fixup lit test based on opidx use in the pass

Author: alexbaden

test/TritonIntelGPU/optimize-block-io-encoding.mlir

@@ -3,8 +3,8 @@
 #blocked = #ttg.blocked<{sizePerThread = [4, 4], threadsPerWarp = [1, 16], warpsPerCTA = [8, 4], order = [1, 0]}>
 #blocked1 = #ttg.blocked<{sizePerThread = [1, 8], threadsPerWarp = [4, 4], warpsPerCTA = [32, 1], order = [1, 0]}>
 #blocked2 = #ttg.blocked<{sizePerThread = [1, 8], threadsPerWarp = [1, 16], warpsPerCTA = [16, 2], order = [1, 0]}>
-// CHECK: #mma = #ttig.subgroup_2d_block<{warpsPerCTA = [8, 4], instrShape = [8, 16], numBlocks=1, order=[1, 0], kWidth=1, threadsPerWarp=16}>
-// CHECK: #mma1 = #ttig.subgroup_2d_block<{warpsPerCTA = [8, 4], instrShape = [8, 16], numBlocks=1, order=[1, 0], kWidth=2, threadsPerWarp=16}>
+// CHECK: #mma = #ttig.subgroup_2d_block<{warpsPerCTA = [8, 4], instrShape = [8, 16], numBlocks=2, order=[1, 0], kWidth=1, threadsPerWarp=16}>
+// CHECK: #mma1 = #ttig.subgroup_2d_block<{warpsPerCTA = [8, 4], instrShape = [16, 16], numBlocks=2, order=[0, 1], kWidth=2, threadsPerWarp=16}>
 // CHECK: #mma2 = #ttig.dpas<{repeatCount = 8, systolicDepth = 8, executionSize = 16, opsPerChan = 2, threadsPerWarp = 16, warpsPerCTA = [8, 4], repCluster = [4, 2], A = [32, 16], B = [16, 32], C = [32, 32]}>
 #mma = #ttig.dpas<{repeatCount = 8, systolicDepth = 8, executionSize = 16, opsPerChan = 2, threadsPerWarp = 16, warpsPerCTA = [8, 4], repCluster = [4, 2], A = [32, 16], B = [16, 32], C = [32, 32]}>
 module attributes {"ttg.num-ctas" = 1 : i32, "ttg.num-warps" = 32 : i32, ttg.target = "xpu", "ttg.threads-per-warp" = 16 : i32, ttig.min_sg_size = 16 : i32, ttig.support_bf16_conversion, ttig.support_dpas, ttig.support_sg_2d_block, ttig.target_arch = "spir64"} {