kernel/linux.git/arch/arm/vfp/vfpdouble.c, branch linux-7.0.y

ARM: 8026/1: Fix emulation of multiply accumulate instructions

2014-04-14T22:28:24+00:00

The emulation for single and double precision multiply accumulate instructions correctly normalised any denormal values in the operand registers, but failed to normalise the destination (accumulator) register. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=70501 Signed-off-by: Jay Foad Signed-off-by: Russell King

[ARM] vfp: fix fuitod/fsitod instructions

2008-01-10T17:07:08+00:00

These two instructions exceptionally take a single precision register as their operand. This means we can't use vfp_get_dm() to read the register number - we need to use vfp_get_sm() instead. Add a flag to indicate this exception to the general rule. Signed-off-by: Russell King

[ARM] 4630/1: Fix the vector stride of the double vector instruction.

2007-10-20T22:42:22+00:00

The vector stride of the double-precision vector instructions must be changed to 1-2 from even 2-4, because the double registers numbering has been changed to 0-15 from even 0-30 by 1356c1948da967bc1d4c663762bfe21dfcec4b2f commit. Signed-off-by: Takashi Ohmasa Signed-off-by: Russell King

[ARM] Remove unnecessary asm/ptrace.h from VFP support code

2007-04-22T09:56:40+00:00

Signed-off-by: Russell King

[ARM] 3899/1: Fix the normalization of the denormal double precision number.

2006-10-28T09:15:31+00:00

The significand should be shifted until the value of bit [62] is 1 to normalize the denormal double number. Signed-off-by: Takashi Ohmasa Signed-off-by: Russell King

[ARM] Cleanups for 4cc9bd2eaa1063c68341c1c00e66660adcfdf254

2006-09-25T09:34:59+00:00

- Document the meaning for OP_SCALAR, OP_SD and add OP_DD. - Formatting cleanups - Remove now redundant code for making compare instructions operate on scalar values. Signed-off-by: Russell King

[ARM] 3789/4: Fix VFP emulation to ignore VECITR for scalar instruction

2006-09-25T09:34:06+00:00

VECITR in Floating-Point Exception register indicates the number of remaining short vector iterations after a potential exception was detected. In case of exception caused by scalar instructions, VECITR is NOT updated. Therefore emulation for VFP must ignore VECITR field and treat "veclen" as zero when recognizing scalar instructing. Signed-off-by: Gen Fukatsu Signed-off-by: Russell King

[ARM] 3750/3: Fix double VFP emulation for EABI kernels

2006-08-30T14:06:39+00:00

Patch from Daniel Jacobowitz vfp_put_double didn't work in a CONFIG_AEABI kernel. By swapping the arguments, we arrange for them to be in the same place regardless of ABI. I made the same change to vfp_put_float for consistency. Signed-off-by: Daniel Jacobowitz Signed-off-by: Russell King

[ARM] 3758/1: Preserve signalling NaNs in conversion

2006-08-27T11:42:14+00:00

Patch from Daniel Jacobowitz The fcvtds and fcvtsd instructions were generating a qnan bit pattern for both quiet and signalling NaNs. Signed-off-by: Daniel Jacobowitz Signed-off-by: Russell King

[ARM] 3749/3: Correct VFP single/double conversion emulation

2006-08-27T11:42:10+00:00

Patch from Daniel Jacobowitz The fcvtsd/fcvtds emulation was left behind when the numbering of double precision registers was changed from 0-30 to 0-15. Both conversion instructions were writing their results to the wrong register. Also, the conversion instructions should stop after the first element even if a vector length is specified. Signed-off-by: Daniel Jacobowitz Signed-off-by: Russell King