From c29018cc7395fdb7efd5e21c6f6c4d9cfbcf9a3c Mon Sep 17 00:00:00 2001 From: "Lucas Mateus Castro (alqotel)" Date: Tue, 24 May 2022 11:05:33 -0300 Subject: [PATCH] target/ppc: Implemented xvf*ger* Implement the following PowerISA v3.1 instructions: xvf32ger: VSX Vector 32-bit Floating-Point GER (rank-1 update) xvf32gernn: VSX Vector 32-bit Floating-Point GER (rank-1 update) Negative multiply, Negative accumulate xvf32gernp: VSX Vector 32-bit Floating-Point GER (rank-1 update) Negative multiply, Positive accumulate xvf32gerpn: VSX Vector 32-bit Floating-Point GER (rank-1 update) Positive multiply, Negative accumulate xvf32gerpp: VSX Vector 32-bit Floating-Point GER (rank-1 update) Positive multiply, Positive accumulate xvf64ger: VSX Vector 64-bit Floating-Point GER (rank-1 update) xvf64gernn: VSX Vector 64-bit Floating-Point GER (rank-1 update) Negative multiply, Negative accumulate xvf64gernp: VSX Vector 64-bit Floating-Point GER (rank-1 update) Negative multiply, Positive accumulate xvf64gerpn: VSX Vector 64-bit Floating-Point GER (rank-1 update) Positive multiply, Negative accumulate xvf64gerpp: VSX Vector 64-bit Floating-Point GER (rank-1 update) Positive multiply, Positive accumulate Signed-off-by: Lucas Mateus Castro (alqotel) Reviewed-by: Richard Henderson Message-Id: <20220524140537.27451-5-lucas.araujo@eldorado.org.br> Signed-off-by: Daniel Henrique Barboza --- target/ppc/cpu.h | 4 + target/ppc/fpu_helper.c | 194 +++++++++++++++++++++++++++- target/ppc/helper.h | 10 ++ target/ppc/insn32.decode | 13 ++ target/ppc/translate/vsx-impl.c.inc | 12 ++ 5 files changed, 231 insertions(+), 2 deletions(-) diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index dff3ca8222..40c779f246 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -2643,6 +2643,8 @@ static inline bool lsw_reg_in_range(int start, int nregs, int rx) #define VsrSW(i) s32[i] #define VsrD(i) u64[i] #define VsrSD(i) s64[i] +#define VsrSF(i) f32[i] +#define VsrDF(i) f64[i] #else #define VsrB(i) u8[15 - (i)] #define VsrSB(i) s8[15 - (i)] @@ -2652,6 +2654,8 @@ static inline bool lsw_reg_in_range(int start, int nregs, int rx) #define VsrSW(i) s32[3 - (i)] #define VsrD(i) u64[1 - (i)] #define VsrSD(i) s64[1 - (i)] +#define VsrSF(i) f32[3 - (i)] +#define VsrDF(i) f64[1 - (i)] #endif static inline int vsr64_offset(int i, bool high) diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index 9489e06504..712c71162c 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -414,7 +414,7 @@ void helper_store_fpscr(CPUPPCState *env, uint64_t val, uint32_t nibbles) ppc_store_fpscr(env, val); } -void helper_fpscr_check_status(CPUPPCState *env) +static void do_fpscr_check_status(CPUPPCState *env, uintptr_t raddr) { CPUState *cs = env_cpu(env); target_ulong fpscr = env->fpscr; @@ -455,13 +455,19 @@ void helper_fpscr_check_status(CPUPPCState *env) } cs->exception_index = POWERPC_EXCP_PROGRAM; env->error_code = error | POWERPC_EXCP_FP; + env->fpscr |= error ? FP_FEX : 0; /* Deferred floating-point exception after target FPSCR update */ if (fp_exceptions_enabled(env)) { raise_exception_err_ra(env, cs->exception_index, - env->error_code, GETPC()); + env->error_code, raddr); } } +void helper_fpscr_check_status(CPUPPCState *env) +{ + do_fpscr_check_status(env, GETPC()); +} + static void do_float_check_status(CPUPPCState *env, bool change_fi, uintptr_t raddr) { @@ -3468,3 +3474,187 @@ void helper_xssubqp(CPUPPCState *env, uint32_t opcode, *xt = t; do_float_check_status(env, true, GETPC()); } + +static inline void vsxger_excp(CPUPPCState *env, uintptr_t retaddr) +{ + /* + * XV*GER instructions execute and set the FPSCR as if exceptions + * are disabled and only at the end throw an exception + */ + target_ulong enable; + enable = env->fpscr & (FP_ENABLES | FP_FI | FP_FR); + env->fpscr &= ~(FP_ENABLES | FP_FI | FP_FR); + int status = get_float_exception_flags(&env->fp_status); + if (unlikely(status & float_flag_invalid)) { + if (status & float_flag_invalid_snan) { + float_invalid_op_vxsnan(env, 0); + } + if (status & float_flag_invalid_imz) { + float_invalid_op_vximz(env, false, 0); + } + if (status & float_flag_invalid_isi) { + float_invalid_op_vxisi(env, false, 0); + } + } + do_float_check_status(env, false, retaddr); + env->fpscr |= enable; + do_fpscr_check_status(env, retaddr); +} + +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, + int flags, float_status *s); + +static void vsxger_muladd32(ppc_vsr_t *at, ppc_vsr_t *a, ppc_vsr_t *b, int i, + int j, int flags, float_status *s) +{ + at[i].VsrSF(j) = float32_muladd(a->VsrSF(i), b->VsrSF(j), + at[i].VsrSF(j), flags, s); +} + +static void vsxger_mul32(ppc_vsr_t *at, ppc_vsr_t *a, ppc_vsr_t *b, int i, + int j, int flags, float_status *s) +{ + at[i].VsrSF(j) = float32_mul(a->VsrSF(i), b->VsrSF(j), s); +} + +static void vsxger_zero32(ppc_vsr_t *at, int i, int j) +{ + at[i].VsrSF(j) = float32_zero; +} + +static void vsxger_muladd64(ppc_vsr_t *at, ppc_vsr_t *a, ppc_vsr_t *b, int i, + int j, int flags, float_status *s) +{ + if (j >= 2) { + j -= 2; + at[i].VsrDF(j) = float64_muladd(a[i / 2].VsrDF(i % 2), b->VsrDF(j), + at[i].VsrDF(j), flags, s); + } +} + +static void vsxger_mul64(ppc_vsr_t *at, ppc_vsr_t *a, ppc_vsr_t *b, int i, + int j, int flags, float_status *s) +{ + if (j >= 2) { + j -= 2; + at[i].VsrDF(j) = float64_mul(a[i / 2].VsrDF(i % 2), b->VsrDF(j), s); + } +} + +static void vsxger_zero64(ppc_vsr_t *at, int i, int j) +{ + if (j >= 2) { + j -= 2; + at[i].VsrDF(j) = float64_zero; + } +} + +static void vsxger(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, vsxger_muladd_f mul, vsxger_muladd_f muladd, + vsxger_zero zero) +{ + int i, j, xmsk_bit, ymsk_bit, op_flags; + uint8_t xmsk = mask & 0x0F; + uint8_t ymsk = (mask >> 4) & 0x0F; + float_status *excp_ptr = &env->fp_status; + op_flags = (neg_acc ^ neg_mul) ? float_muladd_negate_c : 0; + op_flags |= (neg_mul) ? float_muladd_negate_result : 0; + helper_reset_fpstatus(env); + 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)) { + if (acc) { + muladd(at, a, b, i, j, op_flags, excp_ptr); + } else { + mul(at, a, b, i, j, op_flags, excp_ptr); + } + } else { + zero(at, i, j); + } + } + } + vsxger_excp(env, GETPC()); +} + +QEMU_FLATTEN +void helper_XVF32GER(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, false, false, false, vsxger_mul32, + vsxger_muladd32, vsxger_zero32); +} + +QEMU_FLATTEN +void helper_XVF32GERPP(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, true, false, false, vsxger_mul32, + vsxger_muladd32, vsxger_zero32); +} + +QEMU_FLATTEN +void helper_XVF32GERPN(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, true, false, true, vsxger_mul32, + vsxger_muladd32, vsxger_zero32); +} + +QEMU_FLATTEN +void helper_XVF32GERNP(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, true, true, false, vsxger_mul32, + vsxger_muladd32, vsxger_zero32); +} + +QEMU_FLATTEN +void helper_XVF32GERNN(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, true, true, true, vsxger_mul32, + vsxger_muladd32, vsxger_zero32); +} + +QEMU_FLATTEN +void helper_XVF64GER(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, false, false, false, vsxger_mul64, + vsxger_muladd64, vsxger_zero64); +} + +QEMU_FLATTEN +void helper_XVF64GERPP(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, true, false, false, vsxger_mul64, + vsxger_muladd64, vsxger_zero64); +} + +QEMU_FLATTEN +void helper_XVF64GERPN(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, true, false, true, vsxger_mul64, + vsxger_muladd64, vsxger_zero64); +} + +QEMU_FLATTEN +void helper_XVF64GERNP(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, true, true, false, vsxger_mul64, + vsxger_muladd64, vsxger_zero64); +} + +QEMU_FLATTEN +void helper_XVF64GERNN(CPUPPCState *env, ppc_vsr_t *a, ppc_vsr_t *b, + ppc_acc_t *at, uint32_t mask) +{ + vsxger(env, a, b, at, mask, true, true, true, vsxger_mul64, + vsxger_muladd64, vsxger_zero64); +} diff --git a/target/ppc/helper.h b/target/ppc/helper.h index 1666797edf..f38cdbe1d8 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -550,6 +550,16 @@ DEF_HELPER_5(XVI16GER2, void, env, vsr, vsr, acc, i32) DEF_HELPER_5(XVI16GER2S, void, env, vsr, vsr, acc, i32) DEF_HELPER_5(XVI16GER2PP, void, env, vsr, vsr, acc, i32) DEF_HELPER_5(XVI16GER2SPP, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF32GER, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF32GERPP, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF32GERPN, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF32GERNP, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF32GERNN, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF64GER, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF64GERPP, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF64GERPN, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF64GERNP, void, env, vsr, vsr, acc, i32) +DEF_HELPER_5(XVF64GERNN, void, env, vsr, vsr, acc, i32) DEF_HELPER_2(efscfsi, i32, env, i32) DEF_HELPER_2(efscfui, i32, env, i32) diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode index 0e189fe2da..6b644155ec 100644 --- a/target/ppc/insn32.decode +++ b/target/ppc/insn32.decode @@ -178,6 +178,7 @@ # 32 bit GER instructions have all mask bits considered 1 &MMIRR_XX3 xa xb xt pmsk xmsk ymsk %xx_at 23:3 +%xx_xa_pair 2:1 17:4 !function=times_2 @XX3_at ...... ... .. ..... ..... ........ ... &MMIRR_XX3 xt=%xx_at xb=%xx_xb \ pmsk=255 xmsk=15 ymsk=15 @@ -761,3 +762,15 @@ XVI16GER2PP 111011 ... -- ..... ..... 01101011 ..- @XX3_at xa=%xx_xa XVI8GER4SPP 111011 ... -- ..... ..... 01100011 ..- @XX3_at xa=%xx_xa XVI16GER2S 111011 ... -- ..... ..... 00101011 ..- @XX3_at xa=%xx_xa XVI16GER2SPP 111011 ... -- ..... ..... 00101010 ..- @XX3_at xa=%xx_xa + +XVF32GER 111011 ... -- ..... ..... 00011011 ..- @XX3_at xa=%xx_xa +XVF32GERPP 111011 ... -- ..... ..... 00011010 ..- @XX3_at xa=%xx_xa +XVF32GERPN 111011 ... -- ..... ..... 10011010 ..- @XX3_at xa=%xx_xa +XVF32GERNP 111011 ... -- ..... ..... 01011010 ..- @XX3_at xa=%xx_xa +XVF32GERNN 111011 ... -- ..... ..... 11011010 ..- @XX3_at xa=%xx_xa + +XVF64GER 111011 ... -- .... 0 ..... 00111011 ..- @XX3_at xa=%xx_xa_pair +XVF64GERPP 111011 ... -- .... 0 ..... 00111010 ..- @XX3_at xa=%xx_xa_pair +XVF64GERPN 111011 ... -- .... 0 ..... 10111010 ..- @XX3_at xa=%xx_xa_pair +XVF64GERNP 111011 ... -- .... 0 ..... 01111010 ..- @XX3_at xa=%xx_xa_pair +XVF64GERNN 111011 ... -- .... 0 ..... 11111010 ..- @XX3_at xa=%xx_xa_pair diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc index b10eded1da..cc754ab175 100644 --- a/target/ppc/translate/vsx-impl.c.inc +++ b/target/ppc/translate/vsx-impl.c.inc @@ -2898,6 +2898,18 @@ TRANS64(PMXVI16GER2PP, do_ger, gen_helper_XVI16GER2PP) TRANS64(PMXVI16GER2S, do_ger, gen_helper_XVI16GER2S) TRANS64(PMXVI16GER2SPP, do_ger, gen_helper_XVI16GER2SPP) +TRANS(XVF32GER, do_ger, gen_helper_XVF32GER) +TRANS(XVF32GERPP, do_ger, gen_helper_XVF32GERPP) +TRANS(XVF32GERPN, do_ger, gen_helper_XVF32GERPN) +TRANS(XVF32GERNP, do_ger, gen_helper_XVF32GERNP) +TRANS(XVF32GERNN, do_ger, gen_helper_XVF32GERNN) + +TRANS(XVF64GER, do_ger, gen_helper_XVF64GER) +TRANS(XVF64GERPP, do_ger, gen_helper_XVF64GERPP) +TRANS(XVF64GERPN, do_ger, gen_helper_XVF64GERPN) +TRANS(XVF64GERNP, do_ger, gen_helper_XVF64GERNP) +TRANS(XVF64GERNN, do_ger, gen_helper_XVF64GERNN) + #undef GEN_XX2FORM #undef GEN_XX3FORM #undef GEN_XX2IFORM