target/arm: Implement MVE VMAXNMA and VMINNMA

Implement the MVE VMAXNMA and VMINNMA insns; these are 2-operand, but
the destination register must be the same as one of the source
registers.

We defer the decode of the size in bit 28 to the individual insn
patterns rather than doing it in the format, because otherwise we
would have a single insn pattern that overlapped with two groups (eg
VMAXNMA with the VMULH_S and VMULH_U groups). Having two insn
patterns per insn seems clearer than a complex multilevel nesting
of overlapping and non-overlapping groups.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 42 insertions, 0 deletions

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 7395040..57ab3f7 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -428,6 +428,12 @@ DEF_HELPER_FLAGS_4(mve_vmaxnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vminnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vminnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vmaxnmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vmaxnmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vminnmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vminnmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
 DEF_HELPER_FLAGS_4(mve_vfcadd90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vfcadd90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 403381e..b0622e1 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -130,6 +130,11 @@
 @2op_fp_size_rev .... .... .... .... .... .... .... .... &2op \
                  qd=%qd qn=%qn qm=%qm size=%2op_fp_size_rev
 
+# 2-operand, but Qd and Qn share a field. Size is in bit 28, but we
+# don't decode it in this format
+@vmaxnma  .... .... .... .... .... .... .... .... &2op \
+          qd=%qd qn=%qd qm=%qm
+
 # Vector loads and stores
 
 # Widening loads and narrowing stores:
@@ -199,6 +204,8 @@ VMUL             1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op
 # The VSHLL T2 encoding is not a @2op pattern, but is here because it
 # overlaps what would be size=0b11 VMULH/VRMULH
 {
+  VMAXNMA        111 0 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=2
+
   VSHLL_BS       111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b
   VSHLL_BS       111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h
 
@@ -211,6 +218,8 @@ VMUL             1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op
 }
 
 {
+  VMAXNMA        111 1 1110 0 . 11  1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=1
+
   VSHLL_BU       111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b
   VSHLL_BU       111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h
 
@@ -221,6 +230,7 @@ VMUL             1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op
 }
 
 {
+  VMINNMA        111 0 1110 0 . 11  1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=2
   VSHLL_TS       111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b
   VSHLL_TS       111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h
 
@@ -233,6 +243,7 @@ VMUL             1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op
 }
 
 {
+  VMINNMA        111 1 1110 0 . 11  1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=1
   VSHLL_TU       111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b
   VSHLL_TU       111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h
 
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index e478408..a6ad894 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -2855,6 +2855,29 @@ DO_2OP_FP_ALL(vfabd, abd)
 DO_2OP_FP_ALL(vmaxnm, maxnum)
 DO_2OP_FP_ALL(vminnm, minnum)
 
+static inline float16 float16_maxnuma(float16 a, float16 b, float_status *s)
+{
+    return float16_maxnum(float16_abs(a), float16_abs(b), s);
+}
+
+static inline float32 float32_maxnuma(float32 a, float32 b, float_status *s)
+{
+    return float32_maxnum(float32_abs(a), float32_abs(b), s);
+}
+
+static inline float16 float16_minnuma(float16 a, float16 b, float_status *s)
+{
+    return float16_minnum(float16_abs(a), float16_abs(b), s);
+}
+
+static inline float32 float32_minnuma(float32 a, float32 b, float_status *s)
+{
+    return float32_minnum(float32_abs(a), float32_abs(b), s);
+}
+
+DO_2OP_FP_ALL(vmaxnma, maxnuma)
+DO_2OP_FP_ALL(vminnma, minnuma)
+
 #define DO_VCADD_FP(OP, ESIZE, TYPE, FN0, FN1)                          \
     void HELPER(glue(mve_, OP))(CPUARMState *env,                       \
                                 void *vd, void *vn, void *vm)           \
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index d62ed1f..4d702da 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -864,6 +864,8 @@ DO_2OP_FP(VCMLA0, vcmla0)
 DO_2OP_FP(VCMLA90, vcmla90)
 DO_2OP_FP(VCMLA180, vcmla180)
 DO_2OP_FP(VCMLA270, vcmla270)
+DO_2OP_FP(VMAXNMA, vmaxnma)
+DO_2OP_FP(VMINNMA, vminnma)
 
 static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
                           MVEGenTwoOpScalarFn fn)