diff options
| author | Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br> | 2022-05-24 11:05:34 -0300 |
|---|---|---|
| committer | Daniel Henrique Barboza <danielhb413@gmail.com> | 2022-05-26 17:11:33 -0300 |
| commit | 2d9cba74ef72232189ac5611968c1b9045a3e1a7 (patch) | |
| tree | 2ccfd94128649c16915807b36694f20c0c3b9d8d /target/ppc/fpu_helper.c | |
| parent | c29018cc7395fdb7efd5e21c6f6c4d9cfbcf9a3c (diff) | |
target/ppc: Implemented xvf16ger*
Implement the following PowerISA v3.1 instructions:
xvf16ger2: VSX Vector 16-bit Floating-Point GER (rank-2 update)
xvf16ger2nn: VSX Vector 16-bit Floating-Point GER (rank-2 update) Negative
multiply, Negative accumulate
xvf16ger2np: VSX Vector 16-bit Floating-Point GER (rank-2 update) Negative
multiply, Positive accumulate
xvf16ger2pn: VSX Vector 16-bit Floating-Point GER (rank-2 update) Positive
multiply, Negative accumulate
xvf16ger2pp: VSX Vector 16-bit Floating-Point GER (rank-2 update) Positive
multiply, Positive accumulate
Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220524140537.27451-6-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Diffstat (limited to 'target/ppc/fpu_helper.c')
| -rw-r--r-- | target/ppc/fpu_helper.c | 95 |
1 files changed, 95 insertions, 0 deletions
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index 712c71162c..a9b2ef370f 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -36,6 +36,15 @@ static inline float128 float128_snan_to_qnan(float128 x) #define float32_snan_to_qnan(x) ((x) | 0x00400000) #define float16_snan_to_qnan(x) ((x) | 0x0200) +static inline float32 bfp32_neg(float32 a) +{ + if (unlikely(float32_is_any_nan(a))) { + return a; + } else { + return float32_chs(a); + } +} + static inline bool fp_exceptions_enabled(CPUPPCState *env) { #ifdef CONFIG_USER_ONLY @@ -3501,6 +3510,57 @@ static inline void vsxger_excp(CPUPPCState *env, uintptr_t retaddr) do_fpscr_check_status(env, retaddr); } +typedef float64 extract_f16(float16, float_status *); + +static float64 extract_hf16(float16 in, float_status *fp_status) +{ + return float16_to_float64(in, true, fp_status); +} + +static void vsxger16(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask, bool acc, + bool neg_mul, bool neg_acc, extract_f16 extract) +{ + float32 r, aux_acc; + float64 psum, va, vb, vc, vd; + int i, j, xmsk_bit, ymsk_bit; + uint8_t pmsk = FIELD_EX32(mask, GER_MSK, PMSK), + xmsk = FIELD_EX32(mask, GER_MSK, XMSK), + ymsk = FIELD_EX32(mask, GER_MSK, YMSK); + float_status *excp_ptr = &env->fp_status; + for (i = 0, xmsk_bit = 1 << 3; i < 4; i++, xmsk_bit >>= 1) { + for (j = 0, ymsk_bit = 1 << 3; j < 4; j++, ymsk_bit >>= 1) { + if ((xmsk_bit & xmsk) && (ymsk_bit & ymsk)) { + va = !(pmsk & 2) ? float64_zero : + extract(a->VsrHF(2 * i), excp_ptr); + vb = !(pmsk & 2) ? float64_zero : + extract(b->VsrHF(2 * j), excp_ptr); + vc = !(pmsk & 1) ? float64_zero : + extract(a->VsrHF(2 * i + 1), excp_ptr); + vd = !(pmsk & 1) ? float64_zero : + extract(b->VsrHF(2 * j + 1), excp_ptr); + psum = float64_mul(va, vb, excp_ptr); + psum = float64r32_muladd(vc, vd, psum, 0, excp_ptr); + r = float64_to_float32(psum, excp_ptr); + if (acc) { + aux_acc = at[i].VsrSF(j); + if (neg_mul) { + r = bfp32_neg(r); + } + if (neg_acc) { + aux_acc = bfp32_neg(aux_acc); + } + r = float32_add(r, aux_acc, excp_ptr); + } + at[i].VsrSF(j) = r; + } else { + at[i].VsrSF(j) = float32_zero; + } + } + } + vsxger_excp(env, GETPC()); +} + typedef void vsxger_zero(ppc_vsr_t *at, int, int); typedef void vsxger_muladd_f(ppc_vsr_t *, ppc_vsr_t *, ppc_vsr_t *, int, int, @@ -3580,6 +3640,41 @@ static void vsxger(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, } QEMU_FLATTEN +void helper_XVF16GER2(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger16(env, a, b, at, mask, false, false, false, extract_hf16); +} + +QEMU_FLATTEN +void helper_XVF16GER2PP(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger16(env, a, b, at, mask, true, false, false, extract_hf16); +} + +QEMU_FLATTEN +void helper_XVF16GER2PN(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger16(env, a, b, at, mask, true, false, true, extract_hf16); +} + +QEMU_FLATTEN +void helper_XVF16GER2NP(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger16(env, a, b, at, mask, true, true, false, extract_hf16); +} + +QEMU_FLATTEN +void helper_XVF16GER2NN(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger16(env, a, b, at, mask, true, true, true, extract_hf16); +} + +QEMU_FLATTEN void helper_XVF32GER(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, ppc_acc_t *at, uint32_t mask) { |