[llvm] r230651 - Use ".arch_extension" ARM directive to support hwdiv on krait

[Sumanth Gundapaneni]

Author: sgundapa
Date: Thu Feb 26 12:08:41 2015
New Revision: 230651

URL: http://llvm.org/viewvc/llvm-project?rev=230651&view=rev
Log:
Use ".arch_extension" ARM directive to support hwdiv on krait

In case of "krait" CPU, asm printer doesn't emit any ".cpu" so the
features bits are not computed. This patch lets the asm printer
emit ".cpu cortex-a9" directive for krait and the hwdiv feature is
enabled through ".arch_extension". In short, krait is treated
as "cortex-a9" with hwdiv. We can not emit ".krait" as CPU since
it is not supported bu GNU GAS yet

Added:
    llvm/trunk/test/CodeGen/ARM/krait-cpu-div-attribute.ll
Modified:
    llvm/trunk/lib/Target/ARM/ARMAsmPrinter.cpp

Modified: llvm/trunk/lib/Target/ARM/ARMAsmPrinter.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMAsmPrinter.cpp?rev=230651&r1=230650&r2=230651&view=diff
==============================================================================
--- llvm/trunk/lib/Target/ARM/ARMAsmPrinter.cpp (original)
+++ llvm/trunk/lib/Target/ARM/ARMAsmPrinter.cpp Thu Feb 26 12:08:41 2015
@@ -16,6 +16,7 @@
 #include "ARM.h"
 #include "ARMConstantPoolValue.h"
 #include "ARMFPUName.h"
+#include "ARMArchExtName.h"
 #include "ARMMachineFunctionInfo.h"
 #include "ARMTargetMachine.h"
 #include "ARMTargetObjectFile.h"
@@ -668,9 +669,17 @@ void ARMAsmPrinter::emitAttributes() {
 
   std::string CPUString = STI.getCPUString();
 
-  // FIXME: remove krait check when GNU tools support krait cpu
-  if (CPUString != "generic" && CPUString != "krait")
-    ATS.emitTextAttribute(ARMBuildAttrs::CPU_name, CPUString);
+  if (CPUString != "generic") {
+    // FIXME: remove krait check when GNU tools support krait cpu
+    if (STI.isKrait()) {
+      ATS.emitTextAttribute(ARMBuildAttrs::CPU_name, "cortex-a9");
+      // We consider krait as a "cortex-a9" + hwdiv CPU
+      // Enable hwdiv through ".arch_extension idiv"
+      if (STI.hasDivide() || STI.hasDivideInARMMode())
+        ATS.emitArchExtension(ARM::HWDIV);
+    } else
+      ATS.emitTextAttribute(ARMBuildAttrs::CPU_name, CPUString);
+  }
 
   ATS.emitAttribute(ARMBuildAttrs::CPU_arch, getArchForCPU(CPUString, &STI));
 

Added: llvm/trunk/test/CodeGen/ARM/krait-cpu-div-attribute.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/ARM/krait-cpu-div-attribute.ll?rev=230651&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/ARM/krait-cpu-div-attribute.ll (added)
+++ llvm/trunk/test/CodeGen/ARM/krait-cpu-div-attribute.ll Thu Feb 26 12:08:41 2015
@@ -0,0 +1,36 @@
+; Tests the genration of ".arch_extension" attribute for hardware
+; division on krait CPU. For now, krait is recognized as "cortex-a9" + hwdiv
+; Also, tests for the hwdiv instruction on krait CPU
+
+; check for arch_extension/cpu directive
+; RUN: llc < %s -mtriple=armv7-linux-gnueabi -mcpu=krait | FileCheck %s --check-prefix=DIV_EXTENSION
+; RUN: llc < %s -mtriple=thumbv7-linux-gnueabi -mcpu=krait | FileCheck %s --check-prefix=DIV_EXTENSION
+; RUN: llc < %s -mtriple=armv7-linux-gnueabi -mcpu=cortex-a9 | FileCheck %s --check-prefix=NODIV_KRAIT
+; RUN: llc < %s -mtriple=thumbv7-linux-gnueabi -mcpu=cortex-a9 | FileCheck %s --check-prefix=NODIV_KRAIT
+; RUN: llc < %s -mcpu=krait -mattr=-hwdiv,-hwdiv-arm | FileCheck %s --check-prefix=NODIV_KRAIT
+
+; check if correct instruction is emitted by integrated assembler
+; RUN: llc < %s -mtriple=armv7-linux-gnueabi -mcpu=krait -filetype=obj | llvm-objdump -mcpu=krait -triple armv7-linux-gnueabi -d - | FileCheck %s --check-prefix=HWDIV
+; RUN: llc < %s -mtriple=thumbv7-linux-gnueabi -mcpu=krait -filetype=obj | llvm-objdump -mcpu=krait -triple thumbv7-linux-gnueabi -d - | FileCheck %s --check-prefix=HWDIV
+
+; arch_extension attribute
+; DIV_EXTENSION:  .cpu cortex-a9
+; DIV_EXTENSION:  .arch_extension idiv
+; NODIV_KRAIT-NOT:  .arch_extension idiv
+; HWDIV: sdiv
+
+define i32 @main() #0 {
+entry:
+  %retval = alloca i32, align 4
+  %a = alloca i32, align 4
+  %b = alloca i32, align 4
+  %c = alloca i32, align 4
+  store i32 0, i32* %retval
+  store volatile i32 100, i32* %b, align 4
+  store volatile i32 32, i32* %c, align 4
+  %0 = load volatile i32* %b, align 4
+  %1 = load volatile i32* %c, align 4
+  %div = sdiv i32 %0, %1
+  store volatile i32 %div, i32* %a, align 4
+  ret i32 0
+}