estimate vgpr

Author: linqun

example/35_splitK_gemm/gemm_wmma_splitk_reduce_multi_d_fp16.cpp

@@ -33,10 +33,10 @@ using DeviceGemmV2Instance =
         ADataType,   BDataType, DsDataType,  CDataType, AccDataType,  CShuffleDataType,
         AElementOp, BElementOp, CDEElementOp, GemmDefault,
         256,
-        128,  256,  64,
+        128,  128,  64,
         8,    8,
         16,   16,
-        4,    4,
+        4,    2,
         S<4, 64, 1>,     S<0, 2, 1>,    S<0, 2, 1>,
         1,    1,    8,   true,
         S<4, 64, 1>,     S<0, 2, 1>,    S<0, 2, 1>,

example/60_gemm_multi_ABD/gemm_multi_ABD_wmma_bias_fastgelu_bf16_i8.cpp

@@ -81,13 +81,13 @@ using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultipleABD_Wmm
     GemmSpec,
     256,
     128,
-    128,
+    64,
     64,
     8,
     8,
     16,
     16,
-    4,
+    2,
     2,
     S<8, 32, 1>,
     S<1, 0, 2>,
@@ -104,7 +104,7 @@ using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultipleABD_Wmm
     8,
     0,
     1,
-    1,
+    2,
     S<1, 32, 1, 8>,
     S<8, 8, 8>,
     ck::BlockGemmPipelineScheduler::Intrawave,

example/60_gemm_multi_ABD/gemm_multi_ABD_wmma_fastgelu_bf16_i8.cpp

@@ -106,7 +106,7 @@ using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultipleABD_Wmm
     S<1, 32, 1, 8>,
     S<8, 8, 8>,
     ck::BlockGemmPipelineScheduler::Intrawave,
-    ck::BlockGemmPipelineVersion::v3>;
+    ck::BlockGemmPipelineVersion::v1>;
 
 int main(int argc, char* argv[])
 {

example/60_gemm_multi_ABD/gemm_multi_ABD_wmma_multiply_bias_fastgelu_bf16_i8.cpp

@@ -107,7 +107,7 @@ using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultipleABD_Wmm
     S<1, 32, 1, 8>,
     S<8, 8, 8>,
     ck::BlockGemmPipelineScheduler::Intrawave,
-    ck::BlockGemmPipelineVersion::v3>;
+    ck::BlockGemmPipelineVersion::v1>;
 
 int main(int argc, char* argv[])
 {

example/65_gemm_multiply_multiply/gemm_multiply_multiply_wmma_fp16_bpreshuffle.cpp

@@ -65,12 +65,12 @@ using DeviceOpInstance =
         A0DataType, B0DataType, DsDataType, EDataType, AccDataType, CShuffleDataType,
         AElementOp, BElementOp, CDEElementOp, GemmSpec,
         128,
-        32, 128, 128,
+        32, 128, 64,
         8, 8,
         16, 16,
         2, 2,
-        S<16, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0,
-        S<16, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0,
+        S<8, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0,
+        S<8, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 0,
         1, 1, S<1, 16, 1, 8>, S<4, 4, 1>,
         ck::BlockGemmPipelineScheduler::Intrawave,
         ck::BlockGemmPipelineVersion::v1,