e1a2f4713c
AMDGPU: Match global saddr addressing mode
...
The previous implementation was incorrect, and based off incorrect
instruction definitions. Unfortunately we can't match natural
addressing in a lot of cases due to the shift/scale applied in
getelementptrs. This relies on reducing the 64-bit shift to 32-bits.
2020-08-17 15:28:14 -04:00
aa77232a63
[NFC][AMDGPU] Improve fused fmul+fadd tests.
...
Reviewed By: rampitec
Differential Revision: https://reviews.llvm.org/D84903
2020-07-31 04:00:09 +03:00
5660bb6bc9
AMDGPU: Remove denormal subtarget features
...
Switch to using the denormal-fp-math/denormal-fp-math-f32 attributes.
2020-04-02 17:17:12 -04:00
8b20b7dc2b
[AMDGPU] Enabled v2.16 literals for VOP3P
...
Literal encoding needs op_sel_hi to select low 16 bit in this case.
Differential Revision: https://reviews.llvm.org/D45745
llvm-svn: 330230
2018-04-17 23:09:05 +00:00
c40d9f2e5d
AMDGPU/GCN: Bring processors in sync with AMDGPUUsage
...
- Add gfx704
- Change bonaire to gfx704
- Remove gfx804
- Remove gfx901
- Remove gfx903
Differential Revision: https://reviews.llvm.org/D40046
llvm-svn: 320194
2017-12-08 20:52:28 +00:00
4e309b0861
AMDGPU: Start selecting global instructions
...
llvm-svn: 309470
2017-07-29 01:03:53 +00:00
982aee6a38
[AMDGPU] Switch scalarize global loads ON by default
...
Differential revision: https://reviews.llvm.org/D34407
llvm-svn: 307097
2017-07-04 17:32:00 +00:00
e4a741376b
Revert r307026, "[AMDGPU] Switch scalarize global loads ON by default"
...
It broke a testcase.
Failing Tests (1):
LLVM :: CodeGen/AMDGPU/alignbit-pat.ll
llvm-svn: 307054
2017-07-04 02:14:18 +00:00
ea7f08bee5
[AMDGPU] Switch scalarize global loads ON by default
...
Differential revision: https://reviews.llvm.org/D34407
llvm-svn: 307026
2017-07-03 14:54:11 +00:00
3d1cc88c68
AMDGPU: Temporarily disable packed inlinable literals (v2f16, v2i16)
...
Differential Revision: https://reviews.llvm.org/D32361
llvm-svn: 301028
2017-04-21 19:45:22 +00:00
3dbeefa978
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel
...
Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
calling convention can be changed to a non-kernel.
Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'
on the relevant test directories (and undoing in one place that actually
wanted a non-kernel).
llvm-svn: 298444
2017-03-21 21:39:51 +00:00
eb522e68bc
AMDGPU: Support v2i16/v2f16 packed operations
...
llvm-svn: 296396
2017-02-27 22:15:25 +00:00
Matt Arsenault