MIPS: math-emu: Add support for the MIPS R6 MADDF FPU instruction

MIPS R6 introduced the following instruction:
Floating Point Fused Multiply Add:
MADDF.fmt To perform a fused multiply-add of FP values.

MADDF.fmt: FPR[fd] = FPR[fd] + (FPR[fs] x FPR[ft])

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/10956/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This commit is contained in:
Markos Chandras
2015-08-13 09:56:31 +02:00
committed by Ralf Baechle
parent 130fe357ee
commit e24c3bec3e
5 changed files with 553 additions and 2 deletions

View File

@@ -1765,6 +1765,19 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
rv.w = 0;
break;
case fmaddf_op: {
union ieee754sp ft, fs, fd;
if (!cpu_has_mips_r6)
return SIGILL;
SPFROMREG(ft, MIPSInst_FT(ir));
SPFROMREG(fs, MIPSInst_FS(ir));
SPFROMREG(fd, MIPSInst_FD(ir));
rv.s = ieee754sp_maddf(fd, fs, ft);
break;
}
case fabs_op:
handler.u = ieee754sp_abs;
goto scopuop;
@@ -1985,6 +1998,19 @@ copcsr:
rv.l = 0;
break;
case fmaddf_op: {
union ieee754dp ft, fs, fd;
if (!cpu_has_mips_r6)
return SIGILL;
DPFROMREG(ft, MIPSInst_FT(ir));
DPFROMREG(fs, MIPSInst_FS(ir));
DPFROMREG(fd, MIPSInst_FD(ir));
rv.d = ieee754dp_maddf(fd, fs, ft);
break;
}
case fabs_op:
handler.u = ieee754dp_abs;
goto dcopuop;