The China Mail - Voltage Glitch Unlocks Full Memory on Nvidia CMP 170HX Mining Card

USD -
AED 3.6725
AFN 64.501804
ALL 82.074163
AMD 360.410299
ANG 1.790403
AOA 917.999948
ARS 1559.251096
AUD 1.48917
AWG 1.8025
AZN 1.702891
BAM 1.784546
BBD 2.014608
BDT 124.529524
BGN 1.77347
BHD 0.37715
BIF 3006
BMD 1
BND 1.290102
BOB 11.71844
BRL 5.883199
BSD 1.00031
BTN 93.468373
BWP 14.13099
BYN 3.000803
BYR 19600
BZD 2.011688
CAD 1.43333
CDF 2285.000216
CHF 0.843505
CLF 0.025568
CLP 1006.292558
CNY 6.667798
CNH 6.668335
COP 3358.67
CRC 444.714116
CUC 1
CUP 24.006241
CVE 100.788667
CZK 22.23505
DJF 177.71997
DKK 6.812102
DOP 60.300989
DZD 137.140202
EGP 53.746397
ERN 15
ETB 164.179829
EUR 0.91139
FJD 2.287898
FKP 0.756582
GBP 0.760745
GEL 2.589792
GGP 0.756582
GHS 11.769907
GIP 0.756582
GMD 73.502553
GNF 8854.999897
GTQ 7.644614
GYD 209.194637
HKD 7.845295
HNL 26.888579
HRK 6.831965
HTG 131.148887
HUF 336.084502
IDR 18243
ILS 3.27795
IMP 0.756582
INR 93.46535
IQD 1516.380541
IRR 1933164.500507
ISK 124.84984
JEP 0.756582
JMD 158.655425
JOD 0.708975
JPY 159.405497
KES 129.980322
KGS 87.449404
KHR 4075.000433
KMF 448.999805
KPW 900.00035
KRW 1329.179856
KWD 0.31172
KYD 0.833618
KZT 444.858091
LAK 22535.000045
LBP 89549.999719
LKR 332.884718
LRD 168.500318
LSL 17.280062
LTL 2.95274
LVL 0.60489
LYD 6.464983
MAD 9.962636
MDL 18.365056
MGA 4548.523669
MKD 56.080004
MMK 2099.387164
MNT 3606.75335
MOP 8.084275
MRU 40.651846
MUR 47.949885
MVR 15.401912
MWK 1734.461112
MXN 18.861355
MYR 4.113967
MZN 63.903062
NAD 17.195206
NGN 1352.699535
NIO 36.749774
NOK 9.701895
NPR 149.555172
NZD 1.82187
OMR 0.384508
PAB 1.000306
PEN 3.414981
PGK 4.500287
PHP 63.662503
PKR 276.54814
PLN 4.02135
PYG 6261.177415
QAR 3.646749
RON 4.873398
RSD 107.206022
RUB 82.400397
RWF 1480.345998
SAR 3.752254
SBD 8.137041
SCR 13.989309
SDG 601.501313
SEK 10.170885
SGD 1.28919
SHP 0.757117
SLE 22.800282
SLL 20969.503664
SOS 571.644951
SRD 37.3845
STD 20697.981008
STN 22.355442
SVC 8.752264
SYP 13002.000337
SZL 17.192233
THB 33.970096
TJS 9.197668
TMT 3.5
TND 3.029559
TOP 2.40776
TRY 50.467198
TTD 6.787749
TWD 32.944797
TZS 2654.998054
UAH 45.159677
UGX 4190.827262
UYU 40.641096
UZS 12013.157354
VES 915.5019
VND 25692.5
VUV 121.064676
WST 2.823281
XAF 597.832681
XAG 0.021999
XAU 0.000267515941
XCD 2.70255
XCG 1.802704
XDR 0.707052
XOF 597.832681
XPF 108.817344
YER 236.549774
ZAR 17.270615
ZMK 9001.195873
ZMW 20.545177
ZWL 321.999592
SSP 5928.707524
MXV 2.115399
  • RYCEF

    0.4000

    19.71

    +2.03%

  • CMSC

    0.0000

    20.4

    0%

  • BTI

    0.4200

    56.05

    +0.75%

  • BP

    0.2800

    44.43

    +0.63%

  • RBGPF

    1.6000

    67

    +2.39%

  • RIO

    -0.1500

    94.41

    -0.16%

  • AZN

    -0.4300

    166.15

    -0.26%

  • GSK

    0.4600

    49.7

    +0.93%

  • BCE

    -0.4100

    20.56

    -1.99%

  • NGG

    -0.2500

    75.24

    -0.33%

  • VOD

    -0.0400

    16.58

    -0.24%

  • RELX

    -0.4500

    33.07

    -1.36%

  • BCC

    -0.5500

    76.59

    -0.72%

  • CMSD

    -0.0300

    20.27

    -0.15%

  • JRI

    -0.2500

    10.77

    -2.32%

Voltage Glitch Unlocks Full Memory on Nvidia CMP 170HX Mining Card
Voltage Glitch Unlocks Full Memory on Nvidia CMP 170HX Mining Card

Voltage Glitch Unlocks Full Memory on Nvidia CMP 170HX Mining Card

A hardware researcher has demonstrated that a voltage fault injection attack can bypass factory-imposed restrictions on Nvidia’s CMP 170HX mining card, effectively unlocking its full 80GB of high-bandwidth memory and additional compute resources. The exploit reveals that the chip’s secure fuse system contains a fundamental design flaw allowing users to relax hardware limitations rather than just enforce them.

Text size:

A new hardware security analysis indicates that Nvidia’s silicon, long marketed for its ability to restrict functionality through immutable fuses, contains a critical design flaw that allows attackers to reverse those restrictions. The research, published by a researcher known as Kate on her personal blog, demonstrates that the CMP 170HX, a mining accelerator introduced in 2021, can be modified to behave like an Nvidia A100 data center GPU by exploiting a voltage glitch during the boot process.

The CMP 170HX was built using the GA100 die, the same silicon architecture that powers Nvidia’s high-end A100 accelerators. However, Nvidia intentionally disabled significant portions of this hardware at the factory to differentiate the mining card from its professional computing counterparts. The card shipped with only 8GB or 10GB of High Bandwidth Memory (HBM) exposed to software, 70 active streaming multiprocessors (SMs), and a limited PCIe Gen1 interface. Despite these restrictions, the physical chip contains closer to 80GB of HBM and up to 128 SMs, with the remaining capacity hidden by firmware and locked fuses.

Kate’s method involves voltage fault injection, a technique used in hardware security to disrupt a chip’s operation at precise moments. By tapping the signal line between the GPU and its voltage regulator with a microcontroller board, she was able to disturb the power supply during startup. This disturbance nudged the fuse controller into a state where normally unwritable fuses could be burned. Contrary to the standard behavior of secure fuse schemes, which are designed to permanently restrict functionality, the GA100’s architecture allowed Kate to "relax restrictions by blowing more fuses." This effectively re-enabled the memory and compute units that Nvidia had switched off.

The implications of this exploit are significant given the current state of the hardware market. The industry is currently experiencing a severe shortage of HBM, making high-bandwidth memory effectively sold out. Consequently, hardware that conceals usable memory behind software locks has become highly desirable. While community projects like cmpunlocker had previously used patched drivers to expose 64GB of memory on the CMP 170HX, Kate’s hardware-level approach goes further by unlocking the underlying silicon capabilities that software mods cannot access.

In testing, an unlocked CMP 170HX achieved approximately 85.9 TFLOP/s of FP16 fused-multiply-add throughput, compared to roughly 72.5 TFLOP/s for a retail A100. This performance gain stems from the fact that production A100s typically enable only 108 of the die’s 128 SMs for yield reasons, whereas Kate’s unlocked cards reported between 120 and 126 active SMs. However, these figures represent non-tensor FP16 throughput from a single OpenCL benchmark and do not account for tensor-core performance, Error Correction Code (ECC) functionality, NVLink connectivity, or Multi-Instance GPU (MIG) partitioning, which are critical for data center workloads.

Kate noted that ECC, MIG, and video engines remained untested in her initial findings. Furthermore, NVLink is not fully functional without additional board surgery, and pushing the PCIe link to Gen4 requires further hardware modifications. The researcher emphasized that while the card can reach higher raw throughput in specific synthetic tests, it does not function as a drop-in replacement for an A100 in a production environment. She described the modified card as a "GA100 running close to its native potential" rather than a cloned accelerator.

The vulnerability highlights a broader issue with Nvidia’s Ampere-era security architecture. Kate’s work builds on previous research, including a June 2026 paper by Arizona State researcher Jon Pry titled "A Canary in the Crypto Mine," which defeated stack protection in the GPU’s security coprocessor. Academic teams have also spent recent years demonstrating Rowhammer bit flips on Nvidia GPUs and defeating recommended ECC fixes. The common thread across these findings is that the silicon protections often prove less robust than marketing materials suggest.

Kate disclosed the vulnerability to Nvidia’s product security team before publishing her findings. She went public only after another researcher independently discovered the same issue. Nvidia has not issued a public comment on the matter. Because the flaw resides in the physical silicon of chips that have already been manufactured and shipped, there is little Nvidia can do to mitigate the issue for cards already in the field.

For users considering this exploit as a cost-effective route to AI computing power, significant practical caveats remain. Unlocking a single card requires between one and 48 hours of physical rework and per-card tuning. The fuse burns are permanent, meaning any error cannot be reversed. Of the ten cards Kate examined, one had only 64GB of healthy memory rather than the full 80GB, illustrating the variability in yield.

Ken Ashe, an analyst who commented on the work, described the process as "silicon archaeology with a soldering iron." He noted that while one successful hack is impressive, creating ten repeatable cards would constitute infrastructure. The economics of the exploit are also complicated by market volatility. Before software unlocks became available, CMP 170HX cards traded for as little as $250. After word spread about their potential, prices surged past $1,000. In contrast, retail A100s cost near $20,000, but those prices are based on stable supply chains rather than the volatile secondhand market where mining cards are traded.

The research serves as a warning regarding hardware security in an era of component scarcity. It suggests that the locks keeping hidden resources concealed are not as solid as vendors imply, particularly for last-generation hardware that repurposed higher-end die and memory configurations into lower-end packages. The exploit demonstrates that hardware people already own may conceal far more than their vendor cares to admit.

X.So--ThChM