Scalar Single-precision (float) |
Scalar Double-precision (double) |
Packed Single-precision (4 floats) |
Packed Double-precision (2 doubles) |
Comments |
|
add |
addss |
addsd |
addps |
addpd |
sub, mul, div all work the same way |
min |
minss |
minsd |
minps |
minpd |
max works the same way |
sqrt |
sqrtss |
sqrtsd |
sqrtps |
sqrtpd |
Square root (sqrt), reciprocal (rcp), and reciprocal-square-root (rsqrt) all work the same way |
mov |
movss |
movsd |
movaps (aligned) movups (unaligned) |
movapd (aligned) movupd (unaligned) |
Aligned loads are up to 4x
faster, but will crash if given an unaligned address! Stack is always
16-byte aligned specifically for this instruction. Use "align 16" directive for static data. |
cvt | cvtss2sd cvtss2si cvttss2si |
cvtsd2ss cvtsd2si cvttsd2si |
cvtps2pd cvtps2dq cvttps2dq |
cvtpd2ps cvtpd2dq cvttpd2dq |
Convert to ("2", get it?) Single
Integer (si, stored in register like eax) or four DWORDs (dq, stored in
xmm register). "cvtt" versions do truncation (round down); "cvt"
versions round to nearest. |
com |
ucomiss |
ucomisd |
n/a |
n/a |
Sets CPU flags like normal x86 "cmp" instruction, from SSE registers. |
cmp |
cmpeqss |
cmpeqsd |
cmpeqps |
cmpeqpd |
Compare for equality ("lt",
"le", "neq", "nlt", "nle" versions work the same way). Sets all bits
of float to zero if false (0.0), or all bits to ones if true (a NaN).
Result is used as a bitmask for the bitwise AND and OR operations. |
and |
n/a |
n/a |
andps andnps |
andpd andnpd |
Bitwise AND operation. "andn"
versions are bitwise AND-NOT operations (A=(~A) & B). "or"
version works the same way. |
movss xmm3,[pi]; load up constantIt's annoyingly tricky to display full floating-point values. The trouble here is that our function "foo" returns an int to main, so we have to call a function to print floating-point values. Also, with SSE floating-point, on a 64-bit machine you're supposed to keep the stack aligned to a 16-byte boundary (the SSE "movaps" instruction crashes if it's not given a 16-byte aligned value). Sadly, the "call" instruction messes up your stack's alignment by pushing an 8-byte return address, so we've got to use up another 8 bytes of stack space purely for stack alignment, like this.
addss xmm3,xmm3 ; add pi to itself
cvtss2si eax,xmm3 ; round to integer
ret
section .data
pi: dd 3.14159265358979 ; constant
movss xmm3,[pi]; load up constant
addss xmm3,xmm3 ; add pi to itself
movss [output],xmm3; write register out to memory
; Print floating-point output
mov rdi,output ; first parameter: pointer to floats
mov rsi,1 ; second parameter: number of floats
sub rsp,8 ; keep stack 16-byte aligned (else get crash!)
extern farray_print
call farray_print
add rsp,8
ret
section .data
pi: dd 3.14159265358979 ; constant
output: dd 0.0 ; overwritten at runtime
enum {n=4};Unrolling the inner loop, as ugly as it is, speeds things up substantially, to 26ns:
float mat[n][n];
float vec[n];
float outvector[n];
int foo(void) {
for (int row=0;row<4;row++) {
float sum=0.0;
for (int col=0;col<n;col++) {
float m=mat[row][col];
float v=vec[col];
sum+=m*v;
}
outvector[row]=sum;
}
return 0;
}
enum {n=4};Making a line-by-line transformation to SSE doesn't really buy any performance, at 25ns:
float mat[n][n];
float vec[n];
float outvector[n];
int foo(void) {
for (int row=0;row<4;row++) {
float sum=0.0, m,v;
m=mat[row][0];
v=vec[0];
sum+=m*v;
m=mat[row][1];
v=vec[1];
sum+=m*v;
m=mat[row][2];
v=vec[2];
sum+=m*v;
m=mat[row][3];
v=vec[3];
sum+=m*v;
outvector[row]=sum;
}
return 0;
}
#include <pmmintrin.h>The trouble here is that we can cheaply operate on 4-vectors, but summing up the elements of those 4-vectors (with the hadd instruction) is expensive. We can eliminate that horizontal summation by operating on columns, although now we need a new matrix layout. This is down to 19ns on a Pentium 4, and just 12ns on the Q6600!
enum {n=4};
__m128 mat[n]; /* rows */
__m128 vec;
float outvector[n];
int foo(void) {
for (int row=0;row<n;row++) {
__m128 mrow=mat[row];
__m128 v=vec;
__m128 sum=mrow*v;
sum=_mm_hadd_ps(sum,sum); /* adds adjacent-two floats */
_mm_store_ss(&outvector[row],_mm_hadd_ps(sum,sum)); /* adds those floats */
}
return 0;
}
#include <xmmintrin.h>
enum {n=4};
__m128 mat[n]; /* by column */
float vec[n];
__m128 outvector;
int foo(void) {
float z=0.0;
__m128 sum=_mm_load1_ps(&z);
for (int col=0;col<n;col++) {
__m128 mcol=mat[col];
float v=vec[col];
sum+=mcol*_mm_load1_ps(&v);
}
outvector=sum;
return 0;
}