[AArch64] Add sve bf16 fpext and fpround costs.

[davemgreen]

This prevents them from generating Invalid costs, as generating the instructions seems to work fine with and without +bf16. The costs are mostly taken from the number of instructions (minus ptrue and constants) from https://llvm.godbolt.org/z/16zMd47he

[llvmbot]

@llvm/pr-subscribers-llvm-analysis

@llvm/pr-subscribers-backend-aarch64

Author: David Green (davemgreen)

Changes

This prevents them from generating Invalid costs, as generating the instructions seems to work fine with and without +bf16. The costs are mostly taken from the number of instructions (minus ptrue and constants) from https://llvm.godbolt.org/z/16zMd47he

---

Full diff: https://github.com/llvm/llvm-project/pull/150485.diff

3 Files Affected:

• (modified) llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (+27)
• (modified) llvm/test/Analysis/CostModel/AArch64/sve-fpext.ll (+6-6)
• (modified) llvm/test/Analysis/CostModel/AArch64/sve-fptrunc.ll (+17-11)

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 40f49dade6131..ba00d9e4dbb99 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3093,6 +3093,12 @@ InstructionCost AArch64TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
       {ISD::FP_ROUND, MVT::v2bf16, MVT::v2f64, 2}, // bfcvtn+fcvtn
       {ISD::FP_ROUND, MVT::v4bf16, MVT::v4f64, 3}, // fcvtn+fcvtl2+bfcvtn
       {ISD::FP_ROUND, MVT::v8bf16, MVT::v8f64, 6}, // 2 * fcvtn+fcvtn2+bfcvtn
+      {ISD::FP_ROUND, MVT::nxv2bf16, MVT::nxv2f32, 1}, // bfcvt
+      {ISD::FP_ROUND, MVT::nxv4bf16, MVT::nxv4f32, 1}, // bfcvt
+      {ISD::FP_ROUND, MVT::nxv8bf16, MVT::nxv8f32, 3}, // bfcvt+bfcvt+uzp1
+      {ISD::FP_ROUND, MVT::nxv2bf16, MVT::nxv2f64, 2}, // fcvtx+bfcvt
+      {ISD::FP_ROUND, MVT::nxv4bf16, MVT::nxv4f64, 5}, // fcvtx+bfcvt+bfcvt+uzp1
+      {ISD::FP_ROUND, MVT::nxv8bf16, MVT::nxv8f64, 11}, // 4*fcvt+4*bfcvt+3*uzp
   };
 
   if (ST->hasBF16())
@@ -3501,11 +3507,21 @@ InstructionCost AArch64TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
       {ISD::FP_ROUND, MVT::nxv4f16, MVT::nxv4f32, 1},
       {ISD::FP_ROUND, MVT::nxv8f16, MVT::nxv8f32, 3},
 
+      // Truncate from nxvmf32 to nxvmbf16.
+      {ISD::FP_ROUND, MVT::nxv2bf16, MVT::nxv2f32, 8},
+      {ISD::FP_ROUND, MVT::nxv4bf16, MVT::nxv4f32, 8},
+      {ISD::FP_ROUND, MVT::nxv8bf16, MVT::nxv8f32, 17},
+
       // Truncate from nxvmf64 to nxvmf16.
       {ISD::FP_ROUND, MVT::nxv2f16, MVT::nxv2f64, 1},
       {ISD::FP_ROUND, MVT::nxv4f16, MVT::nxv4f64, 3},
       {ISD::FP_ROUND, MVT::nxv8f16, MVT::nxv8f64, 7},
 
+      // Truncate from nxvmf64 to nxvmbf16.
+      {ISD::FP_ROUND, MVT::nxv2bf16, MVT::nxv2f64, 9},
+      {ISD::FP_ROUND, MVT::nxv4bf16, MVT::nxv4f64, 19},
+      {ISD::FP_ROUND, MVT::nxv8bf16, MVT::nxv8f64, 39},
+
       // Truncate from nxvmf64 to nxvmf32.
       {ISD::FP_ROUND, MVT::nxv2f32, MVT::nxv2f64, 1},
       {ISD::FP_ROUND, MVT::nxv4f32, MVT::nxv4f64, 3},
@@ -3516,11 +3532,22 @@ InstructionCost AArch64TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
       {ISD::FP_EXTEND, MVT::nxv4f32, MVT::nxv4f16, 1},
       {ISD::FP_EXTEND, MVT::nxv8f32, MVT::nxv8f16, 2},
 
+      // Extend from nxvmbf16 to nxvmf32.
+      {ISD::FP_EXTEND, MVT::nxv2f32, MVT::nxv2bf16, 1}, // lsl
+      {ISD::FP_EXTEND, MVT::nxv4f32, MVT::nxv4bf16, 1}, // lsl
+      {ISD::FP_EXTEND, MVT::nxv8f32, MVT::nxv8bf16, 2}, // unpck+unpck+lsl+lsl
+
       // Extend from nxvmf16 to nxvmf64.
       {ISD::FP_EXTEND, MVT::nxv2f64, MVT::nxv2f16, 1},
       {ISD::FP_EXTEND, MVT::nxv4f64, MVT::nxv4f16, 2},
       {ISD::FP_EXTEND, MVT::nxv8f64, MVT::nxv8f16, 4},
 
+      // Extend from nxvmbf16 to nxvmf64.
+      {ISD::FP_EXTEND, MVT::nxv2f64, MVT::nxv2bf16, 2},  // lsl+fcvt
+      {ISD::FP_EXTEND, MVT::nxv4f64, MVT::nxv4bf16, 6},  // unpck+unpck+lsl+lsl
+                                                         // + fcvt+fcvt
+      {ISD::FP_EXTEND, MVT::nxv8f64, MVT::nxv8bf16, 14}, // 6*unpck+4*lsl+4*fcvt
+
       // Extend from nxvmf32 to nxvmf64.
       {ISD::FP_EXTEND, MVT::nxv2f64, MVT::nxv2f32, 1},
       {ISD::FP_EXTEND, MVT::nxv4f64, MVT::nxv4f32, 2},
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-fpext.ll b/llvm/test/Analysis/CostModel/AArch64/sve-fpext.ll
index 805b3713830ab..ddc1a72e16318 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-fpext.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-fpext.ll
@@ -34,12 +34,12 @@ define void @sve_fpext() {
 
 define void @sve_fpext_bf16() {
 ; CHECK-LABEL: 'sve_fpext_bf16'
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv2_f16_to_f32 = fpext <vscale x 2 x bfloat> undef to <vscale x 2 x float>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv4_f16_to_f32 = fpext <vscale x 4 x bfloat> undef to <vscale x 4 x float>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_to_f32 = fpext <vscale x 8 x bfloat> undef to <vscale x 8 x float>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv2_f16_to_f64 = fpext <vscale x 2 x bfloat> undef to <vscale x 2 x double>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv4_f16_to_f64 = fpext <vscale x 4 x bfloat> undef to <vscale x 4 x double>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_to_f64 = fpext <vscale x 8 x bfloat> undef to <vscale x 8 x double>
+; CHECK-NEXT:  Cost Model: Found costs of 1 for: %nxv2_f16_to_f32 = fpext <vscale x 2 x bfloat> undef to <vscale x 2 x float>
+; CHECK-NEXT:  Cost Model: Found costs of 1 for: %nxv4_f16_to_f32 = fpext <vscale x 4 x bfloat> undef to <vscale x 4 x float>
+; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_to_f32 = fpext <vscale x 8 x bfloat> undef to <vscale x 8 x float>
+; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %nxv2_f16_to_f64 = fpext <vscale x 2 x bfloat> undef to <vscale x 2 x double>
+; CHECK-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:1 Lat:1 SizeLat:1 for: %nxv4_f16_to_f64 = fpext <vscale x 4 x bfloat> undef to <vscale x 4 x double>
+; CHECK-NEXT:  Cost Model: Found costs of RThru:14 CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_to_f64 = fpext <vscale x 8 x bfloat> undef to <vscale x 8 x double>
 ; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
 ;
   %nxv2_f16_to_f32 = fpext <vscale x 2 x bfloat> undef to <vscale x 2 x float>
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-fptrunc.ll b/llvm/test/Analysis/CostModel/AArch64/sve-fptrunc.ll
index bb31ebfbed4ba..88c53ec4510b1 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-fptrunc.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-fptrunc.ll
@@ -34,14 +34,23 @@ define void @sve_fptruncs() {
 }
 
 define void @sve_fptruncs_bf16() {
-; CHECK-LABEL: 'sve_fptruncs_bf16'
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> undef to <vscale x 2 x bfloat>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> undef to <vscale x 4 x bfloat>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> undef to <vscale x 8 x bfloat>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> undef to <vscale x 2 x bfloat>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> undef to <vscale x 4 x bfloat>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:Invalid CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> undef to <vscale x 8 x bfloat>
-; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+; CHECK-NOBF16-LABEL: 'sve_fptruncs_bf16'
+; CHECK-NOBF16-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: %nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> undef to <vscale x 2 x bfloat>
+; CHECK-NOBF16-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: %nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> undef to <vscale x 4 x bfloat>
+; CHECK-NOBF16-NEXT:  Cost Model: Found costs of RThru:17 CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> undef to <vscale x 8 x bfloat>
+; CHECK-NOBF16-NEXT:  Cost Model: Found costs of RThru:9 CodeSize:1 Lat:1 SizeLat:1 for: %nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> undef to <vscale x 2 x bfloat>
+; CHECK-NOBF16-NEXT:  Cost Model: Found costs of RThru:19 CodeSize:1 Lat:1 SizeLat:1 for: %nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> undef to <vscale x 4 x bfloat>
+; CHECK-NOBF16-NEXT:  Cost Model: Found costs of RThru:39 CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> undef to <vscale x 8 x bfloat>
+; CHECK-NOBF16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-BF16-LABEL: 'sve_fptruncs_bf16'
+; CHECK-BF16-NEXT:  Cost Model: Found costs of 1 for: %nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> undef to <vscale x 2 x bfloat>
+; CHECK-BF16-NEXT:  Cost Model: Found costs of 1 for: %nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> undef to <vscale x 4 x bfloat>
+; CHECK-BF16-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> undef to <vscale x 8 x bfloat>
+; CHECK-BF16-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> undef to <vscale x 2 x bfloat>
+; CHECK-BF16-NEXT:  Cost Model: Found costs of RThru:5 CodeSize:1 Lat:1 SizeLat:1 for: %nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> undef to <vscale x 4 x bfloat>
+; CHECK-BF16-NEXT:  Cost Model: Found costs of RThru:11 CodeSize:1 Lat:1 SizeLat:1 for: %nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> undef to <vscale x 8 x bfloat>
+; CHECK-BF16-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
 ;
   %nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> undef to <vscale x 2 x bfloat>
   %nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> undef to <vscale x 4 x bfloat>
@@ -53,6 +62,3 @@ define void @sve_fptruncs_bf16() {
 
   ret void
 }
-;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
-; CHECK-BF16: {{.*}}
-; CHECK-NOBF16: {{.*}}

[paulwalker-arm]

Some nits but otherwise looks good to me.