target/arm: Implement F1CVTL, F1CVTL2, F2CVTL, F2CVTL2 for AdvSIMD

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260609192110.752384-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index e30c7e5ca9f61e5c59822f3e0c8d211971f97740..3c806259f91d0b2a19622899a718e90c24c4be34 100644 (file)
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -1921,6 +1921,9 @@ URSQRTE_v       0.10 1110 101 00001 11001 0 ..... .....     @qrr_s
 
 FCVTL_v         0.00 1110 0.1 00001 01111 0 ..... .....     @qrr_sd
 
+F1CVTL          0.10 1110 001 00001 01111 0 ..... .....     @qrr_h
+F2CVTL          0.10 1110 011 00001 01111 0 ..... .....     @qrr_h
+
 BF1CVTL         0.10 1110 101 00001 01111 0 ..... .....     @qrr_h
 BF2CVTL         0.10 1110 111 00001 01111 0 ..... .....     @qrr_h
 

diff --git a/target/arm/tcg/fp8_helper.c b/target/arm/tcg/fp8_helper.c
index aad03b0817270e4bd414db1d53065f8237a4ac69..0f3c2796967fc98a65851afa9b4ea0b7073c45fe 100644 (file)
--- a/target/arm/tcg/fp8_helper.c
+++ b/target/arm/tcg/fp8_helper.c
@@ -103,6 +103,14 @@ static bfloat16 fcvt_fp8_to_b16(uint8_t x, fp8_input_fn *f8fmt,
     return bfloat16_round_pack_canonical(&p, s);
 }
 
+static float16 fcvt_fp8_to_f16(uint8_t x, fp8_input_fn *f8fmt,
+                               int scale, float_status *s)
+{
+    FloatParts64 p = f8fmt(x, s);
+    p = parts64_scalbn(&p, scale, s);
+    return float16_round_pack_canonical(&p, s);
+}
+
 void HELPER(advsimd_bfcvtl)(void *vd, void *vn, CPUARMState *env, uint32_t desc)
 {
     FP8Context ctx = fp8_src_start(env, desc, 0x3f);
@@ -123,6 +131,27 @@ void HELPER(advsimd_bfcvtl)(void *vd, void *vn, CPUARMState *env, uint32_t desc)
     clear_tail(vd, 16, simd_maxsz(desc));
 }
 
+void HELPER(advsimd_fcvtl_hb)(void *vd, void *vn,
+                              CPUARMState *env, uint32_t desc)
+{
+    FP8Context ctx = fp8_src_start(env, desc, 0xf);
+    fp8_input_fn *input_fmt = fp8_input_fmt[ctx.f8fmt];
+    uint8_t *n = vn, scratch[16];
+    float16 *d = vd;
+
+    if (vd == vn) {
+        n = memcpy(scratch, vn, 16);
+    }
+    n += ctx.high * 8;
+
+    for (size_t i = 0; i < 8; ++i) {
+        d[H2(i)] = fcvt_fp8_to_f16(n[H1(i)], input_fmt, ctx.scale, &ctx.stat);
+    }
+
+    fp8_cvt_finish(env, &ctx);
+    clear_tail(vd, 16, simd_maxsz(desc));
+}
+
 void HELPER(sve2_bfcvt)(void *vd, void *vn, CPUARMState *env, uint32_t desc)
 {
     FP8Context ctx = fp8_src_start(env, desc, 0x3f);

diff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h
index 966f83d796f3becb40b01e3b28c40c9a88c82226..718463422be25e7976093dca462589966ff775e8 100644 (file)
--- a/target/arm/tcg/helper-fp8-defs.h
+++ b/target/arm/tcg/helper-fp8-defs.h
@@ -7,3 +7,5 @@ DEF_HELPER_FLAGS_4(advsimd_bfcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
 DEF_HELPER_FLAGS_4(sve2_bfcvt, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
 DEF_HELPER_FLAGS_4(sme2_bfcvt_hb, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
 DEF_HELPER_FLAGS_4(sme2_bfcvtl_hb, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(advsimd_fcvtl_hb, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 5e8c86235b47ef1bb7a56292363db743cbaf817f..439a405064aa53bcb8761bd11e3edf1c25a3c575 100644 (file)
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -10740,6 +10740,9 @@ static bool do_f8cvt(DisasContext *s, arg_qrr_e *a,
     return true;
 }
 
+TRANS_FEAT(F1CVTL, aa64_f8cvt, do_f8cvt, a, gen_helper_advsimd_fcvtl_hb, false)
+TRANS_FEAT(F2CVTL, aa64_f8cvt, do_f8cvt, a, gen_helper_advsimd_fcvtl_hb, true)
+
 TRANS_FEAT(BF1CVTL, aa64_f8cvt, do_f8cvt, a, gen_helper_advsimd_bfcvtl, false)
 TRANS_FEAT(BF2CVTL, aa64_f8cvt, do_f8cvt, a, gen_helper_advsimd_bfcvtl, true)