target/arm: Add helper_gvec{_ah}_bfmlsl{_nx}

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-36-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index 8c4705fc539adfea70ee6b3504d1756f4b951ac3..a05b63380cb1a2f3bc7d2196d3a1a79da2c8294a 100644 (file)
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -1095,8 +1095,16 @@ DEF_HELPER_FLAGS_6(gvec_bfmmla, TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmlsl, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_bfmlsl, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmlsl_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_bfmlsl_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)

diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index e8467823f21c2df57686747f3cf66c42b550859c..5dcd6f9282d5a4c1ba75cb821495a0f4d9f8fb37 100644 (file)
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -3186,44 +3186,76 @@ void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va,
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va,
-                         float_status *stat, uint32_t desc)
+static void do_bfmlal(float32 *d, bfloat16 *n, bfloat16 *m, float32 *a,
+                      float_status *stat, uint32_t desc, int negx, int negf)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    intptr_t sel = simd_data(desc);
-    float32 *d = vd, *a = va;
-    bfloat16 *n = vn, *m = vm;
+    intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1);
 
     for (i = 0; i < opr_sz / 4; ++i) {
-        float32 nn = n[H2(i * 2 + sel)] << 16;
+        float32 nn = (negx ^ n[H2(i * 2 + sel)]) << 16;
         float32 mm = m[H2(i * 2 + sel)] << 16;
-        d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], 0, stat);
+        d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], negf, stat);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm,
-                             void *va, float_status *stat, uint32_t desc)
+void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va,
+                         float_status *stat, uint32_t desc)
+{
+    do_bfmlal(vd, vn, vm, va, stat, desc, 0, 0);
+}
+
+void HELPER(gvec_bfmlsl)(void *vd, void *vn, void *vm, void *va,
+                         float_status *stat, uint32_t desc)
+{
+    do_bfmlal(vd, vn, vm, va, stat, desc, 0x8000, 0);
+}
+
+void HELPER(gvec_ah_bfmlsl)(void *vd, void *vn, void *vm, void *va,
+                            float_status *stat, uint32_t desc)
+{
+    do_bfmlal(vd, vn, vm, va, stat, desc, 0, float_muladd_negate_product);
+}
+
+static void do_bfmlal_idx(float32 *d, bfloat16 *n, bfloat16 *m, float32 *a,
+                          float_status *stat, uint32_t desc, int negx, int negf)
 {
     intptr_t i, j, opr_sz = simd_oprsz(desc);
     intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1);
     intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 1, 3);
     intptr_t elements = opr_sz / 4;
     intptr_t eltspersegment = MIN(16 / 4, elements);
-    float32 *d = vd, *a = va;
-    bfloat16 *n = vn, *m = vm;
 
     for (i = 0; i < elements; i += eltspersegment) {
         float32 m_idx = m[H2(2 * i + index)] << 16;
 
         for (j = i; j < i + eltspersegment; j++) {
-            float32 n_j = n[H2(2 * j + sel)] << 16;
-            d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], 0, stat);
+            float32 n_j = (negx ^ n[H2(2 * j + sel)]) << 16;
+            d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], negf, stat);
         }
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
+void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, void *va,
+                             float_status *stat, uint32_t desc)
+{
+    do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0, 0);
+}
+
+void HELPER(gvec_bfmlsl_idx)(void *vd, void *vn, void *vm, void *va,
+                             float_status *stat, uint32_t desc)
+{
+    do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0x8000, 0);
+}
+
+void HELPER(gvec_ah_bfmlsl_idx)(void *vd, void *vn, void *vm, void *va,
+                                float_status *stat, uint32_t desc)
+{
+    do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0, float_muladd_negate_product);
+}
+
 #define DO_CLAMP(NAME, TYPE) \
 void HELPER(NAME)(void *d, void *n, void *m, void *a, uint32_t desc)    \
 {                                                                       \