Commit Graph

17 Commits

Author SHA1 Message Date
Tom Stellard 50122a5890 R600: Match 24-bit arithmetic patterns in a Target DAGCombine
Moving these patterns from TableGen files to PerformDAGCombine()
should allow us to generate better code by eliminating unnecessary
shifts and extensions earlier.

This also fixes a bug where the MAD pattern was calling
SimplifyDemandedBits with a 24-bit mask on the first operand
even when the full pattern wasn't being matched.  This occasionally
resulted in some instructions being incorrectly deleted from the
program.

v2:
  - Fix bug with 64-bit mul

llvm-svn: 205731
2014-04-07 19:45:41 +00:00
Matt Arsenault fae02989b7 R600: Match sign_extend_inreg to BFE instructions
llvm-svn: 204072
2014-03-17 18:58:11 +00:00
Tom Stellard 348273df97 R600: Recommit 199842: Add work-around for the CF stack entry HW bug
The unit test is now disabled on non-asserts builds.

The CF stack can be corrupted if you use CF_ALU_PUSH_BEFORE,
CF_ALU_ELSE_AFTER, CF_ALU_BREAK, or CF_ALU_CONTINUE when the number of
sub-entries on the stack is greater than or equal to the stack entry
size and sub-entries modulo 4 is either 0 or 3 (on cedar the bug is
present when number of sub-entries module 8 is either 7 or 0)

We choose to be conservative and always apply the work-around when the
number of sub-enries is greater than or equal to the stack entry size,
so that we can safely over-allocate the stack when we are unsure of the
stack allocation rules.

reviewed-by: Vincent Lejeune <vljn at ovi.com>
llvm-svn: 199905
2014-01-23 16:18:02 +00:00
Tom Stellard 31e16388d7 Revert "R600: Add work-around for the CF stack entry HW bug"
This reverts commit 35b8331cad6eb512a2506adbc394201181da94ba.

The -debug-only flag for llc doesn't appear to be available in
all build configurations.

llvm-svn: 199845
2014-01-22 22:20:54 +00:00
Tom Stellard e89373e062 R600: Add work-around for the CF stack entry HW bug
The CF stack can be corrupted if you use CF_ALU_PUSH_BEFORE,
CF_ALU_ELSE_AFTER, CF_ALU_BREAK, or CF_ALU_CONTINUE when the number of
sub-entries on the stack is greater than or equal to the stack entry
size and sub-entries modulo 4 is either 0 or 3 (on cedar the bug is
present when number of sub-entries module 8 is either 7 or 0)

We choose to be conservative and always apply the work-around when the
number of sub-enries is greater than or equal to the stack entry size,
so that we can safely over-allocate the stack when we are unsure of the
stack allocation rules.

reviewed-by: Vincent Lejeune <vljn at ovi.com>
llvm-svn: 199842
2014-01-22 21:55:46 +00:00
Tom Stellard a40f97154b R600: Refactor stack size calculation
reviewed-by: Vincent Lejeune <vljn at ovi.com>
llvm-svn: 199840
2014-01-22 21:55:43 +00:00
Tom Stellard 8c347b024e R600: Add wavefront size property to the subtargets v2
v2:
  - Initialize wavefront size to 0

reviewed-by: Vincent Lejeune <vljn at ovi.com>
llvm-svn: 199838
2014-01-22 21:55:40 +00:00
Rafael Espindola ceb0c4962a Turn AMDGPUSubtarget::getDataLayout into a static function.
No functionality change.

llvm-svn: 197310
2013-12-14 06:13:44 +00:00
Tom Stellard 783893a893 R600: Add a SubtargetFeatture for disabling the ifcvt pass.
This is useful when writing test cases for the AMDIL structurizer.

llvm-svn: 195029
2013-11-18 19:43:33 +00:00
Tom Stellard 6e1ee476ab R600/SI: Add compute support for CI v2
v2:
  - Fix LDS size calculation

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 193621
2013-10-29 16:37:28 +00:00
Tom Stellard ed0ceec1c1 R600: Use StructurizeCFGPass for non SI targets
StructurizeCFG pass allows to make complex cfg reducible ; it allows a lot of
shader from shadertoy (which exhibits complex control flow constructs) to works
correctly with respect to CFG handling (and allow us to detect potential bug in
other part of the backend).

We provide a cmd line argument to disable the pass for debug purpose.

Patch by: Vincent Lejeune

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 192363
2013-10-10 17:11:12 +00:00
Andrew Trick 978674b2bc Allow subtarget selection of the default MachineScheduler and document the interface.
The global registry is used to allow command line override of the
scheduler selection, but does not work well as the normal selection
API. For example, the same LLVM process should be able to target
multiple targets or subtargets.

llvm-svn: 191071
2013-09-20 05:14:41 +00:00
Tom Stellard a6c6e1bfc2 R600: Rework subtarget info and remove AMDILDevice classes
This should simplify the subtarget definitions and make it easier to
add new ones.

Reviewed-by: Vincent Lejeune <vljn@ovi.com>
llvm-svn: 183566
2013-06-07 20:37:48 +00:00
Vincent Lejeune f9f4e1e7db R600: Factorize Fetch size limit inside AMDGPUSubTarget
llvm-svn: 182122
2013-05-17 16:49:55 +00:00
Vincent Lejeune c299164284 R600: Add FetchInst bit to instruction defs to denote vertex/tex instructions
v2[Vincent Lejeune]: Split FetchInst into usesTextureCache/usesVertexCache

llvm-svn: 180755
2013-04-30 00:13:39 +00:00
Dmitri Gribenko 226fea5bd6 Remove redundant 'llvm::' qualifications
llvm-svn: 172358
2013-01-13 16:01:15 +00:00
Tom Stellard 75aadc2813 Add R600 backend
A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX

llvm-svn: 169915
2012-12-11 21:25:42 +00:00