diff options
| author | Tom Stellard <thomas.stellard@amd.com> | 2014-04-29 23:12:46 +0000 |
|---|---|---|
| committer | Tom Stellard <thomas.stellard@amd.com> | 2014-04-29 23:12:46 +0000 |
| commit | 19a970b2dafdfaca4263557db69a70e072e0a130 (patch) | |
| tree | fbd885a7557e9b28a3d162c79ab626d7e14f81ff /test/CodeGen | |
| parent | ea89cd8b523756e9e7730e305ae64256251848c3 (diff) | |
| download | llvm-19a970b2dafdfaca4263557db69a70e072e0a130.tar.gz llvm-19a970b2dafdfaca4263557db69a70e072e0a130.tar.bz2 llvm-19a970b2dafdfaca4263557db69a70e072e0a130.tar.xz | |
R600: optimize the UDIVREM 64 algorithm
This is a squash of several optimization commits:
- calculate DIV_Lo and DIV_Hi separately
- use BFE_U32 if we are operating on 32bit values
- use precomputed constants instead of shifting in UDVIREM
- skip the first 32 iterations of udivrem
v2: Check whether BFE is supported before using it
Patch by: Jan Vesely
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207589 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen')
| -rw-r--r-- | test/CodeGen/R600/udivrem64.ll | 84 |
1 files changed, 84 insertions, 0 deletions
diff --git a/test/CodeGen/R600/udivrem64.ll b/test/CodeGen/R600/udivrem64.ll new file mode 100644 index 0000000000..3cdbb691e1 --- /dev/null +++ b/test/CodeGen/R600/udivrem64.ll @@ -0,0 +1,84 @@ +;XUN: llc < %s -march=r600 -mcpu=SI | FileCheck --check-prefix=SI --check-prefix=FUNC %s +;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG --check-prefix=FUNC %s + +;FUNC-LABEL: @test_udiv +;EG: RECIP_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;SI: S_ENDPGM +define void @test_udiv(i64 addrspace(1)* %out, i64 %x, i64 %y) { + %result = udiv i64 %x, %y + store i64 %result, i64 addrspace(1)* %out + ret void +} + +;FUNC-LABEL: @test_urem +;EG: RECIP_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;EG: BFE_UINT +;SI: S_ENDPGM +define void @test_urem(i64 addrspace(1)* %out, i64 %x, i64 %y) { + %result = urem i64 %x, %y + store i64 %result, i64 addrspace(1)* %out + ret void +} |