f7fea730
D2 two_stage_cmos_operational_amplifier 7576×107767576, 32328 1.3 MBe821d3f58e9e5253a6208c69c678ca858c5f092e095a0cd712566c2556ecd20c
D3 sziklai_pair_amplifier 7576×1077615152, 32328 1.3 MB79d9d3706c40b7dbf030fd13890e9c6261d1508889e9945624928bb653a92a5b
D4 two_stage_cmos_opamp_with_frequency_compensation 7576×1077622728, 32328 1.3 MBaf6f0a4909f40419862fe4f048e8ee0b2ffaa38dc2e5de6d9b7c961fd5974d93
D5 pre-trained_neural_network_for_mnist 7576×1077630304, 32328 2.1 MB7752fa2a782b098591b555aca2519fc250ded53d2635bcbb86a3419a68f40d06
D6 rotfpga 7576×1077637880, 32328 1.9 MB7e5f5cc6aa84d3f97d1f07d56b260b007a8bda70e2523f5562fc0834d85f2ecc
D7 treepram 7976×1077645456, 32328 3.7 MBb9fa72d6f392ddeba69d1b2dacdb165ec87559f4b9405e9c75e9a8a07bbea044
E1 treepram-red 7576×107760, 43104 4.5 MB9a48801ee4fd7aafb9eed1d07b8b978f41210b297ac9ff7f6c24fb68de750860
E2 caravel_jacaranda-8 7576×107767576, 43104 1.8 MBcef16616b2482ad39bcd6b54b9c48eef2d0ea5e4a112fe442251dbcda8b9e6f5
E3 sudoku_accelerator 7576×1077615152, 43104 1.9 MB9980250dc8204d1d31a5b7f3f1f238402c650bd8dd00ff2954d702bd65b49c62
E4 fixed2float_converter 7576×1077622728, 43104 1.4 MBaa2dd58c58b8f7f0a5620c900f1ed31acf158f61b300ca36363d9e384a47f42a
E5 high_speed_adder 7576×1077630304, 43104 1.4 MB382a0aa4c6d1236cbba2c004ea160d21f52129feb979e0ea07ea4b36e921ba53
E6 my_proj 7576×1077637880, 43104 1.4 MB16c579f9a08705470c5a5a923af0c83fe556f50689b3f6ba9ea507ebe8fe8a50
E7 pwm_test 7976×1077645456, 43104 1.4 MBd4592f8ef31be4244c8088b60698328a8a360663a6d0c84c1a6627c467581802
F1 elpis-light-mpw3 7576×111760, 53880 3.7 MBc446e5288c4ef3901a916e30baf821d3cf9fb6631ce7e137ac23ea76340b4ca1
F2 vsdbabysoc 7576×111767576, 53880 1.7 MB19a5373be216ed83056d2a0ebcd47c89aacc907bd0f16fd4abba285509ef1a4d
F3 vsdmemsoc 7576×1117615152, 53880 2.0 MB395793bf43649c8afa63bea337329560e0763594255d6e6be61526a463d0aaaa
F4 caravel_sram_test 7576×1117622728, 53880 1.4 MB514d2c847aeb646a8ee3fa84caa226a8c1b566151876911152625268b1b68da0
F5 8-bit_sar-adc_with_offset_calibration 7576×1117630304, 53880 1.3 MBe1e04ed8aa6898098775c6cf5cea7f88f4e603191600288dfdd3f9dc21c71dc3
F6 caravel_hyperram_driver_and_openram 7576×1117637880, 53880 1.5 MBf599d290c3efdc0567d03a4315eac6b548d40317b748151a5957b58e4e9a9352
F7 caravel 7976×1117645456, 53880 1.4 MBe5a904fce408d633b2e60223f4d8d447ff7fd91edb0ce458475b6d067d23b1cb

Position is the tile's top-left corner in the full-resolution image. MD5 and SHA-1 for the same files are in the checksum files linked above.

About NPCM on mpw-003

Resolved: reticle 5CS8008AC, run mpw-003, mask NPCM

Mask layer
NPCM — Nitride Poly Cut
Process step
78 — Nitride poly cut mask
Drawn layer
95:20
Layer on the mask-layer GDS
49:0
Used in SKY130
yes

mpw-003 — SKY130 MPW-3

Foundry product
EF MPW#3
Reticle set
5CS8008AC
Run date
2021-11-15
Submissions closed
2021-11-15
Projects
53
Fab lot
4206521
Identification
confirmed — Lot records: EF MPW#3, lot 4206521 = 'SKY130 MPW 3'; confirmed by a photo of the MPW-3 mask set's VIM2 plate label (DEVICE 5CS8008A-A, LAYER VIM2 560A 03-01, archived 2022-05-13), seen 2026-08-28
Shuttle page
archived copy of https://platform.efabless.com/shuttles/MPW-3 — the platform that hosted it is gone
Foundry data
third_party/shuttle/sky130/mpw-003/foundry

These are renders of the drawn shapes that go on each photomask, taken from the layouts the shuttle's projects taped out — they are not photomask artwork: reticle pitch, the 4x reduction, mirroring and the frame features the fab adds are not modelled. An empty image is a real result; several mask layers are used by no project on a given shuttle. Each die's source layout is named in result.json and lives in the public shuttle repositories under foss-eda-tools.googlesource.com, so every image here can be traced back to the tape-out it came from. Generated with sky130-mask-decoder.