Message ID | 20210626050307.2408505-6-richard.henderson@linaro.org |
---|---|
State | Superseded |
Headers | show |
Series | tcg/s390x: host vector support | expand |
On 26.06.21 07:02, Richard Henderson wrote: > Signed-off-by: Richard Henderson <richard.henderson@linaro.org> > --- > tcg/s390x/tcg-target.c.inc | 122 +++++++++++++++++++++++++++++++++---- > 1 file changed, 110 insertions(+), 12 deletions(-) > > diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc > index 18233c628d..b6ea129e14 100644 > --- a/tcg/s390x/tcg-target.c.inc > +++ b/tcg/s390x/tcg-target.c.inc > @@ -265,6 +265,12 @@ typedef enum S390Opcode { > RX_STC = 0x42, > RX_STH = 0x40, > > + VRX_VL = 0xe706, > + VRX_VLLEZ = 0xe704, > + VRX_VST = 0xe70e, > + VRX_VSTEF = 0xe70b, > + VRX_VSTEG = 0xe70a, > + > NOP = 0x0707, > } S390Opcode; > > @@ -529,6 +535,31 @@ static void tcg_out_insn_RSY(TCGContext *s, S390Opcode op, TCGReg r1, > #define tcg_out_insn_RX tcg_out_insn_RS > #define tcg_out_insn_RXY tcg_out_insn_RSY > > +static int RXB(TCGReg v1, TCGReg v2, TCGReg v3, TCGReg v4) > +{ > + /* > + * Shift bit 4 of each regno to its corresponding bit of RXB. > + * RXB itself begins at bit 8 of the instruction so 8 - 4 = 4 > + * is the left-shift of the 4th operand. > + */ > + return ((v1 & 0x10) << (4 + 3)) > + | ((v2 & 0x10) << (4 + 2)) > + | ((v3 & 0x10) << (4 + 1)) > + | ((v4 & 0x10) << (4 + 0)); > +} > + > +static void tcg_out_insn_VRX(TCGContext *s, S390Opcode op, TCGReg v1, > + TCGReg b2, TCGReg x2, intptr_t d2, int m3) Is intptr_t really the right type here? Just curious ... I'd have used an uint16_t and asserted "!(d1 & 0xf000)". > +{ > + tcg_debug_assert(v1 >= TCG_REG_V0 && v1 <= TCG_REG_V31); > + tcg_debug_assert(d2 >= 0 && d2 <= 0xfff); > + tcg_debug_assert(x2 <= TCG_REG_R15); > + tcg_debug_assert(b2 <= TCG_REG_R15); > + tcg_out16(s, (op & 0xff00) | ((v1 & 15) << 4) | x2); Nit: ((v1 & 0xf) << 4) makes it immediately clearer to me which bits are set by which piece of this puzzle :) > + tcg_out16(s, (b2 << 12) | d2); > + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m3 << 12)); > +} > + > /* Emit an opcode with "type-checking" of the format. */ > #define tcg_out_insn(S, FMT, OP, ...) \ > glue(tcg_out_insn_,FMT)(S, glue(glue(FMT,_),OP), ## __VA_ARGS__) > @@ -705,25 +736,92 @@ static void tcg_out_mem(TCGContext *s, S390Opcode opc_rx, S390Opcode opc_rxy, > } > } > > +static void tcg_out_vrx_mem(TCGContext *s, S390Opcode opc_vrx, > + TCGReg data, TCGReg base, TCGReg index, > + tcg_target_long ofs, int m3) > +{ > + if (ofs < 0 || ofs >= 0x1000) { > + if (ofs >= -0x80000 && ofs < 0x80000) { > + tcg_out_insn(s, RXY, LAY, TCG_TMP0, base, index, ofs); > + base = TCG_TMP0; > + index = TCG_REG_NONE; > + ofs = 0; > + } else { > + tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, ofs); > + if (index != TCG_REG_NONE) { > + tcg_out_insn(s, RRE, AGR, TCG_TMP0, index); > + } > + index = TCG_TMP0; > + ofs = 0; > + } > + } > + tcg_out_insn_VRX(s, opc_vrx, data, base, index, ofs, m3); > +} > > /* load data without address translation or endianness conversion */ > -static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data, > - TCGReg base, intptr_t ofs) > +static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data, > + TCGReg base, intptr_t ofs) > { > - if (type == TCG_TYPE_I32) { > - tcg_out_mem(s, RX_L, RXY_LY, data, base, TCG_REG_NONE, ofs); > - } else { > - tcg_out_mem(s, 0, RXY_LG, data, base, TCG_REG_NONE, ofs); > + switch (type) { > + case TCG_TYPE_I32: > + if (likely(data < 16)) { This actually maps to "if (likely(data <= TCG_REG_R15))", correct? -- Thanks, David / dhildenb
On 9/14/21 9:46 AM, David Hildenbrand wrote: >> +static void tcg_out_insn_VRX(TCGContext *s, S390Opcode op, TCGReg v1, >> + TCGReg b2, TCGReg x2, intptr_t d2, int m3) > > Is intptr_t really the right type here? Just curious ... I'd have used an uint16_t and > asserted "!(d1 & 0xf000)". It does come from upstream, as part of a host address. If you use uint16_t, the assert misses the upper bits being zero because they've been truncated. r~
On 9/14/21 9:46 AM, David Hildenbrand wrote: >> + if (likely(data < 16)) { > > This actually maps to "if (likely(data <= TCG_REG_R15))", correct? Sure. r~
On 9/14/21 3:03 PM, Richard Henderson wrote: > On 9/14/21 9:46 AM, David Hildenbrand wrote: >>> + if (likely(data < 16)) { >> >> This actually maps to "if (likely(data <= TCG_REG_R15))", correct? > > Sure. I'm going to add is_general_reg and is_vector_reg predicates. r~
On 15.09.21 00:14, Richard Henderson wrote: > On 9/14/21 3:03 PM, Richard Henderson wrote: >> On 9/14/21 9:46 AM, David Hildenbrand wrote: >>>> + if (likely(data < 16)) { >>> >>> This actually maps to "if (likely(data <= TCG_REG_R15))", correct? >> >> Sure. > > I'm going to add is_general_reg and is_vector_reg predicates. That will make it easier to grasp, thanks! -- Thanks, David / dhildenb
diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc index 18233c628d..b6ea129e14 100644 --- a/tcg/s390x/tcg-target.c.inc +++ b/tcg/s390x/tcg-target.c.inc @@ -265,6 +265,12 @@ typedef enum S390Opcode { RX_STC = 0x42, RX_STH = 0x40, + VRX_VL = 0xe706, + VRX_VLLEZ = 0xe704, + VRX_VST = 0xe70e, + VRX_VSTEF = 0xe70b, + VRX_VSTEG = 0xe70a, + NOP = 0x0707, } S390Opcode; @@ -529,6 +535,31 @@ static void tcg_out_insn_RSY(TCGContext *s, S390Opcode op, TCGReg r1, #define tcg_out_insn_RX tcg_out_insn_RS #define tcg_out_insn_RXY tcg_out_insn_RSY +static int RXB(TCGReg v1, TCGReg v2, TCGReg v3, TCGReg v4) +{ + /* + * Shift bit 4 of each regno to its corresponding bit of RXB. + * RXB itself begins at bit 8 of the instruction so 8 - 4 = 4 + * is the left-shift of the 4th operand. + */ + return ((v1 & 0x10) << (4 + 3)) + | ((v2 & 0x10) << (4 + 2)) + | ((v3 & 0x10) << (4 + 1)) + | ((v4 & 0x10) << (4 + 0)); +} + +static void tcg_out_insn_VRX(TCGContext *s, S390Opcode op, TCGReg v1, + TCGReg b2, TCGReg x2, intptr_t d2, int m3) +{ + tcg_debug_assert(v1 >= TCG_REG_V0 && v1 <= TCG_REG_V31); + tcg_debug_assert(d2 >= 0 && d2 <= 0xfff); + tcg_debug_assert(x2 <= TCG_REG_R15); + tcg_debug_assert(b2 <= TCG_REG_R15); + tcg_out16(s, (op & 0xff00) | ((v1 & 15) << 4) | x2); + tcg_out16(s, (b2 << 12) | d2); + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m3 << 12)); +} + /* Emit an opcode with "type-checking" of the format. */ #define tcg_out_insn(S, FMT, OP, ...) \ glue(tcg_out_insn_,FMT)(S, glue(glue(FMT,_),OP), ## __VA_ARGS__) @@ -705,25 +736,92 @@ static void tcg_out_mem(TCGContext *s, S390Opcode opc_rx, S390Opcode opc_rxy, } } +static void tcg_out_vrx_mem(TCGContext *s, S390Opcode opc_vrx, + TCGReg data, TCGReg base, TCGReg index, + tcg_target_long ofs, int m3) +{ + if (ofs < 0 || ofs >= 0x1000) { + if (ofs >= -0x80000 && ofs < 0x80000) { + tcg_out_insn(s, RXY, LAY, TCG_TMP0, base, index, ofs); + base = TCG_TMP0; + index = TCG_REG_NONE; + ofs = 0; + } else { + tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, ofs); + if (index != TCG_REG_NONE) { + tcg_out_insn(s, RRE, AGR, TCG_TMP0, index); + } + index = TCG_TMP0; + ofs = 0; + } + } + tcg_out_insn_VRX(s, opc_vrx, data, base, index, ofs, m3); +} /* load data without address translation or endianness conversion */ -static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data, - TCGReg base, intptr_t ofs) +static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data, + TCGReg base, intptr_t ofs) { - if (type == TCG_TYPE_I32) { - tcg_out_mem(s, RX_L, RXY_LY, data, base, TCG_REG_NONE, ofs); - } else { - tcg_out_mem(s, 0, RXY_LG, data, base, TCG_REG_NONE, ofs); + switch (type) { + case TCG_TYPE_I32: + if (likely(data < 16)) { + tcg_out_mem(s, RX_L, RXY_LY, data, base, TCG_REG_NONE, ofs); + break; + } + tcg_out_vrx_mem(s, VRX_VLLEZ, data, base, TCG_REG_NONE, ofs, MO_32); + break; + + case TCG_TYPE_I64: + if (likely(data < 16)) { + tcg_out_mem(s, 0, RXY_LG, data, base, TCG_REG_NONE, ofs); + break; + } + /* fallthru */ + + case TCG_TYPE_V64: + tcg_out_vrx_mem(s, VRX_VLLEZ, data, base, TCG_REG_NONE, ofs, MO_64); + break; + + case TCG_TYPE_V128: + /* Hint quadword aligned. */ + tcg_out_vrx_mem(s, VRX_VL, data, base, TCG_REG_NONE, ofs, 4); + break; + + default: + g_assert_not_reached(); } } -static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg data, - TCGReg base, intptr_t ofs) +static void tcg_out_st(TCGContext *s, TCGType type, TCGReg data, + TCGReg base, intptr_t ofs) { - if (type == TCG_TYPE_I32) { - tcg_out_mem(s, RX_ST, RXY_STY, data, base, TCG_REG_NONE, ofs); - } else { - tcg_out_mem(s, 0, RXY_STG, data, base, TCG_REG_NONE, ofs); + switch (type) { + case TCG_TYPE_I32: + if (likely(data < 16)) { + tcg_out_mem(s, RX_ST, RXY_STY, data, base, TCG_REG_NONE, ofs); + } else { + tcg_out_vrx_mem(s, VRX_VSTEF, data, base, TCG_REG_NONE, ofs, 1); + } + break; + + case TCG_TYPE_I64: + if (likely(data < 16)) { + tcg_out_mem(s, 0, RXY_STG, data, base, TCG_REG_NONE, ofs); + break; + } + /* fallthru */ + + case TCG_TYPE_V64: + tcg_out_vrx_mem(s, VRX_VSTEG, data, base, TCG_REG_NONE, ofs, 0); + break; + + case TCG_TYPE_V128: + /* Hint quadword aligned. */ + tcg_out_vrx_mem(s, VRX_VST, data, base, TCG_REG_NONE, ofs, 4); + break; + + default: + g_assert_not_reached(); } }
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/s390x/tcg-target.c.inc | 122 +++++++++++++++++++++++++++++++++---- 1 file changed, 110 insertions(+), 12 deletions(-) -- 2.25.1