Commit Graph

3 Commits

Author SHA1 Message Date
David Stuttard 20235ef3e7 [AMDGPU] Enable v4f16 and above for v_pk_fma instructions
Summary:
If isel is presented with <2 x half> vectors then it will correctly select
v_pk_fma style instructions.
If isel is presented with e.g. <4 x half> vectors it will scalarize, unlike for
other instruction types (such as fadd, fmul etc.)

Added extra support to enable this. Updated one of the tests to include a test
for this (as well as extending the test to GFX9)

Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, tpr, t-tye, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D65325

Change-Id: I50a4577a3f8223fb53992af3b7d26121f65b71ee
llvm-svn: 367206
2019-07-29 08:15:10 +00:00
Matt Arsenault 5dbe4a9926 AMDGPU: Eliminate test usage of legacy FP elim attributes
llvm-svn: 363950
2019-06-20 17:03:27 +00:00
Stanislav Mekhanoshin 28a1936f6d [AMDGPU] gfx1010: use fmac instructions
Differential Revision: https://reviews.llvm.org/D61527

llvm-svn: 359959
2019-05-04 04:20:37 +00:00