On DataLayout, omit the default of p:64:64:64.

[oota-llvm.git] / lib / Target / R600 / SIInstructions.td

diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td
index 7827a9ac6246357d8e6d4e49c66fc6b6e799729c..a0d49d7bccf11bc99f8fc265d546b6ca4d3a600f 100644 (file)
--- a/lib/Target/R600/SIInstructions.td
+++ b/lib/Target/R600/SIInstructions.td
@@ -489,14 +489,17 @@ def TBUFFER_STORE_FORMAT_XYZW : MTBUF_Store_Helper <0x00000007, "TBUFFER_STORE_F
 
 let mayLoad = 1 in {
 
-defm S_LOAD_DWORD : SMRD_Helper <0x00, "S_LOAD_DWORD", SReg_64, SReg_32>;
+// We are using the SGPR_32 and not the SReg_32 register class for 32-bit
+// SMRD instructions, because the SGPR_32 register class does not include M0
+// and writing to M0 from an SMRD instruction will hang the GPU.
+defm S_LOAD_DWORD : SMRD_Helper <0x00, "S_LOAD_DWORD", SReg_64, SGPR_32>;
 defm S_LOAD_DWORDX2 : SMRD_Helper <0x01, "S_LOAD_DWORDX2", SReg_64, SReg_64>;
 defm S_LOAD_DWORDX4 : SMRD_Helper <0x02, "S_LOAD_DWORDX4", SReg_64, SReg_128>;
 defm S_LOAD_DWORDX8 : SMRD_Helper <0x03, "S_LOAD_DWORDX8", SReg_64, SReg_256>;
 defm S_LOAD_DWORDX16 : SMRD_Helper <0x04, "S_LOAD_DWORDX16", SReg_64, SReg_512>;
 
 defm S_BUFFER_LOAD_DWORD : SMRD_Helper <
-  0x08, "S_BUFFER_LOAD_DWORD", SReg_128, SReg_32
+  0x08, "S_BUFFER_LOAD_DWORD", SReg_128, SGPR_32
 >;
 
 defm S_BUFFER_LOAD_DWORDX2 : SMRD_Helper <
@@ -873,8 +876,21 @@ def : Pat <
                      $src2), sub1)
 >;
 
-defm V_READLANE_B32 : VOP2_32 <0x00000001, "V_READLANE_B32", []>;
-defm V_WRITELANE_B32 : VOP2_32 <0x00000002, "V_WRITELANE_B32", []>;
+def V_READLANE_B32 : VOP2 <
+  0x00000001,
+  (outs SReg_32:$vdst),
+  (ins VReg_32:$src0, SSrc_32:$vsrc1),
+  "V_READLANE_B32 $vdst, $src0, $vsrc1",
+  []
+>;
+
+def V_WRITELANE_B32 : VOP2 <
+  0x00000002,
+  (outs VReg_32:$vdst),
+  (ins SReg_32:$src0, SSrc_32:$vsrc1),
+  "V_WRITELANE_B32 $vdst, $src0, $vsrc1",
+  []
+>;
 
 let isCommutable = 1 in {
 defm V_ADD_F32 : VOP2_32 <0x00000003, "V_ADD_F32",