riscv
/
qemu
mirror of https://gitea.goldendeliverer.com/riscv/qemu.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

target/i386: DPPS rounding fix 

The DPPS (Dot Product) instruction is defined to first sum pairs of
intermediate results, then sum those values to get the final result.
i.e. (A+B)+(C+D)

We incrementally sum the results, i.e. ((A+B)+C)+D, which can result
in incorrect rouding.

For consistency, also change the variable names to the ones used
in the Intel SDM and implement DPPD following the manual.

Based on a patch by Paul Brook <paul@nowt.org>.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
pull/220/head
Paolo Bonzini 4 years ago
parent
75046ad72e
commit
bf30ad8cef
1 changed files with 35 additions and 32 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 67
      target/i386/ops_sse.h

67
target/i386/ops_sse.h
View File

@ -1943,56 +1943,59 @@ SSE_HELPER_I(helper_pblendw, W, 8, FBLENDP)
void glue(helper_dpps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
{
float32 iresult = float32_zero;
float32 prod1, prod2, temp2, temp3, temp4;
/*
* We must evaluate (A+B)+(C+D), not ((A+B)+C)+D
* to correctly round the intermediate results
*/
if (mask & (1 << 4)) {
iresult = float32_add(iresult,
float32_mul(d->ZMM_S(0), s->ZMM_S(0),
&env->sse_status),
&env->sse_status);
prod1 = float32_mul(d->ZMM_S(0), s->ZMM_S(0), &env->sse_status);
} else {
prod1 = float32_zero;
}
if (mask & (1 << 5)) {
iresult = float32_add(iresult,
float32_mul(d->ZMM_S(1), s->ZMM_S(1),
&env->sse_status),
&env->sse_status);
prod2 = float32_mul(d->ZMM_S(1), s->ZMM_S(1), &env->sse_status);
} else {
prod2 = float32_zero;
}
temp2 = float32_add(prod1, prod2, &env->sse_status);
if (mask & (1 << 6)) {
iresult = float32_add(iresult,
float32_mul(d->ZMM_S(2), s->ZMM_S(2),
&env->sse_status),
&env->sse_status);
prod1 = float32_mul(d->ZMM_S(2), s->ZMM_S(2), &env->sse_status);
} else {
prod1 = float32_zero;
}
if (mask & (1 << 7)) {
iresult = float32_add(iresult,
float32_mul(d->ZMM_S(3), s->ZMM_S(3),
&env->sse_status),
&env->sse_status);
prod2 = float32_mul(d->ZMM_S(3), s->ZMM_S(3), &env->sse_status);
} else {
prod2 = float32_zero;
}
d->ZMM_S(0) = (mask & (1 << 0)) ? iresult : float32_zero;
d->ZMM_S(1) = (mask & (1 << 1)) ? iresult : float32_zero;
d->ZMM_S(2) = (mask & (1 << 2)) ? iresult : float32_zero;
d->ZMM_S(3) = (mask & (1 << 3)) ? iresult : float32_zero;
temp3 = float32_add(prod1, prod2, &env->sse_status);
temp4 = float32_add(temp2, temp3, &env->sse_status);
d->ZMM_S(0) = (mask & (1 << 0)) ? temp4 : float32_zero;
d->ZMM_S(1) = (mask & (1 << 1)) ? temp4 : float32_zero;
d->ZMM_S(2) = (mask & (1 << 2)) ? temp4 : float32_zero;
d->ZMM_S(3) = (mask & (1 << 3)) ? temp4 : float32_zero;
}
void glue(helper_dppd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
{
float64 iresult = float64_zero;
float64 prod1, prod2, temp2;
if (mask & (1 << 4)) {
iresult = float64_add(iresult,
float64_mul(d->ZMM_D(0), s->ZMM_D(0),
&env->sse_status),
&env->sse_status);
prod1 = float64_mul(d->ZMM_D(0), s->ZMM_D(0), &env->sse_status);
} else {
prod1 = float64_zero;
}
if (mask & (1 << 5)) {
iresult = float64_add(iresult,
float64_mul(d->ZMM_D(1), s->ZMM_D(1),
&env->sse_status),
&env->sse_status);
prod2 = float64_mul(d->ZMM_D(1), s->ZMM_D(1), &env->sse_status);
} else {
prod2 = float64_zero;
}
d->ZMM_D(0) = (mask & (1 << 0)) ? iresult : float64_zero;
d->ZMM_D(1) = (mask & (1 << 1)) ? iresult : float64_zero;
temp2 = float64_add(prod1, prod2, &env->sse_status);
d->ZMM_D(0) = (mask & (1 << 0)) ? temp2 : float64_zero;
d->ZMM_D(1) = (mask & (1 << 1)) ? temp2 : float64_zero;
}
void glue(helper_mpsadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,

Write Preview
Loading…
Cancel
Save