Add HVX IEEE floating-point min/max instructions:
- vfmin_hf, vfmin_sf: IEEE floating-point minimum
- vfmax_hf, vfmax_sf: IEEE floating-point maximum
- vmax_hf, vmax_sf: qfloat IEEE maximum
- vmin_hf, vmin_sf: qfloat IEEE minimum
The Hexagon qfloat variants are similar to the IEEE-754 ones, but they
handle NaN slightly differently. See comment on hvx_ieee_fp.h
Reviewed-by: Taylor Simpson <ltaylorsimpson@gmail.com>
Signed-off-by: Matheus Tavares Bernardino <matheus.bernardino@oss.qualcomm.com>
---
target/hexagon/mmvec/hvx_ieee_fp.h | 6 +++
target/hexagon/attribs_def.h.inc | 2 +
target/hexagon/mmvec/hvx_ieee_fp.c | 50 ++++++++++++++++++++
target/hexagon/hex_common.py | 1 +
target/hexagon/imported/mmvec/encode_ext.def | 10 ++++
target/hexagon/imported/mmvec/ext.idef | 36 +++++++++++++-
6 files changed, 104 insertions(+), 1 deletion(-)
diff --git a/target/hexagon/mmvec/hvx_ieee_fp.h b/target/hexagon/mmvec/hvx_ieee_fp.h
index 75008deb3b..dff2fab14c 100644
--- a/target/hexagon/mmvec/hvx_ieee_fp.h
+++ b/target/hexagon/mmvec/hvx_ieee_fp.h
@@ -15,4 +15,10 @@ float32 fp_mult_sf_hf(float16 a1, float16 a2, float_status *fp_status);
float32 fp_vdmpy(float16 a1, float16 a2, float16 a3, float16 a4,
float_status *fp_status);
+/* Qfloat min/max treat +NaN as greater than +INF and -NaN as smaller than -INF */
+float32 qf_max_sf(float32 a1, float32 a2, float_status *fp_status);
+float32 qf_min_sf(float32 a1, float32 a2, float_status *fp_status);
+float16 qf_max_hf(float16 a1, float16 a2, float_status *fp_status);
+float16 qf_min_hf(float16 a1, float16 a2, float_status *fp_status);
+
#endif
diff --git a/target/hexagon/attribs_def.h.inc b/target/hexagon/attribs_def.h.inc
index d3c4bf6301..2d0fc7e9c0 100644
--- a/target/hexagon/attribs_def.h.inc
+++ b/target/hexagon/attribs_def.h.inc
@@ -81,6 +81,7 @@ DEF_ATTRIB(CVI_SCATTER, "CVI Scatter operation", "", "")
DEF_ATTRIB(CVI_SCATTER_RELEASE, "CVI Store Release for scatter", "", "")
DEF_ATTRIB(CVI_TMP_DST, "CVI instruction that doesn't write a register", "", "")
DEF_ATTRIB(CVI_SLOT23, "Can execute in slot 2 or slot 3 (HVX)", "", "")
+DEF_ATTRIB(CVI_VA_2SRC, "Execs on multimedia vector engine; requires two srcs", "", "")
DEF_ATTRIB(VTCM_ALLBANK_ACCESS, "Allocates in all VTCM schedulers.", "", "")
@@ -179,6 +180,7 @@ DEF_ATTRIB(HVX_IEEE_FP_ACC, "HVX IEEE FP accumulate instruction", "", "")
DEF_ATTRIB(HVX_IEEE_FP_OUT_16, "HVX IEEE FP 16-bit output", "", "")
DEF_ATTRIB(HVX_IEEE_FP_OUT_32, "HVX IEEE FP 32-bit output", "", "")
DEF_ATTRIB(CVI_VX_NO_TMP_LD, "HVX multiply without tmp load", "", "")
+DEF_ATTRIB(HVX_FLT, "This a floating point HVX instruction.", "", "")
/* Keep this as the last attribute: */
DEF_ATTRIB(ZZ_LASTATTRIB, "Last attribute in the file", "", "")
diff --git a/target/hexagon/mmvec/hvx_ieee_fp.c b/target/hexagon/mmvec/hvx_ieee_fp.c
index 3367226998..2ae79a485a 100644
--- a/target/hexagon/mmvec/hvx_ieee_fp.c
+++ b/target/hexagon/mmvec/hvx_ieee_fp.c
@@ -19,3 +19,53 @@ float32 fp_vdmpy(float16 a1, float16 a2, float16 a3, float16 a4,
return float32_add(fp_mult_sf_hf(a1, a3, fp_status),
fp_mult_sf_hf(a2, a4, fp_status), fp_status);
}
+
+#define float32_is_pos_nan(X) (float32_is_any_nan(X) && !float32_is_neg(X))
+#define float32_is_neg_nan(X) (float32_is_any_nan(X) && float32_is_neg(X))
+#define float16_is_pos_nan(X) (float16_is_any_nan(X) && !float16_is_neg(X))
+#define float16_is_neg_nan(X) (float16_is_any_nan(X) && float16_is_neg(X))
+
+/* Qfloat min/max treat +NaN as greater than +INF and -NaN as smaller than -INF */
+float32 qf_max_sf(float32 a1, float32 a2, float_status *fp_status)
+{
+ if (float32_is_pos_nan(a1) || float32_is_neg_nan(a2)) {
+ return a1;
+ }
+ if (float32_is_pos_nan(a2) || float32_is_neg_nan(a1)) {
+ return a2;
+ }
+ return float32_max(a1, a2, fp_status);
+}
+
+float32 qf_min_sf(float32 a1, float32 a2, float_status *fp_status)
+{
+ if (float32_is_pos_nan(a1) || float32_is_neg_nan(a2)) {
+ return a2;
+ }
+ if (float32_is_pos_nan(a2) || float32_is_neg_nan(a1)) {
+ return a1;
+ }
+ return float32_min(a1, a2, fp_status);
+}
+
+float16 qf_max_hf(float16 a1, float16 a2, float_status *fp_status)
+{
+ if (float16_is_pos_nan(a1) || float16_is_neg_nan(a2)) {
+ return a1;
+ }
+ if (float16_is_pos_nan(a2) || float16_is_neg_nan(a1)) {
+ return a2;
+ }
+ return float16_max(a1, a2, fp_status);
+}
+
+float16 qf_min_hf(float16 a1, float16 a2, float_status *fp_status)
+{
+ if (float16_is_pos_nan(a1) || float16_is_neg_nan(a2)) {
+ return a2;
+ }
+ if (float16_is_pos_nan(a2) || float16_is_neg_nan(a1)) {
+ return a1;
+ }
+ return float16_min(a1, a2, fp_status);
+}
diff --git a/target/hexagon/hex_common.py b/target/hexagon/hex_common.py
index 9819201b50..168112c66f 100755
--- a/target/hexagon/hex_common.py
+++ b/target/hexagon/hex_common.py
@@ -216,6 +216,7 @@ def need_env(tag):
"A_CVI_GATHER" in attribdict[tag] or
"A_CVI_SCATTER" in attribdict[tag] or
"A_HVX_IEEE_FP" in attribdict[tag] or
+ "A_HVX_FLT" in attribdict[tag] or
"A_IMPLICIT_WRITES_USR" in attribdict[tag])
diff --git a/target/hexagon/imported/mmvec/encode_ext.def b/target/hexagon/imported/mmvec/encode_ext.def
index 4ce87d09fd..d7f50db778 100644
--- a/target/hexagon/imported/mmvec/encode_ext.def
+++ b/target/hexagon/imported/mmvec/encode_ext.def
@@ -823,4 +823,14 @@ DEF_ENC(V6_vsub_sf_hf,"00011111100vvvvvPP1uuuuu101ddddd")
DEF_ENC(V6_vadd_hf_hf,"00011111101vvvvvPP1uuuuu111ddddd")
DEF_ENC(V6_vsub_hf_hf,"00011111011vvvvvPP1uuuuu000ddddd")
+/* IEEE FP min/max instructions */
+DEF_ENC(V6_vfmin_hf,"00011100011vvvvvPP1uuuuu000ddddd")
+DEF_ENC(V6_vfmin_sf,"00011100011vvvvvPP1uuuuu001ddddd")
+DEF_ENC(V6_vfmax_hf,"00011100011vvvvvPP1uuuuu010ddddd")
+DEF_ENC(V6_vfmax_sf,"00011100011vvvvvPP1uuuuu011ddddd")
+DEF_ENC(V6_vmax_sf,"00011111110vvvvvPP1uuuuu001ddddd")
+DEF_ENC(V6_vmin_sf,"00011111110vvvvvPP1uuuuu010ddddd")
+DEF_ENC(V6_vmax_hf,"00011111110vvvvvPP1uuuuu011ddddd")
+DEF_ENC(V6_vmin_hf,"00011111110vvvvvPP1uuuuu100ddddd")
+
#endif /* NO MMVEC */
diff --git a/target/hexagon/imported/mmvec/ext.idef b/target/hexagon/imported/mmvec/ext.idef
index 14df8e4790..0e9cace203 100644
--- a/target/hexagon/imported/mmvec/ext.idef
+++ b/target/hexagon/imported/mmvec/ext.idef
@@ -43,7 +43,9 @@
EXTINSN(V6_##TAG, SYNTAX, ATTRIBS(A_EXTENSION,A_CVI,A_CVI_VA), \
DESCR, DO_FOR_EACH_CODE(WIDTH, CODE))
-
+#define ITERATOR_INSN_ANY_SLOT_2SRC(WIDTH,TAG,SYNTAX,DESCR,CODE) \
+EXTINSN(V6_##TAG, SYNTAX, ATTRIBS(A_EXTENSION,A_CVI,A_CVI_VA,A_CVI_VA_2SRC,A_HVX_FLT), \
+DESCR, DO_FOR_EACH_CODE(WIDTH, CODE))
#define ITERATOR_INSN2_ANY_SLOT(WIDTH,TAG,SYNTAX,SYNTAX2,DESCR,CODE) \
ITERATOR_INSN_ANY_SLOT(WIDTH,TAG,SYNTAX2,DESCR,CODE)
@@ -3000,6 +3002,38 @@ ITERATOR_INSN_IEEE_FP_DOUBLE_32(32, vsub_sf_hf,
VddV.v[1].sf[i] = float32_sub(f16_to_f32(VuV.hf[2*i+1]),
f16_to_f32(VvV.hf[2*i+1]), &env->hvx_fp_status))
+#define ITERATOR_INSN_IEEE_FP_16_32_LATE(WIDTH,TAG,SYNTAX,DESCR,CODE) \
+EXTINSN(V6_##TAG, SYNTAX, \
+ ATTRIBS(A_EXTENSION,A_HVX_IEEE_FP,A_CVI,A_CVI_VX,A_HVX_IEEE_FP_OUT_16,A_HVX_IEEE_FP_OUT_32), \
+ DESCR, DO_FOR_EACH_CODE(WIDTH, CODE))
+
+/* IEEE FP min/max instructions */
+ITERATOR_INSN_IEEE_FP_16_32_LATE(16, vfmin_hf, "Vd32.hf=vfmin(Vu32.hf,Vv32.hf)", \
+ "Vector IEEE min: hf", VdV.hf[i] = float16_min(VuV.hf[i], VvV.hf[i], \
+ &env->hvx_fp_status))
+ITERATOR_INSN_IEEE_FP_16_32_LATE(32, vfmin_sf, "Vd32.sf=vfmin(Vu32.sf,Vv32.sf)", \
+ "Vector IEEE min: sf", VdV.sf[i] = float32_min(VuV.sf[i], VvV.sf[i], \
+ &env->hvx_fp_status))
+ITERATOR_INSN_IEEE_FP_16_32_LATE(16, vfmax_hf, "Vd32.hf=vfmax(Vu32.hf,Vv32.hf)", \
+ "Vector IEEE max: hf", VdV.hf[i] = float16_max(VuV.hf[i], VvV.hf[i], \
+ &env->hvx_fp_status))
+ITERATOR_INSN_IEEE_FP_16_32_LATE(32, vfmax_sf, "Vd32.sf=vfmax(Vu32.sf,Vv32.sf)", \
+ "Vector IEEE max: sf", VdV.sf[i] = float32_max(VuV.sf[i], VvV.sf[i], \
+ &env->hvx_fp_status))
+
+ITERATOR_INSN_ANY_SLOT_2SRC(32,vmax_sf,"Vd32.sf=vmax(Vu32.sf,Vv32.sf)", \
+ "Vector max of sf input", VdV.sf[i] = qf_max_sf(VuV.sf[i], VvV.sf[i], \
+ &env->hvx_fp_status))
+ITERATOR_INSN_ANY_SLOT_2SRC(32,vmin_sf,"Vd32.sf=vmin(Vu32.sf,Vv32.sf)", \
+ "Vector min of sf input", VdV.sf[i] = qf_min_sf(VuV.sf[i], VvV.sf[i], \
+ &env->hvx_fp_status))
+ITERATOR_INSN_ANY_SLOT_2SRC(16,vmax_hf,"Vd32.hf=vmax(Vu32.hf,Vv32.hf)", \
+ "Vector max of hf input", VdV.hf[i] = qf_max_hf(VuV.hf[i], VvV.hf[i], \
+ &env->hvx_fp_status))
+ITERATOR_INSN_ANY_SLOT_2SRC(16,vmin_hf,"Vd32.hf=vmin(Vu32.hf,Vv32.hf)", \
+ "Vector min of hf input", VdV.hf[i] = qf_min_hf(VuV.hf[i], VvV.hf[i], \
+ &env->hvx_fp_status))
+
/******************************************************************************
DEBUG Vector/Register Printing
******************************************************************************/
--
2.37.2