This argument is no longer used.
Reviewed-by: Philippe Mathieu-Daudé <[email protected]>
Signed-off-by: Richard Henderson <[email protected]>
---
target/arm/tcg/vec_internal.h | 12 +++------
target/arm/tcg/sme_helper.c | 6 ++---
target/arm/tcg/vec_helper.c | 50 +++++++++++++++--------------------
3 files changed, 29 insertions(+), 39 deletions(-)
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index 4edd2b4fc1..c7ccb28b18 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -270,7 +270,6 @@ float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2,
float_status *fpst);
* @sum: addend
* @e1, @e2: multiplicand vectors
* @fpst: floating-point status to use
- * @fpst_odd: floating-point status to use for round-to-odd operations
*
* BFloat16 2-way dot product of @e1 & @e2, accumulating with @sum.
* The @e1 and @e2 operands correspond to the 32-bit source vector
@@ -279,23 +278,20 @@ float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2,
float_status *fpst);
* Corresponds to the ARM pseudocode function BFDotAdd, specialized
* for the FPCR.EBF == 1 case.
*/
-float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2,
- float_status *fpst, float_status *fpst_odd);
+float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2, float_status
*fpst);
/**
* is_ebf:
* @env: CPU state
* @statusp: pointer to floating point status to fill in
- * @oddstatusp: pointer to floating point status to fill in for round-to-odd
*
* Determine whether a BFDotAdd operation should use FPCR.EBF = 0
- * or FPCR.EBF = 1 semantics. On return, has initialized *statusp
- * and *oddstatusp to suitable float_status arguments to use with either
- * bfdotadd() or bfdotadd_ebf().
+ * or FPCR.EBF = 1 semantics. On return, has initialized *statusp as suitable
+ * for float_status arguments to either bfdotadd() or bfdotadd_ebf().
* Returns true for EBF = 1, false for EBF = 0. (The caller should use this
* to decide whether to call bfdotadd() or bfdotadd_ebf().)
*/
-bool is_ebf(CPUARMState *env, float_status *statusp, float_status *oddstatusp);
+bool is_ebf(CPUARMState *env, float_status *statusp);
/*
* Negate as for FPCR.AH=1 -- do not negate NaNs.
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index ab5999c592..0702a1b129 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1435,9 +1435,9 @@ static void do_bfmopa_w(void *vza, void *vzn, void *vzm,
uint32_t desc, uint32_t negx, bool ah_neg)
{
intptr_t row, col, oprsz = simd_maxsz(desc);
- float_status fpst, fpst_odd;
+ float_status fpst;
- if (is_ebf(env, &fpst, &fpst_odd)) {
+ if (is_ebf(env, &fpst)) {
for (row = 0; row < oprsz; ) {
uint16_t prow = pn[H2(row >> 4)];
do {
@@ -1458,7 +1458,7 @@ static void do_bfmopa_w(void *vza, void *vzn, void *vzm,
uint32_t m = *(uint32_t *)(vzm + H1_4(col));
m = f16mop_adj_pair(m, pcol, 0);
- *a = bfdotadd_ebf(*a, n, m, &fpst, &fpst_odd);
+ *a = bfdotadd_ebf(*a, n, m, &fpst);
}
col += 4;
pcol >>= 4;
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 85bcaac3d1..3231bb2100 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -2845,7 +2845,7 @@ DO_MMLA_B(gvec_usmmla_b, do_usmmla_b)
* BFloat16 Dot Product
*/
-bool is_ebf(CPUARMState *env, float_status *statusp, float_status *oddstatusp)
+bool is_ebf(CPUARMState *env, float_status *statusp)
{
/*
* For BFDOT, BFMMLA, etc, the behaviour depends on FPCR.EBF.
@@ -2865,11 +2865,7 @@ bool is_ebf(CPUARMState *env, float_status *statusp,
float_status *oddstatusp)
*statusp = env->vfp.fp_status[is_a64(env) ? FPST_A64 : FPST_A32];
set_default_nan_mode(true, statusp);
- if (ebf) {
- /* EBF=1 needs to do a step with round-to-odd semantics */
- *oddstatusp = *statusp;
- set_float_rounding_mode(float_round_to_odd, oddstatusp);
- } else {
+ if (!ebf) {
set_flush_to_zero(true, statusp);
set_flush_inputs_to_zero(true, statusp);
set_float_rounding_mode(float_round_to_odd_inf, statusp);
@@ -2893,8 +2889,7 @@ float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2,
float_status *fpst)
return t1;
}
-float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2,
- float_status *fpst, float_status *fpst_odd)
+float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2, float_status *fpst)
{
/* Unpack two BFloat16 into two Float32, trivially. */
float32 s1r = e1 << 16;
@@ -2965,11 +2960,11 @@ void HELPER(gvec_bfdot)(void *vd, void *vn, void *vm,
void *va,
intptr_t i, opr_sz = simd_oprsz(desc);
float32 *d = vd, *a = va;
uint32_t *n = vn, *m = vm;
- float_status fpst, fpst_odd;
+ float_status fpst;
- if (is_ebf(env, &fpst, &fpst_odd)) {
+ if (is_ebf(env, &fpst)) {
for (i = 0; i < opr_sz / 4; ++i) {
- d[i] = bfdotadd_ebf(a[i], n[i], m[i], &fpst, &fpst_odd);
+ d[i] = bfdotadd_ebf(a[i], n[i], m[i], &fpst);
}
} else {
for (i = 0; i < opr_sz / 4; ++i) {
@@ -2988,14 +2983,14 @@ void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void
*vm,
intptr_t eltspersegment = MIN(16 / 4, elements);
float32 *d = vd, *a = va;
uint32_t *n = vn, *m = vm;
- float_status fpst, fpst_odd;
+ float_status fpst;
- if (is_ebf(env, &fpst, &fpst_odd)) {
+ if (is_ebf(env, &fpst)) {
for (i = 0; i < elements; i += eltspersegment) {
uint32_t m_idx = m[i + H4(index)];
for (j = i; j < i + eltspersegment; j++) {
- d[j] = bfdotadd_ebf(a[j], n[j], m_idx, &fpst, &fpst_odd);
+ d[j] = bfdotadd_ebf(a[j], n[j], m_idx, &fpst);
}
}
} else {
@@ -3022,17 +3017,16 @@ void HELPER(sme2_bfvdot_idx)(void *vd, void *vn, void
*vm,
uint16_t *n0 = vn;
uint16_t *n1 = vn + sizeof(ARMVectorReg);
uint32_t *m = vm;
- float_status fpst, fpst_odd;
+ float_status fpst;
- if (is_ebf(env, &fpst, &fpst_odd)) {
+ if (is_ebf(env, &fpst)) {
for (i = 0; i < elements; i += eltspersegment) {
uint32_t m_idx = m[i + H4(idx)];
for (j = 0; j < eltspersegment; j++) {
uint32_t nn = (n0[H2(2 * (i + j) + sel)])
| (n1[H2(2 * (i + j) + sel)] << 16);
- d[i + H4(j)] = bfdotadd_ebf(a[i + H4(j)], nn, m_idx,
- &fpst, &fpst_odd);
+ d[i + H4(j)] = bfdotadd_ebf(a[i + H4(j)], nn, m_idx, &fpst);
}
}
} else {
@@ -3055,9 +3049,9 @@ void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm,
void *va,
intptr_t s, opr_sz = simd_oprsz(desc);
float32 *d = vd, *a = va;
uint32_t *n = vn, *m = vm;
- float_status fpst, fpst_odd;
+ float_status fpst;
- if (is_ebf(env, &fpst, &fpst_odd)) {
+ if (is_ebf(env, &fpst)) {
for (s = 0; s < opr_sz / 4; s += 4) {
float32 sum00, sum01, sum10, sum11;
@@ -3069,20 +3063,20 @@ void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm,
void *va,
* i j i k j k
*/
sum00 = a[s + H4(0 + 0)];
- sum00 = bfdotadd_ebf(sum00, n[s + H4(0 + 0)], m[s + H4(0 + 0)],
&fpst, &fpst_odd);
- sum00 = bfdotadd_ebf(sum00, n[s + H4(0 + 1)], m[s + H4(0 + 1)],
&fpst, &fpst_odd);
+ sum00 = bfdotadd_ebf(sum00, n[s + H4(0 + 0)], m[s + H4(0 + 0)],
&fpst);
+ sum00 = bfdotadd_ebf(sum00, n[s + H4(0 + 1)], m[s + H4(0 + 1)],
&fpst);
sum01 = a[s + H4(0 + 1)];
- sum01 = bfdotadd_ebf(sum01, n[s + H4(0 + 0)], m[s + H4(2 + 0)],
&fpst, &fpst_odd);
- sum01 = bfdotadd_ebf(sum01, n[s + H4(0 + 1)], m[s + H4(2 + 1)],
&fpst, &fpst_odd);
+ sum01 = bfdotadd_ebf(sum01, n[s + H4(0 + 0)], m[s + H4(2 + 0)],
&fpst);
+ sum01 = bfdotadd_ebf(sum01, n[s + H4(0 + 1)], m[s + H4(2 + 1)],
&fpst);
sum10 = a[s + H4(2 + 0)];
- sum10 = bfdotadd_ebf(sum10, n[s + H4(2 + 0)], m[s + H4(0 + 0)],
&fpst, &fpst_odd);
- sum10 = bfdotadd_ebf(sum10, n[s + H4(2 + 1)], m[s + H4(0 + 1)],
&fpst, &fpst_odd);
+ sum10 = bfdotadd_ebf(sum10, n[s + H4(2 + 0)], m[s + H4(0 + 0)],
&fpst);
+ sum10 = bfdotadd_ebf(sum10, n[s + H4(2 + 1)], m[s + H4(0 + 1)],
&fpst);
sum11 = a[s + H4(2 + 1)];
- sum11 = bfdotadd_ebf(sum11, n[s + H4(2 + 0)], m[s + H4(2 + 0)],
&fpst, &fpst_odd);
- sum11 = bfdotadd_ebf(sum11, n[s + H4(2 + 1)], m[s + H4(2 + 1)],
&fpst, &fpst_odd);
+ sum11 = bfdotadd_ebf(sum11, n[s + H4(2 + 0)], m[s + H4(2 + 0)],
&fpst);
+ sum11 = bfdotadd_ebf(sum11, n[s + H4(2 + 1)], m[s + H4(2 + 1)],
&fpst);
d[s + H4(0 + 0)] = sum00;
d[s + H4(0 + 1)] = sum01;
--
2.43.0
