Supported Hardware
gfx1030 is the LLVM target name for AMD’s Navi 21 GPU (RDNA2 generation, codename
Sienna Cichlid). Several retail and workstation cards use this die and therefore report themselves
as gfx1030.
Cards that natively report as gfx1030
| Card | Architecture | VRAM | Compute Units | Notes |
|---|---|---|---|---|
| Radeon RX 6950 XT | RDNA2 / Navi 21 | 16 GB GDDR6 | 80 | No ECC |
| Radeon RX 6900 XT | RDNA2 / Navi 21 | 16 GB GDDR6 | 80 | No ECC |
| Radeon RX 6800 XT | RDNA2 / Navi 21 | 16 GB GDDR6 | 72 | Same CU count as V620; 16 GB, no ECC |
| Radeon RX 6800 | RDNA2 / Navi 21 | 16 GB GDDR6 | 60 | No ECC |
| Radeon PRO W6800 | RDNA2 / Navi 21 | 32 GB GDDR6 | 60 | ECC on by default (~30 GB visible) |
| Radeon PRO V620 | RDNA2 / Navi 21 | 32 GB GDDR6 | 72 | Data-center; ECC on by default (~30 GB visible) |
Pro cards hide ~2 GB behind ECC. See Disabling ECC if you want the full 32 GB.
Do not flash W6800 VBIOS onto a V620.
#general(Sep 2026): pre-modded eBay cards and DIY flashes that load a W6800 BIOS on a V620 drop active CUs from 72 → 54 (W6800’s different CU layout). That is a large compute hit — stay on stock V620 BIOS. Cooling shroud mods are fine; BIOS swaps are not a free “Pro unlock.”Need OverDrive / unlocked clocks in a passthrough VM without flashing? Prefer the reversible 4-byte PowerPlay soft unlock (
Tamalero/amd-v620-soft-unlock) over a W6800 flash — see Power tuning → Soft unlock.
All of these are on the officially supported list for recent ROCm releases on Linux.
AMD BC-250 (gfx1013)
Headless mining APU board (Cyan Skillfish). RDNA2, reports as gfx1013 — not Navi 21 / gfx1030.
Community ROCm and Vulkan work exists; most of this wiki still targets Navi 21.
| Card | Architecture | VRAM | Compute Units | Notes |
|---|---|---|---|---|
| AMD BC-250 | RDNA2 / Cyan Skillfish | 16 GB GDDR6 UMA | 24 (40 unlocked) |
Community references: AMD BC-250 docs, akandr/bc250-rocm.
RDNA2 relatives that can run gfx1030 code
The rest of the RDNA2 line uses a different LLVM target but shares the same ISA family. They are not
on the official support matrix, but in practice they run gfx1030 kernels once you set
HSA_OVERRIDE_GFX_VERSION=10.3.0 (see HSA_OVERRIDE for RDNA2 Cousins).
| Card | LLVM target | Die |
|---|---|---|
| RX 6750 XT / 6700 XT / 6700 | gfx1031 | Navi 22 |
| RX 6650 XT / 6600 XT / 6600 | gfx1032 | Navi 23 |
| RX 6500 XT / 6400 | gfx1034 | Navi 24 |
| Ryzen 6000/7000 iGPU (RDNA2) | gfx1035 / gfx1036 | Rembrandt / Phoenix |
Architecture highlights (Navi 21)
- RDNA2 compute units with a native wavefront size of 32 (wave32), unlike GCN’s wave64.
- Infinity Cache (128 MB on Navi 21) that dramatically raises effective memory bandwidth.
- No dedicated matrix/tensor cores — RDNA2 predates the WMMA/matrix instructions added in RDNA3
(
gfx11xx). Matrix math runs on the regular vector ALUs, so expect lower peak throughput than RDNA3 or CDNA cards, but very good price/performance for inference. - FP16 is well supported; BF16 has limited/emulated support and is best avoided for hot paths
(prefer
float16).
How to check your GPU target
rocminfo | grep -i 'gfx\|Name'
# or, more directly:
rocminfo | grep -m1 -o 'gfx[0-9]*'
If the output shows gfx1030, everything in this wiki applies directly. If it shows gfx1031,
gfx1032, etc., head to HSA_OVERRIDE for RDNA2 Cousins first.