Displaying 8 results from an estimated 8 matches for "ftst".
Did you mean:
fast
2005 Mar 16
0
[LLVMdev] Floating point compare instruction selection
...s also
> generated! As far as I can tell it should return right after this:
>
> BuildMI(BB, X86::SAHF, 1);
>
> instead it falls through and goes on to generate the normal compare
> instruction... Am I right?
Nope. It's emitting a compare against zero with fucomi instead of ftst.
fucomi is a PPRO+ instruction that deposits the result of the comparison
into the integer condition codes. This saves having to use SAHF and some
bit-twiddling, so it's usually a bit faster than using ftst. The simple
isel used to produce ftst for compare against zero. If you do some
be...
2005 Mar 16
2
[LLVMdev] Floating point compare instruction selection
Hello,
I didn't get any reply to my previous mail about adding floating point intrinsics to the X86 pattern instruction
selector... And I could really need some help. Anyway, I think my confusion was caused partly by an already existing bug
in the instruction selection for floating point compares.
The case which emits code for the special case of comparing against constant 0.0 does not
2005 Mar 17
1
[LLVMdev] Floating point compare instruction selection
...tell it should return right
>> after this:
>>
>> BuildMI(BB, X86::SAHF, 1);
>>
>> instead it falls through and goes on to generate the normal compare
>> instruction... Am I right?
>
> Nope. It's emitting a compare against zero with fucomi instead of ftst.
> fucomi is a PPRO+ instruction that deposits the result of the comparison
> into the integer condition codes. This saves having to use SAHF and some
> bit-twiddling, so it's usually a bit faster than using ftst. The simple
> isel used to produce ftst for compare against zero....
2005 Mar 11
0
[LLVMdev] FP Intrinsics
...431 mov dword ptr ds:[161D624Ch],0
1716043B mov eax,76E4560h
17160440 mov dword ptr [esp],eax
17160443 call HueVMReadCommands_LLVMReadVoxel (19BB229h)
17160448 fsub dword ptr ds:[161D6280h]
1716044E fabs
17160450 fst qword ptr [esp+14h]
17160454 ftst
17160456 fstp st(0)
17160458 fnstsw ax
1716045A sahf
1716045B fldz
1716045D fchs
1716045F fld qword ptr [esp+14h]
17160463 fucomip st,st(1)
17160465 fstp st(0)
17160467 jbe 17160498
1716046D mov eax,76E4F60h
17160472 mov dword ptr [e...
2010 May 18
2
Function that is giving me a headache- any help appreciated (automatic read )
...is the Waynesboro Gauge on the Savannah River Proper (SRS)
#02102908 is the Flat Creek Gauge (ftbrfcms)
#02133500 is the Drowning Creek (ftbrbmcm)
#02341800 is the Upatoi Creek Near Columbus (ftbn)
#02342500 is the Uchee Creek Near Fort Mitchell (ftbn)
#02203000 is the Canoochee River Near Claxton (ftst)
#02196690 is the Horse Creek Gauge at Clearwater, S.C.
a <- "http://waterdata.usgs.gov/nwis/uv?format=rdb&period="
b <- "&site_no=021973269,02102908,02133500,02341800,02342500,02203000,02196690"
z <- paste(a, days, b, sep="")
L <- readLines(z)
#l...
2005 May 13
1
[LLVMdev] gmake check failures on FreeBSD
...iled: (isNew && "Got into the map somehow?"), function
AddLegalizedOperand, file
/usr/home/llvm/obj/../lib/CodeGen/SelectionDAG/LegalizeDAG.cpp, line 79.
.text
.align 16
.globl test1
.type test1, @function
test1:
fldl 4(%esp)
ftst
fstp %st(0)
fnstsw
sahf
setne %al
movzbl %al, %eax
#FP_REG_KILL
ret
Abort trap (core dumped)
FAIL:
/usr/home/llvm/obj/../test/Regression/CodeGen/X86/fast-cc-pass-in-regs.ll:
Does not have a RUN line
Running /usr/home/llvm/obj/../test/Regres...
2009 Oct 06
1
ggplot2 applying a function based on facet
...is the Waynesboro Gauge on the Savannah River Proper (SRS)
#02102908 is the Flat Creek Gauge (ftbrfcms)
#02133500 is the Drowning Creek (ftbrbmcm)
#02341800 is the Upatoi Creek Near Columbus (ftbn)
#02342500 is the Uchee Creek Near Fort Mitchell (ftbn)
#02203000 is the Canoochee River Near Claxton (ftst)
a <- "http://waterdata.usgs.gov/nwis/uv?format=rdb&period="
b <- "&site_no=021973269,02102908,02133500,02341800,02342500,02203000"
z <- paste(a, days, b, sep="")
L <- readLines(z)
#look for the data with USGS in front of it (this take advantage o...
2005 Mar 11
5
[LLVMdev] FP Intrinsics
Hello,
I am trying to make the FP intrinsics (abs, sin, cos, sqrt) I've added
work with the X86ISelPattern, but I'm having some difficulties
understanding what needs to be done. I assume I have to add new
nodetypes for the FP instructions to SelectionDAGNodes.h, and make nodes
for these in SelectionDAGLowering::visitCall when I find the intrinsic...
The part I don't quite