[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

Aaron Watry  changed:

   What|Removed |Added

 Status|NEW |RESOLVED
 Resolution|--- |FIXED

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #14 from Aaron Watry  ---
I still get errors with the v8i32/v16i32 loads, but those aren't currently
enabled in the R600 or SI back-ends as far as I know.

If I comment out the vload8 and vload16 tests everything runs correctly for me
on my 7850 with git master llvm/clang and my vload/vstore changes for libclc.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #13 from Tom Stellard  ---
(In reply to comment #9)
> The piglit test should work with this patch:
> http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20130624/179364.
> html
> 
> But we should still try to fix the bug in libclc.

I've just pushed this patch.  What is the status of this bug with your
vstore/vload fixes?

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #13 from Tom Stellard tstel...@gmail.com ---
(In reply to comment #9)
 The piglit test should work with this patch:
 http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20130624/179364.
 html
 
 But we should still try to fix the bug in libclc.

I've just pushed this patch.  What is the status of this bug with your
vstore/vload fixes?

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #14 from Aaron Watry awa...@gmail.com ---
I still get errors with the v8i32/v16i32 loads, but those aren't currently
enabled in the R600 or SI back-ends as far as I know.

If I comment out the vload8 and vload16 tests everything runs correctly for me
on my 7850 with git master llvm/clang and my vload/vstore changes for libclc.

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

Aaron Watry awa...@gmail.com changed:

   What|Removed |Added

 Status|NEW |RESOLVED
 Resolution|--- |FIXED

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #12 from Aaron Watry  ---
No problem.  I'll just revert the vload/vstore code to pure CLC implementations
and then override with assembly in the R600 back-end.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #11 from Tom Stellard  ---
(In reply to comment #10)
> I've got a draft fix in my libclc repo on fdo.o.  I've tested for
> regressions on Cedar (successfully), and I will test on SI with your 64-bit
> load patch asap (hopefully tonight, but we'll see).

I took a look at your libclc fix, and I realized that we can't use address
space qualifiers in common code, because addrspace(1) may not mean global
address space on all targets.

I think you might find that the optimizers are good enough to turn a .cl
implementation into optimal code, but if not we may be have to move the LLVM IR
implementations into target specific code.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #12 from Aaron Watry awa...@gmail.com ---
No problem.  I'll just revert the vload/vstore code to pure CLC implementations
and then override with assembly in the R600 back-end.

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #10 from Aaron Watry  ---
I've got a draft fix in my libclc repo on fdo.o.  I've tested for regressions
on Cedar (successfully), and I will test on SI with your 64-bit load patch asap
(hopefully tonight, but we'll see).

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #9 from Tom Stellard  ---
The piglit test should work with this patch:
http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20130624/179364.html

But we should still try to fix the bug in libclc.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #8 from Aaron Watry  ---
"Pointers on SI are 64-bit."

Talk about a "duh" moment. I'll see what I can do to fix and test the
vload/vstore implementation pointer generation since this is broken on SI,
maybe 64-bit PTX, and would also be broken on x86_64 (and others) if we ever
get around to supporting CPU targets in libclc.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #7 from Tom Stellard  ---
The SI backend needs to be fixed so it can handle zext i64 loads, but there is
also a bug in libclc.  The vload implementation assumes pointer types are
32-bit:

define <2 x i32> @__clc_vload2_impl_i32__global(i32 %offset,  i32 addrspace(1)*
nocapture %addr) nounwind readonly alwaysinline {
  %1 = ptrtoint i32 addrspace(1)* %addr to i32
  %2 = add i32 %1, %offset
  %3 = inttoptr i32 %2 to <2 x i32> addrspace(1)*
  %4 = load <2 x i32> addrspace(1)* %3, align 4, !tbaa !3
  ret <2 x i32> %4
}

Pointers on SI are 64-bit.  This ptrtoint, add, inttoptr sequence should be
replaced with a getelementptr and a bitcast.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #7 from Tom Stellard tstel...@gmail.com ---
The SI backend needs to be fixed so it can handle zext i64 loads, but there is
also a bug in libclc.  The vload implementation assumes pointer types are
32-bit:

define 2 x i32 @__clc_vload2_impl_i32__global(i32 %offset,  i32 addrspace(1)*
nocapture %addr) nounwind readonly alwaysinline {
  %1 = ptrtoint i32 addrspace(1)* %addr to i32
  %2 = add i32 %1, %offset
  %3 = inttoptr i32 %2 to 2 x i32 addrspace(1)*
  %4 = load 2 x i32 addrspace(1)* %3, align 4, !tbaa !3
  ret 2 x i32 %4
}

Pointers on SI are 64-bit.  This ptrtoint, add, inttoptr sequence should be
replaced with a getelementptr and a bitcast.

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #8 from Aaron Watry awa...@gmail.com ---
Pointers on SI are 64-bit.

Talk about a duh moment. I'll see what I can do to fix and test the
vload/vstore implementation pointer generation since this is broken on SI,
maybe 64-bit PTX, and would also be broken on x86_64 (and others) if we ever
get around to supporting CPU targets in libclc.

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #9 from Tom Stellard tstel...@gmail.com ---
The piglit test should work with this patch:
http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20130624/179364.html

But we should still try to fix the bug in libclc.

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #10 from Aaron Watry awa...@gmail.com ---
I've got a draft fix in my libclc repo on fdo.o.  I've tested for regressions
on Cedar (successfully), and I will test on SI with your 64-bit load patch asap
(hopefully tonight, but we'll see).

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #11 from Tom Stellard tstel...@gmail.com ---
(In reply to comment #10)
 I've got a draft fix in my libclc repo on fdo.o.  I've tested for
 regressions on Cedar (successfully), and I will test on SI with your 64-bit
 load patch asap (hopefully tonight, but we'll see).

I took a look at your libclc fix, and I realized that we can't use address
space qualifiers in common code, because addrspace(1) may not mean global
address space on all targets.

I think you might find that the optimizers are good enough to turn a .cl
implementation into optimal code, but if not we may be have to move the LLVM IR
implementations into target specific code.

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

Aaron Watry  changed:

   What|Removed |Added

  Attachment #80972|0   |1
is obsolete||

--- Comment #6 from Aaron Watry  ---
Created attachment 81038
  --> https://bugs.freedesktop.org/attachment.cgi?id=81038=edit
Output from llc -debug-only=isel --march=r600 --mcpu=verde < vload-int.ll

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

Aaron Watry  changed:

   What|Removed |Added

  Attachment #80971|0   |1
is obsolete||

--- Comment #5 from Aaron Watry  ---
Created attachment 81037
  --> https://bugs.freedesktop.org/attachment.cgi?id=81037=edit
LLVM Assembly that is produced from vload-int.cl (after first patch)

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #4 from Aaron Watry  ---
The good news is that the store error is gone...

Now I get a load error :/

LLVM ERROR: Cannot select: 0x2c92af0: i64,ch = load 0x21fe0c8, 0x2c924f0,
0x2c921f0 [ID=15]
  0x2c924f0: i64 = add 0x2c91ef0, 0x2c923f0 [ID=13]
0x2c91ef0: i64,ch = CopyFromReg 0x21fe0c8, 0x2c91df0 [ID=12]
  0x2c91df0: i64 = Register %vreg0 [ID=1]
0x2c923f0: i64 = Constant<44> [ID=4]
  0x2c921f0: i64 = undef [ID=3]

I'll attach the llvm assembly in a follow-up

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #3 from Tom Stellard  ---
These patches should fix the issue:

http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20130617/178156.html

The first patch is unrelated to the bug, but it is required in order to prevent
the test case in the second patch from crashing on Cayman.  I've tested this on
llc, can you verify it works on real hardware.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #2 from Aaron Watry  ---
Created attachment 80972
  --> https://bugs.freedesktop.org/attachment.cgi?id=80972=edit
Output from llc -debug-only=isel --march=r600 --mcpu=verde < vload-int.ll

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-dae...@freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #1 from Aaron Watry  ---
Created attachment 80971
  --> https://bugs.freedesktop.org/attachment.cgi?id=80971=edit
LLVM assembly that is produced from the vload-int.cl test case

-- 
You are receiving this mail because:
You are the assignee for the bug.
-- next part --
An HTML attachment was scrubbed...
URL: 

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #3 from Tom Stellard tstel...@gmail.com ---
These patches should fix the issue:

http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20130617/178156.html

The first patch is unrelated to the bug, but it is required in order to prevent
the test case in the second patch from crashing on Cayman.  I've tested this on
llc, can you verify it works on real hardware.

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #4 from Aaron Watry awa...@gmail.com ---
The good news is that the store error is gone...

Now I get a load error :/

LLVM ERROR: Cannot select: 0x2c92af0: i64,ch = load 0x21fe0c8, 0x2c924f0,
0x2c921f0LD4[undef](align=8), zext from i32 [ID=15]
  0x2c924f0: i64 = add 0x2c91ef0, 0x2c923f0 [ID=13]
0x2c91ef0: i64,ch = CopyFromReg 0x21fe0c8, 0x2c91df0 [ID=12]
  0x2c91df0: i64 = Register %vreg0 [ID=1]
0x2c923f0: i64 = Constant44 [ID=4]
  0x2c921f0: i64 = undef [ID=3]

I'll attach the llvm assembly in a follow-up

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

Aaron Watry awa...@gmail.com changed:

   What|Removed |Added

  Attachment #80971|0   |1
is obsolete||

--- Comment #5 from Aaron Watry awa...@gmail.com ---
Created attachment 81037
  -- https://bugs.freedesktop.org/attachment.cgi?id=81037action=edit
LLVM Assembly that is produced from vload-int.cl (after first patch)

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

Aaron Watry awa...@gmail.com changed:

   What|Removed |Added

  Attachment #80972|0   |1
is obsolete||

--- Comment #6 from Aaron Watry awa...@gmail.com ---
Created attachment 81038
  -- https://bugs.freedesktop.org/attachment.cgi?id=81038action=edit
Output from llc -debug-only=isel --march=r600 --mcpu=verde  vload-int.ll

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #1 from Aaron Watry awa...@gmail.com ---
Created attachment 80971
  -- https://bugs.freedesktop.org/attachment.cgi?id=80971action=edit
LLVM assembly that is produced from the vload-int.cl test case

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 65873] R600/SI: Cannot select store with truncate to 32-bit

[bugzilla-daemon]

https://bugs.freedesktop.org/show_bug.cgi?id=65873

--- Comment #2 from Aaron Watry awa...@gmail.com ---
Created attachment 80972
  -- https://bugs.freedesktop.org/attachment.cgi?id=80972action=edit
Output from llc -debug-only=isel --march=r600 --mcpu=verde  vload-int.ll

-- 
You are receiving this mail because:
You are the assignee for the bug.
___
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel