Skip to content

S
swiftshader
Switch branch/tag
  1. 07 Aug, 2014 2 commits
    • Subzero: Use scalar arithmetic when no vector instruction exists. · afeaee41
      Matt Wala authored 
      Implement scalarizeArithmetic() which extracts the components of the
input vectors, performs the operation with scalar instructions, and
builds the output vector component by component.

Fix the lowering of sdiv and srem.  These were previously emitting a
wrong instruction (cdq) for i8 and i16 inputs (needing cbw, cwd).

In the test_arith crosstest, mask the inputs to vector shift
operations to ensure that the shifts are in range.  Otherwise the
Subzero output is not identical to the llc output in some (undefined)
cases.

BUG=none
R=stichnot@chromium.org

Review URL: https://codereview.chromium.org/443203003
    • Subzero: A few fixes toward running larger programs. · 206833c6
      Jim Stichnoth authored 
      1. Add 'llvm2ice -disable-globals' to disable Subzero translation of
global initializers, since full support isn't yet implemented.

2. Change the names of intra-block branch target labels to avoid
collisions with basic block labels.

3. Fix lowering of "br i1 <constant>, label ...", which was producing
invalid instructions like "cmp 1, 0".

4. Fix the "make format-diff" operation, which was diffing against the wrong target.

BUG= none
R=wala@chromium.org

Review URL: https://codereview.chromium.org/449093002
  3. 05 Aug, 2014 1 commit
    • Subzero: Fix and clean up some cross tests. · 7da431b5
      Jim Stichnoth authored 
      1. It turns out that the crosstest scripts mix different versions of
clang - build_pnacl_ir.py uses pnacl-clang from the NaCl SDK for the
tests, while crosstest.py uses clang/clang++ from LLVM_BIN_PATH for
the driver.  The SDK has been updated to use a different version of
the standard library, and now there is a mismatch as to whether int8_t
is typedef'd to 'char' or 'signed char', leading to name mangling
mismatches.  (char, signed char, and unsigned char are distinct
types.)  We deal with this by using myint8_t which is explicitly
defined as signed char.

2. Some ugly function pointer casting in test_arith_main.cpp is fixed/removed.

3. std::endl is replaced with "\n".

4. License text is added to tests that were touched by the above items.

BUG= none
R=wala@chromium.org

Review URL: https://codereview.chromium.org/435353002
  5. 31 Jul, 2014 1 commit
    • Subzero: Fix some issues related to legalization and undef handling. · e377767c
      Matt Wala authored 
      1. Much of the lowering code for vector operations was not properly
checking that the input operand was in a register or memory. This
problem could be exhibited by passing undef values as inputs.

=> Change the vector legalization code to legalize input operands to
register or memory before producing instructions that use the
operands. Also, append a suffix to the variable names in the vector
legalization code to clarify the legalization status of the values.

2. Undef values should never be emitted directly. Rather, they should
have been appropriately legalized to a zero value.

=> To enforce this, make ConstantUndef::emit() issue an error
message. Do this in the x86 backend, as other backends may decide to
treat undef values differently.

3. The regalloc_evict_non_overlap test was loading from an undef
pointer. Subzero was not handling this correctly (the undef pointer was
being emitted without being legalized), but it does not have to handle
this case since PNaCl IR disallows undef pointers.

=> Fix the regalloc_evict_non_overlap test to use an inttoptr instead of
directly loading from the undef pointer. Also, add an assert in
IceTargetLoweringX8632::FormMemoryOperand() to make sure that undef
pointers are never encountered.

BUG=none
R=jvoung@chromium.org, stichnot@chromium.org

Review URL: https://codereview.chromium.org/432613002
  7. 30 Jul, 2014 6 commits
  9. 29 Jul, 2014 1 commit
  11. 28 Jul, 2014 2 commits
    • A couple of fixes for using Makefile.standalone on Mac. · 839c4cea
      Jan Voung authored 
      (*) PNaCl toolchain_build builds 64-bit libraries for LLVM on Mac.
    That won't link with subzero code if subzero is built with -m32,
    so add an option to override the -m32.
(*) include locale header
(*) Mark xMacroIntegrityCheck unused to avoid clang compiler warning.
(*) virtual dtor, for inheritable class
(*) Mark compare function const

BUG=none
R=stichnot@chromium.org

Review URL: https://codereview.chromium.org/428733003
    • Subzero: Make Ice::Ostream a typedef for llvm::raw_ostream. · 78282f6c
      Jim Stichnoth authored 
      Previously Ostream was a class that wrapped a raw_ostream pointer,
structured that way in case we wanted to wrap an alternate stream
type.

Also, Ostream used to include a Cfg pointer, but that had to go away
when the Ostream became associated with the GlobalContext which
persists beyond the Cfg lifetime, so the Cfg pointer was removed
leaving only the raw_ostream.

Since llvm::raw_ostream is supposed to be very lightweight, we can
just give up the abstraction and equate it to Ice::Ostream.

BUG= none
R=kschimpf@google.com

Review URL: https://codereview.chromium.org/413393005
  13. 25 Jul, 2014 1 commit
  15. 24 Jul, 2014 4 commits
  17. 23 Jul, 2014 3 commits
  19. 22 Jul, 2014 3 commits
  21. 21 Jul, 2014 1 commit
  23. 18 Jul, 2014 4 commits
  25. 17 Jul, 2014 1 commit
    • Lower the rest of the vector arithmetic operations. · 7fa22d8a
      Matt Wala authored 
      The instructions emitted by the lowering operations require memory
operands to be aligned to 16 bytes. Since there is no support for
aligning memory operands in Subzero, do the arithmetic in registers for
now.

Add vector arithmetic to the arith crosstest. Pass the -mstackrealign
parameter to the crosstest clang so that llc code called back from
Subzero code (helper calls) doesn't assume that the stack is aligned at
the entry to the call.

BUG=none
R=jvoung@chromium.org, stichnot@chromium.org

Review URL: https://codereview.chromium.org/397833002
  27. 16 Jul, 2014 2 commits
    • Lower casting operations that involve vector types. · 83b8036b
      Matt Wala authored 
      Impacted instructions:

bitcast {v4f32, v4i32, v8i16, v16i8} <-> {v4f32, v4i32, v8i16, v16i8}
bitcast v8i1 <-> i8
bitcast v16i1 <-> i16

(There was already code present to handle trivial bitcasts like v16i1 <-> v16i1.)

[sz]ext v4i1 -> v4i32
[sz]ext v8i1 -> v8i16
[sz]ext v16i1 -> v16i8

trunc v4i32 -> v4i1
trunc v8i16 -> v8i1
trunc v16i8 -> v16i1

[su]itofp v4i32 -> v4f32
fpto[su]i v4f32 -> v4i32

Where there is a relatively simple lowering to x86 instructions, it has been used. Otherwise a helper call is used.

Some lowerings require a materialization of a integer vector with 1s in each entry. Since there is no support for vector constant pools, the constant is materialized purely through register operations.

BUG=none
R=jvoung@chromium.org, stichnot@chromium.org

Review URL: https://codereview.chromium.org/383303003
    • Lower bitmanip intrinsics, assuming absence of BMI/SSE4.2 for now. · e4da26f6
      Jan Voung authored 
      We'll need the fallbacks in any case. However, once we've
decided on how to specify the CPU features of the user
machine we can use the nicer LZCNT/TZCNT/POPCNT as well.

Adds cmov, bsf, and bsr instructions.

Calls a popcount helper function for machines without SSE4.2.

Not handling bswap yet (which can also take i16 params).

BUG= https://code.google.com/p/nativeclient/issues/detail?id=3882
R=stichnot@chromium.org, wala@chromium.org

Review URL: https://codereview.chromium.org/390443005
  29. 15 Jul, 2014 2 commits
  31. 14 Jul, 2014 2 commits
  33. 11 Jul, 2014 4 commits