arch-gcn3: make read2st64_b32 write proper registers

Per the GCN3 ISA, read2st64_b32 writes to consecutive registers

Change-Id: Ibc1672584a72cf7de12e06068a03fe304b34dce2
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/32236
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Reviewed-by: Alexandru Duțu <alexandru.dutu@amd.com>
Reviewed-by: Bradford Beckmann <brad.beckmann@amd.com>
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

diff --git a/src/arch/gcn3/insts/instructions.cc b/src/arch/gcn3/insts/instructions.cc
index 6e81e2cd9fd877384cff948bcbc5728b430741bf..955d8013d2b8699015123e4707a659bc298c3ed1 100644 (file)
--- a/src/arch/gcn3/insts/instructions.cc
+++ b/src/arch/gcn3/insts/instructions.cc
@@ -32206,7 +32206,7 @@ namespace Gcn3ISA
     Inst_DS__DS_READ2ST64_B32::completeAcc(GPUDynInstPtr gpuDynInst)
     {
         VecOperandU32 vdst0(gpuDynInst, extData.VDST);
-        VecOperandU32 vdst1(gpuDynInst, extData.VDST + 2);
+        VecOperandU32 vdst1(gpuDynInst, extData.VDST + 1);
 
         for (int lane = 0; lane < NumVecElemPerVecReg; ++lane) {
             if (gpuDynInst->exec_mask[lane]) {