Athlon 64 Family (90–130 nm) These processors were the first AMD CPUs to use the "FX" designation and identified the chip as being higher-performance. The frequency multiplier was unlocked in these chips.
SledgeHammer Core (130 nm) •
Socket 940 • L1 cache: 64 kb + 64 kb (data + instruction) • L2 cache: 1024 kb (full speed) • Instruction sets:
MMX,
SSE,
SSE2,
Enhanced 3DNow!,
NX bit,
AMD64 FX-51 (2.2 GHz) and FX-53 (2.4 GHz)
ClawHammer Core (130 nm) •
Socket 939 • L1 cache: 64 kb + 64 kb (data + instruction) • L2 cache: 1024 kb (full speed) • Instruction sets:
MMX,
SSE,
SSE2,
Enhanced 3DNow!,
NX bit,
AMD64 FX-53 (2.4 GHz) and FX-55 (2.6 GHz)
SanDiego Core (90 nm) •
Socket 939 • L1 cache: 64 kb + 64 kb (data + instruction) • L2 cache: 1024 kb (full speed) • Instruction sets:
MMX,
SSE,
SSE2,
SSE3,
Enhanced 3DNow!,
NX bit,
AMD64,
Cool'n'Quiet FX-55 (2.6 GHz) and FX-57 (2.8 GHz)
Toledo Core (90 nm, dual-core) •
Socket 939 • L1 cache (per core): 64 kb + 64 kb (data + instruction) • L2 cache (per core): 1024 kb (full speed) • Instruction sets:
MMX,
SSE,
SSE2,
SSE3,
Enhanced 3DNow!,
NX bit,
AMD64,
Cool'n'Quiet FX-60 (2.6 GHz)
Windsor Core (90 nm, dual-core) •
Socket AM2 • L1 cache (per core): 64 kb + 64 kb (data + instruction) • L2 cache (per core): 1024 kb (full speed) • Instruction sets:
MMX,
SSE,
SSE2,
SSE3,
Enhanced 3DNow!,
NX bit,
AMD64,
Cool'n'Quiet,
AMD-V FX-62 (2.8 GHz)
Windsor Core (90 nm, dual-core, dual-processor) •
Socket F • L1 cache (per core): 64 kb + 64 kb (data + instruction) • L2 cache (per core): 1024 kb (full speed) • Instruction sets:
MMX,
SSE,
SSE2,
SSE3,
Enhanced 3DNow!,
NX bit,
AMD64,
Cool'n'Quiet,
AMD-V FX-70 (2.6 GHz), FX-72 (2.8 GHz), FX-74 (3.0 GHz)
Bulldozer Family (32 nm) • All models
binned from 8 logical cores with simple OROCHI die production, in 938 pins μPGA package
AM3+ socket. • All AMD FX microprocessors are unlocked and overclockable. • Two Integers-Clusters (seen as logical cores from OS) in each Bulldozer
Module. • 4 Bulldozer modules within FX-8 series, 3 in FX-6 series, and 2 in FX-4 series. • All models support up to 4
DIMMs of
DDR3-1866 memory.
Bulldozer Core (Zambezi, 32 nm) • Codenamed:
Zambezi • Transistors: ~1.6 billion (real node count) •
Die size: 319 mm2 (real measured up size) • L1 data cache (per core): 16 kb • L1 instruction cache (per module): 64 kb • L2 cache (per module): 2048 kb • All models support:
MMX(+),
SSE1 -
2 -
3 -
3s -
4.1 -
4.2 -
4a,
NX bit,
AMD64,
AMD-V,
IOMMU,
AES,
CLMUL,
AVX,
XOP,
FMA4,
F16C,
ABM,
Turbo Core 2.0,
PowerNow!,
ECC Piledriver Core (Vishera, 32 nm) • Codenamed:
Vishera • L1 data cache (per core): 16 kb • L1 instruction cache (per module): 64 kb • L2 cache (per module): 2048 kb • All models support:
MMX(+),
SSE1 -
2 -
3 -
3s -
4.1 -
4.2 -
4a,
NX bit,
AMD64,
AMD-V,
IOMMU,
AES,
CLMUL,
AVX,
AVX 1.1,
XOP,
FMA3,
FMA4,
F16C,
ABM,
BMI1,
TBM,
Turbo Core 3.0,
PowerNow!, EVP (Enhanced Virus Protection),
ECC == Notes ==