[clang] 6f258c0 - [Clang] Don't test register allocation

[Nikita Popov via cfe-commits]

Author: Nikita Popov
Date: 2022-06-23T12:46:00+02:00
New Revision: 6f258c0fd34cf4001ffa08c61f6e4e0f1254c50f

URL: https://github.com/llvm/llvm-project/commit/6f258c0fd34cf4001ffa08c61f6e4e0f1254c50f
DIFF: https://github.com/llvm/llvm-project/commit/6f258c0fd34cf4001ffa08c61f6e4e0f1254c50f.diff

LOG: [Clang] Don't test register allocation

This test was broken by 719658d078c4093d1ee716fb65ae94673df7b22b.

How did an assembly test get into clang/test?

Added: 
    

Modified: 
    clang/test/CodeGenCUDA/atomics-remarks-gfx90a.cu

Removed: 
    


################################################################################
diff  --git a/clang/test/CodeGenCUDA/atomics-remarks-gfx90a.cu b/clang/test/CodeGenCUDA/atomics-remarks-gfx90a.cu
index 96892286fd75e..946927d88a1ee 100644
--- a/clang/test/CodeGenCUDA/atomics-remarks-gfx90a.cu
+++ b/clang/test/CodeGenCUDA/atomics-remarks-gfx90a.cu
@@ -9,7 +9,7 @@
 
 // GFX90A-CAS: A compare and swap loop was generated for an atomic fadd operation at system memory scope
 // GFX90A-CAS-LABEL: _Z14atomic_add_casPf
-// GFX90A-CAS:  flat_atomic_cmpswap v0, v[2:3], v[4:5] glc
+// GFX90A-CAS:  flat_atomic_cmpswap
 // GFX90A-CAS:  s_cbranch_execnz
 __device__ float atomic_add_cas(float *p) {
   return __atomic_fetch_add(p, 1.0f, memory_order_relaxed);