Re: [Qemu-devel] [PATCH] target-i386: add Intel AVX-512 support

[Chao Peng <chao.p.peng@linux.intel.com>]

On Thu, Oct 23, 2014 at 05:49:23PM -0200, Eduardo Habkost wrote:
> On Thu, Oct 23, 2014 at 11:02:43AM +0800, Chao Peng wrote:
> [...]
> > @@ -707,6 +714,24 @@ typedef union {
> >  } XMMReg;
> >  
> >  typedef union {
> > +    uint8_t _b[32];
> > +    uint16_t _w[16];
> > +    uint32_t _l[8];
> > +    uint64_t _q[4];
> > +    float32 _s[8];
> > +    float64 _d[4];
> > +} YMMReg;
> > +
> > +typedef union {
> > +    uint8_t _b[64];
> > +    uint16_t _w[32];
> > +    uint32_t _l[16];
> > +    uint64_t _q[8];
> > +    float32 _s[16];
> > +    float64 _d[8];
> > +} ZMMReg;
> > +
> > +typedef union {
> >      uint8_t _b[8];
> >      uint16_t _w[4];
> >      uint32_t _l[2];
> > @@ -725,6 +750,20 @@ typedef struct BNDCSReg {
> >  } BNDCSReg;
> >  
> >  #ifdef HOST_WORDS_BIGENDIAN
> > +#define ZMM_B(n) _b[63 - (n)]
> > +#define ZMM_W(n) _w[31 - (n)]
> > +#define ZMM_L(n) _l[15 - (n)]
> > +#define ZMM_S(n) _s[15 - (n)]
> > +#define ZMM_Q(n) _q[7 - (n)]
> > +#define ZMM_D(n) _d[7 - (n)]
> > +
> > +#define YMM_B(n) _b[31 - (n)]
> > +#define YMM_W(n) _w[15 - (n)]
> > +#define YMM_L(n) _l[7 - (n)]
> > +#define YMM_S(n) _s[7 - (n)]
> > +#define YMM_Q(n) _q[3 - (n)]
> > +#define YMM_D(n) _d[3 - (n)]
> > +
> >  #define XMM_B(n) _b[15 - (n)]
> >  #define XMM_W(n) _w[7 - (n)]
> >  #define XMM_L(n) _l[3 - (n)]
> > @@ -737,6 +776,20 @@ typedef struct BNDCSReg {
> >  #define MMX_L(n) _l[1 - (n)]
> >  #define MMX_S(n) _s[1 - (n)]
> >  #else
> > +#define ZMM_B(n) _b[n]
> > +#define ZMM_W(n) _w[n]
> > +#define ZMM_L(n) _l[n]
> > +#define ZMM_S(n) _s[n]
> > +#define ZMM_Q(n) _q[n]
> > +#define ZMM_D(n) _d[n]
> > +
> > +#define YMM_B(n) _b[n]
> > +#define YMM_W(n) _w[n]
> > +#define YMM_L(n) _l[n]
> > +#define YMM_S(n) _s[n]
> > +#define YMM_Q(n) _q[n]
> > +#define YMM_D(n) _d[n]
> > +
> 
> I am probably not being able to see some future use case of those data
> structures, but: why all the extra complexity here, if only ZMM_Q and
> YMM_Q are being used in the code, and the only place affected by the
> ordering of YMMReg and ZMMReg array elements are the memcpy() calls on
> kvm_{put,get}_xsave(), where the data always have the same layout?
> 

Thanks Eduardo, then I feel comfortable to drop most of these macros and
only keep YMM_Q/ZMM_Q left. As no acutal benefit for ordering, then I
will also make these two endiness-insensitive.

Chao