diff options
| author | Craig Topper <craig.topper@gmail.com> | 2017-01-10 06:01:16 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@gmail.com> | 2017-01-10 06:01:16 +0000 |
| commit | d55b83128bc12ba86dc121f8e016e3bcb7bc11db (patch) | |
| tree | 05b5b4ff15671276b25e041dcdca8867b875f75a /llvm/test | |
| parent | e6663d376e0aa5c983f930672d44265baeeb72fa (diff) | |
| download | bcm5719-llvm-d55b83128bc12ba86dc121f8e016e3bcb7bc11db.tar.gz bcm5719-llvm-d55b83128bc12ba86dc121f8e016e3bcb7bc11db.zip | |
AMD family 17h (znver1) enablement
Summary:
This patch enables the following
1. AMD family 17h architecture using "znver1" tune flag (-march, -mcpu).
2. ISAs that are enabled for "znver1" architecture.
3. Checks ADX isa from cpuid to identify "znver1" flag when -march=native is used.
4. ISAs FMA4, XOP are disabled as they are dropped from amdfam17.
5. For the time being, it uses the btver2 scheduler model.
6. Test file is updated to check this flag.
This item is linked to clang review item https://reviews.llvm.org/D28018
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, RKSimon, ashutosh.nema, llvm-commits
Differential Revision: https://reviews.llvm.org/D28017
llvm-svn: 291543
Diffstat (limited to 'llvm/test')
| -rw-r--r-- | llvm/test/CodeGen/X86/cpus.ll | 1 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll | 2 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/slow-unaligned-mem.ll | 1 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/x86-64-double-shifts-var.ll | 1 |
4 files changed, 5 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/cpus.ll b/llvm/test/CodeGen/X86/cpus.ll index ee1f7bb5295..20ce932a184 100644 --- a/llvm/test/CodeGen/X86/cpus.ll +++ b/llvm/test/CodeGen/X86/cpus.ll @@ -33,3 +33,4 @@ ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=bdver4 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=btver1 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=btver2 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty +; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=znver1 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty diff --git a/llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll b/llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll index 6f4cb84a2b9..c69dbf573f4 100644 --- a/llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll +++ b/llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll @@ -3,6 +3,8 @@ ; Eg: zext(or(setcc(cmp), setcc(cmp))) -> shr(or(lzcnt, lzcnt)) ; RUN: llc < %s -mtriple=x86_64-pc-linux -mcpu=btver2 | FileCheck %s ; RUN: llc < %s -mtriple=x86_64-pc-linux -mcpu=btver2 -mattr=-fast-lzcnt | FileCheck --check-prefix=NOFASTLZCNT %s +; RUN: llc < %s -mtriple=x86_64-pc-linux -mcpu=znver1 | FileCheck %s +; RUN: llc < %s -mtriple=x86_64-pc-linux -mcpu=znver1 -mattr=-fast-lzcnt | FileCheck --check-prefix=NOFASTLZCNT %s ; Test one 32-bit input, output is 32-bit, no transformations expected. define i32 @test_zext_cmp0(i32 %a) { diff --git a/llvm/test/CodeGen/X86/slow-unaligned-mem.ll b/llvm/test/CodeGen/X86/slow-unaligned-mem.ll index 41e9a95bcdd..8251eb324a7 100644 --- a/llvm/test/CodeGen/X86/slow-unaligned-mem.ll +++ b/llvm/test/CodeGen/X86/slow-unaligned-mem.ll @@ -46,6 +46,7 @@ ; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=bdver2 2>&1 | FileCheck %s --check-prefix=FAST ; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=bdver3 2>&1 | FileCheck %s --check-prefix=FAST ; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=bdver4 2>&1 | FileCheck %s --check-prefix=FAST +; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=znver1 2>&1 | FileCheck %s --check-prefix=FAST ; Other chips with slow unaligned memory accesses diff --git a/llvm/test/CodeGen/X86/x86-64-double-shifts-var.ll b/llvm/test/CodeGen/X86/x86-64-double-shifts-var.ll index 8d2dbbdb5d2..c025ee874b2 100644 --- a/llvm/test/CodeGen/X86/x86-64-double-shifts-var.ll +++ b/llvm/test/CodeGen/X86/x86-64-double-shifts-var.ll @@ -17,6 +17,7 @@ ; RUN: llc < %s -march=x86-64 -mcpu=bdver2 | FileCheck %s ; RUN: llc < %s -march=x86-64 -mcpu=bdver3 | FileCheck %s ; RUN: llc < %s -march=x86-64 -mcpu=bdver4 | FileCheck %s +; RUN: llc < %s -march=x86-64 -mcpu=znver1 | FileCheck %s ; Verify that for the X86_64 processors that are known to have poor latency ; double precision shift instructions we do not generate 'shld' or 'shrd' |
