[llvm] [AIX][TLS] Produce a faster local-exec access sequence for the "aix-small-tls" global variable attribute (PR #83053)

[Felix via llvm-commits]

================
@@ -0,0 +1,196 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
+; RUN: llc  -verify-machineinstrs -mcpu=pwr7 -ppc-asm-full-reg-names \
+; RUN:      -mtriple powerpc64-ibm-aix-xcoff < %s \
+; RUN:      | FileCheck %s --check-prefix=CHECK-SMALLCM64
+; RUN: llc  -verify-machineinstrs -mcpu=pwr7 -ppc-asm-full-reg-names \
+; RUN:      -mtriple powerpc64-ibm-aix-xcoff --code-model=large \
+; RUN:      < %s | FileCheck %s --check-prefix=CHECK-LARGECM64
+
+ at mySmallLocalExecTLS6 = external thread_local(localexec) global [60 x i64], align 8
+ at mySmallLocalExecTLS2 = external thread_local(localexec) global [3000 x i64], align 8 #0
+ at MyTLSGDVar = thread_local global [800 x i64] zeroinitializer, align 8
+ at mySmallLocalExecTLS3 = internal thread_local(localexec) global [3000 x i64] zeroinitializer, align 8
+ at mySmallLocalExecTLS4 = internal thread_local(localexec) global [3000 x i64] zeroinitializer, align 8 #0
+ at mySmallLocalExecTLS5 = thread_local(localexec) global [3000 x i64] zeroinitializer, align 8 #0
+declare nonnull ptr @llvm.threadlocal.address.p0(ptr nonnull)
+
+; All accesses use a "faster" local-exec sequence directly off the thread pointer.
+define i64 @StoreLargeAccess1() #1 {
----------------
orcguru wrote:

Some trivial comment:
"""
See https://llvm.org/docs/TestingGuide.html#best-practices-for-regression-tests
I think we should avoid any unnamed instructions in the input IR.
"""

A possible solution to this comment:

define i64 @StoreLargeAccess1() #1 {
entry:
  %tls0 = tail call align 8 ptr @llvm.threadlocal.address.p0(ptr align 8 @mySmallLocalExecTLS6)
  %arrayidx = getelementptr inbounds [60 x i64], ptr %tls0, i64 0, i64 53
  store i64 212, ptr %arrayidx, align 8
  %tls1 = tail call align 8 ptr @llvm.threadlocal.address.p0(ptr align 8 @mySmallLocalExecTLS2)
  %arrayidx1 = getelementptr inbounds [3000 x i64], ptr %tls1, i64 0, i64 150
  store i64 203, ptr %arrayidx1, align 8
  %tls2 = tail call align 8 ptr @llvm.threadlocal.address.p0(ptr align 8 @MyTLSGDVar)
  %arrayidx2 = getelementptr inbounds [800 x i64], ptr %tls2, i64 0, i64 55
  store i64 44, ptr %arrayidx2, align 8
  %tls3 = tail call align 8 ptr @llvm.threadlocal.address.p0(ptr align 8 @mySmallLocalExecTLS3)
  %arrayidx3 = getelementptr inbounds [3000 x i64], ptr %tls3, i64 0, i64 250
  store i64 6, ptr %arrayidx3, align 8
  %tls4 = tail call align 8 ptr @llvm.threadlocal.address.p0(ptr align 8 @mySmallLocalExecTLS4)
  %arrayidx4 = getelementptr inbounds [3000 x i64], ptr %tls4, i64 0, i64 850
  store i64 100, ptr %arrayidx4, align 8
  %tls5 = tail call align 8 ptr @llvm.threadlocal.address.p0(ptr align 8 @mySmallLocalExecTLS5)
  %arrayidx5 = getelementptr inbounds [3000 x i64], ptr %tls5, i64 0, i64 1050
  store i64 882, ptr %arrayidx5, align 8
  %load1 = load i64, ptr %arrayidx1, align 8
  %load2 = load i64, ptr %arrayidx3, align 8
  %load3 = load i64, ptr %arrayidx4, align 8
  %add = add i64 %load1, 882
  %add9 = add i64 %add, %load2
  %add11 = add i64 %add9, %load3
  ret i64 %add11
}



https://github.com/llvm/llvm-project/pull/83053