target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-53-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 0bb8af194b397f3c8ae63eafee1272fd8c1919b4..97e70959e8afd3ca89c944b5b6ba493f92402f4f 100644 (file)
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -212,3 +212,8 @@ DEF_HELPER_FLAGS_5(sme2_umlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr,
 DEF_HELPER_FLAGS_5(sme2_umlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sme2_usmlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sme2_sumlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_bfcvt, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_bfcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_fcvt_n, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_fcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 22e2a68b1b9361378381346f34575ec5d13437a2..831179c0eedde64963238a4a26f4c9e01a6fd42c 100644 (file)
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -720,3 +720,15 @@ SUB_aaz_s       11000001 101 000000 .. 111 ....0 11 ...     @az_2x2_o3
 SUB_aaz_s       11000001 101 000010 .. 111 ...00 11 ...     @az_4x4_o3
 SUB_aaz_d       11000001 111 000000 .. 111 ....0 11 ...     @az_2x2_o3
 SUB_aaz_d       11000001 111 000010 .. 111 ...00 11 ...     @az_4x4_o3
+
+### SME2 Multi-vector SVE Constructive Unary
+
+&zz_n           zd zn n
+@zz_1x2         ........ ... ..... ...... ..... zd:5        \
+                &zz_n n=1 zn=%zn_ax2
+
+BFCVT           11000001 011 00000 111000 ....0 .....       @zz_1x2
+BFCVTN          11000001 011 00000 111000 ....1 .....       @zz_1x2
+
+FCVT_n          11000001 001 00000 111000 ....0 .....       @zz_1x2
+FCVTN           11000001 001 00000 111000 ....1 .....       @zz_1x2

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 0f79d7cb6e358914d1e5c7080f012a0b6568cfae..d97afdb69cf62b2c69a2f6e6b003643a4f9489c6 100644 (file)
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1517,3 +1517,77 @@ DO_MLALL_IDX(sme2_usmlall_idx_s, uint32_t, uint8_t, int8_t, H4, H1, +)
 DO_MLALL_IDX(sme2_sumlall_idx_s, uint32_t, int8_t, uint8_t, H4, H1, +)
 
 #undef DO_MLALL_IDX
+
+/* Convert and compress */
+void HELPER(sme2_bfcvt)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+    ARMVectorReg scratch;
+    size_t oprsz = simd_oprsz(desc);
+    size_t i, n = oprsz / 4;
+    float32 *s0 = vs;
+    float32 *s1 = vs + sizeof(ARMVectorReg);
+    bfloat16 *d = vd;
+
+    if (vd == s1) {
+        s1 = memcpy(&scratch, s1, oprsz);
+    }
+
+    for (i = 0; i < n; ++i) {
+        d[H2(i)] = float32_to_bfloat16(s0[H4(i)], fpst);
+    }
+    for (i = 0; i < n; ++i) {
+        d[H2(i) + n] = float32_to_bfloat16(s1[H4(i)], fpst);
+    }
+}
+
+void HELPER(sme2_fcvt_n)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+    ARMVectorReg scratch;
+    size_t oprsz = simd_oprsz(desc);
+    size_t i, n = oprsz / 4;
+    float32 *s0 = vs;
+    float32 *s1 = vs + sizeof(ARMVectorReg);
+    float16 *d = vd;
+
+    if (vd == s1) {
+        s1 = memcpy(&scratch, s1, oprsz);
+    }
+
+    for (i = 0; i < n; ++i) {
+        d[H2(i)] = sve_f32_to_f16(s0[H4(i)], fpst);
+    }
+    for (i = 0; i < n; ++i) {
+        d[H2(i) + n] = sve_f32_to_f16(s1[H4(i)], fpst);
+    }
+}
+
+/* Convert and interleave */
+void HELPER(sme2_bfcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+    size_t i, n = simd_oprsz(desc) / 4;
+    float32 *s0 = vs;
+    float32 *s1 = vs + sizeof(ARMVectorReg);
+    bfloat16 *d = vd;
+
+    for (i = 0; i < n; ++i) {
+        bfloat16 d0 = float32_to_bfloat16(s0[H4(i)], fpst);
+        bfloat16 d1 = float32_to_bfloat16(s1[H4(i)], fpst);
+        d[H2(i * 2 + 0)] = d0;
+        d[H2(i * 2 + 1)] = d1;
+    }
+}
+
+void HELPER(sme2_fcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+    size_t i, n = simd_oprsz(desc) / 4;
+    float32 *s0 = vs;
+    float32 *s1 = vs + sizeof(ARMVectorReg);
+    bfloat16 *d = vd;
+
+    for (i = 0; i < n; ++i) {
+        bfloat16 d0 = sve_f32_to_f16(s0[H4(i)], fpst);
+        bfloat16 d1 = sve_f32_to_f16(s1[H4(i)], fpst);
+        d[H2(i * 2 + 0)] = d0;
+        d[H2(i * 2 + 1)] = d1;
+    }
+}

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index a2c363a4e17387170b35a752b4b2d4501d95d83c..b522ddaf7cb3aee8b39626ef136d4252d20b5f88 100644 (file)
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4576,7 +4576,7 @@ static inline float64 sve_f16_to_f64(float16 f, float_status *fpst)
     return ret;
 }
 
-static inline float16 sve_f32_to_f16(float32 f, float_status *fpst)
+float16 sve_f32_to_f16(float32 f, float_status *fpst)
 {
     bool save = get_flush_to_zero(fpst);
     float16 ret;

diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 4c3b9aa7d6ce6ed92a34d84f0ec86568101c3e9d..10e5b77040ebcc15dea78fbcdedfda5e9e9ef957 100644 (file)
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1335,3 +1335,28 @@ TRANS_FEAT(SMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlal
 TRANS_FEAT(SMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_d)
 TRANS_FEAT(UMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlall_idx_d)
 TRANS_FEAT(UMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_d)
+
+static bool do_zz_fpst(DisasContext *s, arg_zz_n *a, int data,
+                       ARMFPStatusFlavour type, gen_helper_gvec_2_ptr *fn)
+{
+    if (sme_sm_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        TCGv_ptr fpst = fpstatus_ptr(type);
+
+        for (int i = 0, n = a->n; i < n; ++i) {
+            tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd + i),
+                               vec_full_reg_offset(s, a->zn + i),
+                               fpst, svl, svl, data, fn);
+        }
+    }
+    return true;
+}
+
+TRANS_FEAT(BFCVT, aa64_sme2, do_zz_fpst, a, 0,
+           FPST_A64, gen_helper_sme2_bfcvt)
+TRANS_FEAT(BFCVTN, aa64_sme2, do_zz_fpst, a, 0,
+           FPST_A64, gen_helper_sme2_bfcvtn)
+TRANS_FEAT(FCVT_n, aa64_sme2, do_zz_fpst, a, 0,
+           FPST_A64, gen_helper_sme2_fcvt_n)
+TRANS_FEAT(FCVTN, aa64_sme2, do_zz_fpst, a, 0,
+           FPST_A64, gen_helper_sme2_fcvtn)

diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index 64a7249d017a0714c02a68a9960137c01d4e40ad..c8199a3ef8ec0e881ed7ec5479261e2dc47360b1 100644 (file)
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -306,4 +306,6 @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah)
 bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst);
 bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst);
 
+float16 sve_f32_to_f16(float32 f, float_status *fpst);
+
 #endif /* TARGET_ARM_VEC_INTERNAL_H */