Does a processor that supports SSE4 support SSSE3 instructions?

Question

I am developing a hardware platform that requires the SSSE3 instruction set. When looking at a processor such as the Intel Atom® x5-Z8350 the datasheet says it has support for SSE4.1 and SSE4.2. Would this allow software written for SSSE3 instructions to function?

I believe this question is slightly different than this question as it never explicitly says SSE4 is a superset of SSSE3. It only says AVX is a superset.

Answer 1

This answer is for Intel processors only.

First, all Intel Atom processors from the earliest ones to the most recent ones support SSSE3. Section 1.2.14 of the Intel manual states:

The initial Intel Atom Processor family and subsequent generations including Intel Atom processor D2000, N2000, E2000, Z2000, C1000 series provide the following features:

• ...
• Support for instruction set extensions up to and including Supplemental Streaming SIMD Extensions 3 (SSSE3).
• ...

And also Table 5-1 of the manual states:

SSSE3 Extensions: Intel Xeon processor 3xxx, 5100, 5200, 5300, 5400, 5500, 5600, 7300, 7400, 7500 series, Intel Core 2 Extreme processors QX6000 series, Intel Core 2 Duo, Intel Core 2 Quad processors, Intel Pentium Dual-Core processors, Intel Atom processors.

This is also consistent with Wikipedia.

I'm not sure whether the manual states explicitly that if SSE4 is supported then SSSE3 is supported, but we can derive that.

Section 12.7.3 discusses how to check for SSSE3 support:

Before an application attempts to use the SSSE3 extensions, the application should follow the steps illustrated in Section 11.6.2, “Checking for SSE/SSE2 Support.” Next, use the additional step provided below:

• Check that the processor supports SSSE3 (if CPUID.01H:ECX.SSSE3[bit 9] = 1).

also Section 12.12.2 discusses how to check for SSE4.1 support:

Check that the processor supports SSE4.1 (if CPUID.01H:ECX.SSE4_1[bit 19] = 1), SSE3 (if CPUID.01H:ECX.SSE3[bit 0] = 1), and SSSE3 (if CPUID.01H:ECX.SSSE3[bit 9] = 1).

and finally Section 12.12.3 discusses how to check for SSE4.2 support:

Check that the processor supports SSE4.2 (if CPUID.01H:ECX.SSE4_2[bit 20] = 1), SSE4.1 (if CPUID.01H:ECX.SSE4_1[bit 19] = 1), and SSSE3 (if CPUID.01H:ECX.SSSE3[bit 9] = 1).

As you can see, both SSE4.1 and SSE4.1 require support for SSSE3. We can also conclude that SSSE3 requires support for SSE2.

CAVEAT: Most likely this will continue to hold in the future, although it's hard to be sure 100%.

One interesting observation though is when comparing the list of processors that support SSSE3 against the lists of those that support SSE4.1 and SSE4.2 (Table 5-1 and Table 5-2), there is only one processor, Intel Core i7 965 processor, that is in the list of SSE4.2 but not SSSE3, yet the processor actually supports SSSE3. Not sure whether this is an error in the manual, or more horrifyingly, it's incomplete.

Another interesting observation is that, for processors other than Atom (see the quote from Section 1.2.14 above), it seems that support for SSSE3, SSE4.1, or SSE4.2 does not necessarily mean that SSE3 is supported. I didn't find anything in the manual that enables me to make that conclusion. At the same time, I don't know of any processor that supports SSSE3, SSE4.1, or SSE4.2, but not SSE3.

Section 12.1.1 specifies which registers are available in SSSE3:

In compatibility mode, SSE3, SSSE3, and SSE4 function like they do in protected mode. In 64-bit mode, eight additional XMM registers are accessible. Registers XMM8-XMM15 are accessed by using REX prefixes.

Section 12.7.1 discusses OS support for SSSE3:

Ensure that your operating system supports SSE/SSE2/SSE3/SSSE3 extensions. (Operating system support for the SSE extensions implies sufficient support for SSE2, SSE3, and SSSE3.)

So any OS that requires SSE automatically supports SSSE3.

Answer 2

I think that "supports" in new processors means "the new" things, while the backward compatibility is mandatory, at least in Intel area - few things may be different for AMD, then lowest common denominator is used in OS code and only low-level kernel variants/paths can be optimized if its really worth. Special/scientific/experimental/media software may state processor ISA required (video rendering, audio DSP FX, etc)