OpenE2K/qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity
759bac673a
qemu-e2k/target/ppc/translate/vmx-ops.c.inc
Lucas Mateus Castro (alqotel) 26c964f851 target/ppc: Move VABSDU[BHW] to decodetree and use gvec 
Moved VABSDUB, VABSDUH and VABSDUW to decodetree and use gvec to
translate them.

vabsdub:
rept    loop    master             patch
8       12500   0,03601600         0,00688500 (-80.9%)
25      4000    0,03651000         0,00532100 (-85.4%)
100     1000    0,03666900         0,00595300 (-83.8%)
500     200     0,04305800         0,01244600 (-71.1%)
2500    40      0,06893300         0,04273700 (-38.0%)
8000    12      0,14633200         0,12660300 (-13.5%)

vabsduh:
rept    loop    master             patch
8       12500   0,02172400         0,00687500 (-68.4%)
25      4000    0,02154100         0,00531500 (-75.3%)
100     1000    0,02235400         0,00596300 (-73.3%)
500     200     0,02827500         0,01245100 (-56.0%)
2500    40      0,05638400         0,04285500 (-24.0%)
8000    12      0,13166000         0,12641400 (-4.0%)

vabsduw:
rept    loop    master             patch
8       12500   0,01646400         0,00688300 (-58.2%)
25      4000    0,01454500         0,00475500 (-67.3%)
100     1000    0,01545800         0,00511800 (-66.9%)
500     200     0,02168200         0,01114300 (-48.6%)
2500    40      0,04571300         0,04138800 (-9.5%)
8000    12      0,12209500         0,12178500 (-0.3%)

Same as VADDCUW and VSUBCUW, overall performance gain but it uses more
TCGop (4 before the patch, 6 after).

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20221019125040.48028-8-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
2022-10-28 13:15:22 -03:00

233 lines
9.3 KiB
SQL
Raw Blame History

#define GEN_VR_LDX(name, opc2, opc3) \
GEN_HANDLER(name, 0x1F, opc2, opc3, 0x00000001, PPC_ALTIVEC)
#define GEN_VR_STX(name, opc2, opc3) \
GEN_HANDLER(st##name, 0x1F, opc2, opc3, 0x00000001, PPC_ALTIVEC)
#define GEN_VR_LVE(name, opc2, opc3) \
GEN_HANDLER(lve##name, 0x1F, opc2, opc3, 0x00000001, PPC_ALTIVEC)
#define GEN_VR_STVE(name, opc2, opc3) \
GEN_HANDLER(stve##name, 0x1F, opc2, opc3, 0x00000001, PPC_ALTIVEC)
GEN_VR_LDX(lvx, 0x07, 0x03),
GEN_VR_LDX(lvxl, 0x07, 0x0B),
GEN_VR_LVE(bx, 0x07, 0x00),
GEN_VR_LVE(hx, 0x07, 0x01),
GEN_VR_LVE(wx, 0x07, 0x02),
GEN_VR_STX(svx, 0x07, 0x07),
GEN_VR_STX(svxl, 0x07, 0x0F),
GEN_VR_STVE(bx, 0x07, 0x04),
GEN_VR_STVE(hx, 0x07, 0x05),
GEN_VR_STVE(wx, 0x07, 0x06),
#define GEN_VX_LOGICAL(name, tcg_op, opc2, opc3) \
GEN_HANDLER(name, 0x04, opc2, opc3, 0x00000000, PPC_ALTIVEC)
#define GEN_VX_LOGICAL_207(name, tcg_op, opc2, opc3) \
GEN_HANDLER_E(name, 0x04, opc2, opc3, 0x00000000, PPC_NONE, PPC2_ALTIVEC_207)
GEN_VX_LOGICAL(vand, tcg_gen_and_i64, 2, 16),
GEN_VX_LOGICAL(vandc, tcg_gen_andc_i64, 2, 17),
GEN_VX_LOGICAL(vor, tcg_gen_or_i64, 2, 18),
GEN_VX_LOGICAL(vxor, tcg_gen_xor_i64, 2, 19),
GEN_VX_LOGICAL(vnor, tcg_gen_nor_i64, 2, 20),
GEN_VX_LOGICAL_207(veqv, tcg_gen_eqv_i64, 2, 26),
GEN_VX_LOGICAL_207(vnand, tcg_gen_nand_i64, 2, 22),
GEN_VX_LOGICAL_207(vorc, tcg_gen_orc_i64, 2, 21),
#define GEN_VXFORM(name, opc2, opc3) \
GEN_HANDLER(name, 0x04, opc2, opc3, 0x00000000, PPC_ALTIVEC)
#define GEN_VXFORM_207(name, opc2, opc3) \
GEN_HANDLER_E(name, 0x04, opc2, opc3, 0x00000000, PPC_NONE, PPC2_ALTIVEC_207)
#define GEN_VXFORM_300(name, opc2, opc3) \
GEN_HANDLER_E(name, 0x04, opc2, opc3, 0x00000000, PPC_NONE, PPC2_ISA300)
#define GEN_VXFORM_300_EXT(name, opc2, opc3, inval) \
GEN_HANDLER_E(name, 0x04, opc2, opc3, inval, PPC_NONE, PPC2_ISA300)
#define GEN_VXFORM_300_EO(name, opc2, opc3, opc4) \
GEN_HANDLER_E_2(name, 0x04, opc2, opc3, opc4, 0x00000000, PPC_NONE, \
PPC2_ISA300)
#define GEN_VXFORM_310(name, opc2, opc3) \
GEN_HANDLER_E(name, 0x04, opc2, opc3, 0x00000000, PPC_NONE, PPC2_ISA310)
#define GEN_VXFORM_DUAL(name0, name1, opc2, opc3, type0, type1) \
GEN_HANDLER_E(name0##_##name1, 0x4, opc2, opc3, 0x00000000, type0, type1)
#define GEN_VXRFORM_DUAL(name0, name1, opc2, opc3, tp0, tp1) \
GEN_HANDLER_E(name0##_##name1, 0x4, opc2, opc3, 0x00000000, tp0, tp1), \
GEN_HANDLER_E(name0##_##name1, 0x4, opc2, (opc3 | 0x10), 0x00000000, tp0, tp1),
GEN_VXFORM_DUAL(vaddubm, vmul10cuq, 0, 0, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM_DUAL(vadduhm, vmul10ecuq, 0, 1, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM(vadduwm, 0, 2),
GEN_VXFORM_207(vaddudm, 0, 3),
GEN_VXFORM_DUAL(vsububm, bcdadd, 0, 16, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM_DUAL(vsubuhm, bcdsub, 0, 17, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM_DUAL(vsubuwm, bcdus, 0, 18, PPC_ALTIVEC, PPC2_ISA300),
GEN_VXFORM_DUAL(vsubudm, bcds, 0, 19, PPC2_ALTIVEC_207, PPC2_ISA300),
GEN_VXFORM_300(bcds, 0, 27),
GEN_VXFORM(vmaxub, 1, 0),
GEN_VXFORM(vmaxuh, 1, 1),
GEN_VXFORM(vmaxuw, 1, 2),
GEN_VXFORM_207(vmaxud, 1, 3),
GEN_VXFORM(vmaxsb, 1, 4),
GEN_VXFORM(vmaxsh, 1, 5),
GEN_VXFORM(vmaxsw, 1, 6),
GEN_VXFORM_207(vmaxsd, 1, 7),
GEN_VXFORM(vminub, 1, 8),
GEN_VXFORM(vminuh, 1, 9),
GEN_VXFORM(vminuw, 1, 10),
GEN_VXFORM_207(vminud, 1, 11),
GEN_VXFORM(vminsb, 1, 12),
GEN_VXFORM(vminsh, 1, 13),
GEN_VXFORM(vminsw, 1, 14),
GEN_VXFORM_207(vminsd, 1, 15),
GEN_VXFORM(vmrghb, 6, 0),
GEN_VXFORM(vmrghh, 6, 1),
GEN_VXFORM(vmrghw, 6, 2),
GEN_VXFORM(vmrglb, 6, 4),
GEN_VXFORM(vmrglh, 6, 5),
GEN_VXFORM(vmrglw, 6, 6),
GEN_VXFORM_300(vextublx, 6, 24),
GEN_VXFORM_300(vextuhlx, 6, 25),
GEN_VXFORM_DUAL(vmrgow, vextuwlx, 6, 26, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_300(vextubrx, 6, 28),
GEN_VXFORM_300(vextuhrx, 6, 29),
GEN_VXFORM_DUAL(vmrgew, vextuwrx, 6, 30, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_207(vmuluwm, 4, 2),
GEN_VXFORM_300(vsrv, 2, 28),
GEN_VXFORM_300(vslv, 2, 29),
GEN_VXFORM(vslo, 6, 16),
GEN_VXFORM(vsro, 6, 17),
GEN_VXFORM(xpnd04_1, 0, 22),
GEN_VXFORM_300(bcdsr, 0, 23),
GEN_VXFORM_300(bcdsr, 0, 31),
GEN_VXFORM_DUAL(vaddubs, vmul10uq, 0, 8, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM_DUAL(vadduhs, vmul10euq, 0, 9, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM(vadduws, 0, 10),
GEN_VXFORM(vaddsbs, 0, 12),
GEN_VXFORM_DUAL(vaddshs, bcdcpsgn, 0, 13, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM(vaddsws, 0, 14),
GEN_VXFORM_DUAL(vsububs, bcdadd, 0, 24, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM_DUAL(vsubuhs, bcdsub, 0, 25, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM(vsubuws, 0, 26),
GEN_VXFORM_DUAL(vsubsbs, bcdtrunc, 0, 28, PPC_ALTIVEC, PPC2_ISA300),
GEN_VXFORM(vsubshs, 0, 29),
GEN_VXFORM_DUAL(vsubsws, xpnd04_2, 0, 30, PPC_ALTIVEC, PPC_NONE),
GEN_VXFORM_300(bcdtrunc, 0, 20),
GEN_VXFORM_300(bcdutrunc, 0, 21),
GEN_VXFORM(vsl, 2, 7),
GEN_VXFORM(vsr, 2, 11),
GEN_VXFORM(vpkuhum, 7, 0),
GEN_VXFORM(vpkuwum, 7, 1),
GEN_VXFORM_207(vpkudum, 7, 17),
GEN_VXFORM(vpkuhus, 7, 2),
GEN_VXFORM(vpkuwus, 7, 3),
GEN_VXFORM_207(vpkudus, 7, 19),
GEN_VXFORM(vpkshus, 7, 4),
GEN_VXFORM(vpkswus, 7, 5),
GEN_VXFORM_207(vpksdus, 7, 21),
GEN_VXFORM(vpkshss, 7, 6),
GEN_VXFORM(vpkswss, 7, 7),
GEN_VXFORM_207(vpksdss, 7, 23),
GEN_VXFORM(vpkpx, 7, 12),
GEN_VXFORM(vsum4ubs, 4, 24),
GEN_VXFORM(vsum4sbs, 4, 28),
GEN_VXFORM(vsum4shs, 4, 25),
GEN_VXFORM(vsum2sws, 4, 26),
GEN_VXFORM(vsumsws, 4, 30),
GEN_VXFORM(vaddfp, 5, 0),
GEN_VXFORM(vsubfp, 5, 1),
GEN_VXFORM(vmaxfp, 5, 16),
GEN_VXFORM(vminfp, 5, 17),
#define GEN_VXRFORM1(opname, name, str, opc2, opc3) \
GEN_HANDLER2(name, str, 0x4, opc2, opc3, 0x00000000, PPC_ALTIVEC),
#define GEN_VXRFORM1_300(opname, name, str, opc2, opc3) \
GEN_HANDLER2_E(name, str, 0x4, opc2, opc3, 0x00000000, PPC_NONE, PPC2_ISA300),
#define GEN_VXRFORM(name, opc2, opc3) \
GEN_VXRFORM1(name, name, #name, opc2, opc3) \
GEN_VXRFORM1(name##_dot, name##_, #name ".", opc2, (opc3 | (0x1 << 4)))
#define GEN_VXRFORM_300(name, opc2, opc3) \
GEN_VXRFORM1_300(name, name, #name, opc2, opc3) \
GEN_VXRFORM1_300(name##_dot, name##_, #name ".", opc2, (opc3 | (0x1 << 4)))
GEN_VXRFORM(vcmpeqfp, 3, 3)
GEN_VXRFORM(vcmpgefp, 3, 7)
GEN_VXRFORM(vcmpgtfp, 3, 11)
GEN_VXRFORM(vcmpbfp, 3, 15)
#define GEN_VXFORM_DUAL_INV(name0, name1, opc2, opc3, inval0, inval1, type) \
GEN_OPCODE_DUAL(name0##_##name1, 0x04, opc2, opc3, inval0, inval1, type, \
PPC_NONE)
GEN_VXFORM_DUAL_INV(vspltb, vextractub, 6, 8, 0x00000000, 0x100000,
PPC_ALTIVEC),
GEN_VXFORM_DUAL_INV(vsplth, vextractuh, 6, 9, 0x00000000, 0x100000,
PPC_ALTIVEC),
GEN_VXFORM_DUAL_INV(vspltw, vextractuw, 6, 10, 0x00000000, 0x100000,
PPC_ALTIVEC),
GEN_VXFORM_300_EXT(vextractd, 6, 11, 0x100000),
GEN_VXFORM(vspltisb, 6, 12),
GEN_VXFORM(vspltish, 6, 13),
GEN_VXFORM(vspltisw, 6, 14),
GEN_VXFORM_300_EO(vctzb, 0x01, 0x18, 0x1C),
GEN_VXFORM_300_EO(vctzh, 0x01, 0x18, 0x1D),
GEN_VXFORM_300_EO(vctzw, 0x01, 0x18, 0x1E),
GEN_VXFORM_300_EO(vctzd, 0x01, 0x18, 0x1F),
GEN_VXFORM_300_EO(vclzlsbb, 0x01, 0x18, 0x0),
GEN_VXFORM_300_EO(vctzlsbb, 0x01, 0x18, 0x1),
#define GEN_VXFORM_NOA(name, opc2, opc3) \
GEN_HANDLER(name, 0x04, opc2, opc3, 0x001f0000, PPC_ALTIVEC)
GEN_VXFORM_NOA(vupkhsb, 7, 8),
GEN_VXFORM_NOA(vupkhsh, 7, 9),
GEN_VXFORM_207(vupkhsw, 7, 25),
GEN_VXFORM_NOA(vupklsb, 7, 10),
GEN_VXFORM_NOA(vupklsh, 7, 11),
GEN_VXFORM_207(vupklsw, 7, 27),
GEN_VXFORM_NOA(vupkhpx, 7, 13),
GEN_VXFORM_NOA(vupklpx, 7, 15),
GEN_VXFORM_NOA(vrefp, 5, 4),
GEN_VXFORM_NOA(vrsqrtefp, 5, 5),
GEN_VXFORM_NOA(vexptefp, 5, 6),
GEN_VXFORM_NOA(vlogefp, 5, 7),
GEN_VXFORM_NOA(vrfim, 5, 11),
GEN_VXFORM_NOA(vrfin, 5, 8),
GEN_VXFORM_NOA(vrfip, 5, 10),
GEN_VXFORM_NOA(vrfiz, 5, 9),
#define GEN_VXFORM_UIMM(name, opc2, opc3) \
GEN_HANDLER(name, 0x04, opc2, opc3, 0x00000000, PPC_ALTIVEC)
GEN_VXFORM_UIMM(vcfux, 5, 12),
GEN_VXFORM_UIMM(vcfsx, 5, 13),
GEN_VXFORM_UIMM(vctuxs, 5, 14),
GEN_VXFORM_UIMM(vctsxs, 5, 15),
#define GEN_VAFORM_PAIRED(name0, name1, opc2) \
GEN_HANDLER(name0##_##name1, 0x04, opc2, 0xFF, 0x00000000, PPC_ALTIVEC)
GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23),
GEN_VXFORM_DUAL(vclzb, vpopcntb, 1, 28, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_DUAL(vclzh, vpopcnth, 1, 29, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_DUAL(vclzw, vpopcntw, 1, 30, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_DUAL(vclzd, vpopcntd, 1, 31, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_300(vbpermd, 6, 23),
GEN_VXFORM_207(vbpermq, 6, 21),
GEN_VXFORM_207(vgbbd, 6, 20),
GEN_VXFORM_207(vpmsumb, 4, 16),
GEN_VXFORM_207(vpmsumh, 4, 17),
GEN_VXFORM_207(vpmsumw, 4, 18),
GEN_VXFORM_207(vsbox, 4, 23),
GEN_VXFORM_DUAL(vcipher, vcipherlast, 4, 20, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_DUAL(vncipher, vncipherlast, 4, 21, PPC_NONE, PPC2_ALTIVEC_207),
GEN_VXFORM_207(vshasigmaw, 1, 26),
GEN_VXFORM_207(vshasigmad, 1, 27),
GEN_VXFORM_DUAL(vsldoi, vpermxor, 22, 0xFF, PPC_ALTIVEC, PPC_NONE),
Reference in New Issue View Git Blame Copy Permalink