[Openmp-commits] [openmp] Add openmp support to System z (PR #66081)

[Neale Ferguson via Openmp-commits]

nealef wrote:

I'm still a little confused as to what should go in. Were any of the above in a separate PR? Here's what I have to commit at the moment. It doesn't have the frame pointer suggestions because I couldn't work out if they were going in separately.
```
diff --git a/llvm/lib/Target/SystemZ/SystemZTargetMachine.cpp b/llvm/lib/Target/SystemZ/SystemZTargetMachine.cpp
index 7a3a2a7e9013..6abb203f0c36 100644
--- a/llvm/lib/Target/SystemZ/SystemZTargetMachine.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZTargetMachine.cpp
@@ -226,6 +226,8 @@ void SystemZPassConfig::addIRPasses() {
     addPass(createLoopDataPrefetchPass());
   }

+  addPass(createAtomicExpandPass());
+
   TargetPassConfig::addIRPasses();
 }

diff --git a/openmp/runtime/src/kmp.h b/openmp/runtime/src/kmp.h
index 339e4ca4be6b..4397565e8f47 100644
--- a/openmp/runtime/src/kmp.h
+++ b/openmp/runtime/src/kmp.h
@@ -2456,12 +2456,21 @@ typedef struct kmp_depend_info {
   union {
     kmp_uint8 flag; // flag as an unsigned char
     struct { // flag as a set of 8 bits
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+      unsigned all : 1;
+      unsigned unused : 3;
+      unsigned set : 1;
+      unsigned mtx : 1;
+      unsigned out : 1;
+      unsigned in : 1;
+#else
       unsigned in : 1;
       unsigned out : 1;
       unsigned mtx : 1;
       unsigned set : 1;
       unsigned unused : 3;
       unsigned all : 1;
+#endif
     } flags;
   };
 } kmp_depend_info_t;
diff --git a/openmp/runtime/src/z_Linux_asm.S b/openmp/runtime/src/z_Linux_asm.S
index 3533ef2d14ec..a72705528d41 100644
--- a/openmp/runtime/src/z_Linux_asm.S
+++ b/openmp/runtime/src/z_Linux_asm.S
@@ -2310,9 +2310,18 @@ __kmp_invoke_microtask:
 	.cfi_startproc

 	stmg	%r6,%r14,48(%r15)
+        .cfi_offset %r6, -112
+        .cfi_offset %r7, -104
+        .cfi_offset %r8, -96
+        .cfi_offset %r9, -88
+        .cfi_offset %r10, -80
+        .cfi_offset %r11, -72
+        .cfi_offset %r12, -64
+        .cfi_offset %r13, -56
+        .cfi_offset %r14, -48
+        .cfi_offset %r15, -40
 	lgr	%r11,%r15
-	.cfi_def_cfa	%r15, 0
-	.cfi_offset	%r15, 0
+	.cfi_def_cfa %r11, 160

 	// Compute the dynamic stack size:
 	//
@@ -2342,7 +2351,7 @@ __kmp_invoke_microtask:
 #if OMPT_SUPPORT
 	// Save frame pointer into exit_frame
 	lg	%r8,160(%r11)
-	stg	%r15,0(%r8)
+	stg	%r11,0(%r8)
 #endif

 	// Prepare arguments for the pkfn function (first 5 using r2-r6 registers)
diff --git a/openmp/runtime/test/ompt/callback.h b/openmp/runtime/test/ompt/callback.h
index 8e9bab363b16..efbd4c716e0e 100644
--- a/openmp/runtime/test/ompt/callback.h
+++ b/openmp/runtime/test/ompt/callback.h
@@ -232,10 +232,18 @@ ompt_label_##id:
 // On s390x the NOP instruction is 2 bytes long. For non-void runtime
 // functions Clang inserts a STY instruction (but only if compiling under
 // -fno-PIC which will be the default with Clang 8.0, another 6 bytes).
+//
+// Another possibility is:
+//
+//                brasl %r14,__kmpc_end_master at plt
+//   a7 f4 00 02  j 0f
+//   47 00 00 00  0: nop
+//   a7 f4 00 02  j addr
+//                addr:
 #define print_possible_return_addresses(addr)                                  \
-  printf("%" PRIu64 ": current_address=%p or %p\n",                            \
+  printf("%" PRIu64 ": current_address=%p or %p or %p\n",                      \
          ompt_get_thread_data()->value, ((char *)addr) - 2,                    \
-         ((char *)addr) - 8)
+         ((char *)addr) - 8, ((char *)addr) - 12)
 #else
 #error Unsupported target architecture, cannot determine address offset!
 #endif
```
What's missing or what should be excluded?

https://github.com/llvm/llvm-project/pull/66081