diff --git a/llvm/test/CodeGen/RISCV/sadd_sat.ll b/llvm/test/CodeGen/RISCV/sadd_sat.ll index d35e23c0a1cc..98b366939dab 100644 --- a/llvm/test/CodeGen/RISCV/sadd_sat.ll +++ b/llvm/test/CodeGen/RISCV/sadd_sat.ll @@ -1,8 +1,10 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=riscv32 -mattr=+m | FileCheck %s --check-prefix=RV32I ; RUN: llc < %s -mtriple=riscv64 -mattr=+m | FileCheck %s --check-prefix=RV64I -; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefix=RV32IZbb -; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefix=RV64IZbb +; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbNOZbt +; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbNOZbt +; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbZbt +; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbZbt declare i4 @llvm.sadd.sat.i4(i4, i4) declare i8 @llvm.sadd.sat.i8(i8, i8) @@ -45,22 +47,22 @@ define signext i32 @func(i32 signext %x, i32 signext %y) nounwind { ; RV64I-NEXT: lui a0, 524288 ; RV64I-NEXT: ret ; -; RV32IZbb-LABEL: func: -; RV32IZbb: # %bb.0: -; RV32IZbb-NEXT: mv a2, a0 -; RV32IZbb-NEXT: add a3, a0, a1 -; RV32IZbb-NEXT: lui a0, 524288 -; RV32IZbb-NEXT: bgez a3, .LBB0_2 -; RV32IZbb-NEXT: # %bb.1: -; RV32IZbb-NEXT: addi a0, a0, -1 -; RV32IZbb-NEXT: .LBB0_2: -; RV32IZbb-NEXT: slt a2, a3, a2 -; RV32IZbb-NEXT: slti a1, a1, 0 -; RV32IZbb-NEXT: bne a1, a2, .LBB0_4 -; RV32IZbb-NEXT: # %bb.3: -; RV32IZbb-NEXT: mv a0, a3 -; RV32IZbb-NEXT: .LBB0_4: -; RV32IZbb-NEXT: ret +; RV32IZbbNOZbt-LABEL: func: +; RV32IZbbNOZbt: # %bb.0: +; RV32IZbbNOZbt-NEXT: mv a2, a0 +; RV32IZbbNOZbt-NEXT: add a3, a0, a1 +; RV32IZbbNOZbt-NEXT: lui a0, 524288 +; RV32IZbbNOZbt-NEXT: bgez a3, .LBB0_2 +; RV32IZbbNOZbt-NEXT: # %bb.1: +; RV32IZbbNOZbt-NEXT: addi a0, a0, -1 +; RV32IZbbNOZbt-NEXT: .LBB0_2: +; RV32IZbbNOZbt-NEXT: slt a2, a3, a2 +; RV32IZbbNOZbt-NEXT: slti a1, a1, 0 +; RV32IZbbNOZbt-NEXT: bne a1, a2, .LBB0_4 +; RV32IZbbNOZbt-NEXT: # %bb.3: +; RV32IZbbNOZbt-NEXT: mv a0, a3 +; RV32IZbbNOZbt-NEXT: .LBB0_4: +; RV32IZbbNOZbt-NEXT: ret ; ; RV64IZbb-LABEL: func: ; RV64IZbb: # %bb.0: @@ -70,6 +72,19 @@ define signext i32 @func(i32 signext %x, i32 signext %y) nounwind { ; RV64IZbb-NEXT: min a0, a0, a2 ; RV64IZbb-NEXT: max a0, a0, a1 ; RV64IZbb-NEXT: ret +; +; RV32IZbbZbt-LABEL: func: +; RV32IZbbZbt: # %bb.0: +; RV32IZbbZbt-NEXT: add a2, a0, a1 +; RV32IZbbZbt-NEXT: slti a3, a2, 0 +; RV32IZbbZbt-NEXT: lui a4, 524288 +; RV32IZbbZbt-NEXT: addi a5, a4, -1 +; RV32IZbbZbt-NEXT: cmov a3, a3, a5, a4 +; RV32IZbbZbt-NEXT: slt a0, a2, a0 +; RV32IZbbZbt-NEXT: slti a1, a1, 0 +; RV32IZbbZbt-NEXT: xor a0, a1, a0 +; RV32IZbbZbt-NEXT: cmov a0, a0, a3, a2 +; RV32IZbbZbt-NEXT: ret %tmp = call i32 @llvm.sadd.sat.i32(i32 %x, i32 %y); ret i32 %tmp; } @@ -118,47 +133,80 @@ define i64 @func2(i64 %x, i64 %y) nounwind { ; RV64I-NEXT: .LBB1_4: ; RV64I-NEXT: ret ; -; RV32IZbb-LABEL: func2: -; RV32IZbb: # %bb.0: -; RV32IZbb-NEXT: mv a4, a1 -; RV32IZbb-NEXT: mv a1, a0 -; RV32IZbb-NEXT: add a5, a4, a3 -; RV32IZbb-NEXT: add a0, a0, a2 -; RV32IZbb-NEXT: sltu a1, a0, a1 -; RV32IZbb-NEXT: add a2, a5, a1 -; RV32IZbb-NEXT: lui a1, 524288 -; RV32IZbb-NEXT: bgez a2, .LBB1_2 -; RV32IZbb-NEXT: # %bb.1: -; RV32IZbb-NEXT: addi a1, a1, -1 -; RV32IZbb-NEXT: .LBB1_2: -; RV32IZbb-NEXT: xor a5, a4, a2 -; RV32IZbb-NEXT: xor a3, a4, a3 -; RV32IZbb-NEXT: andn a3, a5, a3 -; RV32IZbb-NEXT: bltz a3, .LBB1_4 -; RV32IZbb-NEXT: # %bb.3: -; RV32IZbb-NEXT: mv a1, a2 -; RV32IZbb-NEXT: ret -; RV32IZbb-NEXT: .LBB1_4: -; RV32IZbb-NEXT: srai a0, a2, 31 -; RV32IZbb-NEXT: ret +; RV32IZbbNOZbt-LABEL: func2: +; RV32IZbbNOZbt: # %bb.0: +; RV32IZbbNOZbt-NEXT: mv a4, a1 +; RV32IZbbNOZbt-NEXT: mv a1, a0 +; RV32IZbbNOZbt-NEXT: add a5, a4, a3 +; RV32IZbbNOZbt-NEXT: add a0, a0, a2 +; RV32IZbbNOZbt-NEXT: sltu a1, a0, a1 +; RV32IZbbNOZbt-NEXT: add a2, a5, a1 +; RV32IZbbNOZbt-NEXT: lui a1, 524288 +; RV32IZbbNOZbt-NEXT: bgez a2, .LBB1_2 +; RV32IZbbNOZbt-NEXT: # %bb.1: +; RV32IZbbNOZbt-NEXT: addi a1, a1, -1 +; RV32IZbbNOZbt-NEXT: .LBB1_2: +; RV32IZbbNOZbt-NEXT: xor a5, a4, a2 +; RV32IZbbNOZbt-NEXT: xor a3, a4, a3 +; RV32IZbbNOZbt-NEXT: andn a3, a5, a3 +; RV32IZbbNOZbt-NEXT: bltz a3, .LBB1_4 +; RV32IZbbNOZbt-NEXT: # %bb.3: +; RV32IZbbNOZbt-NEXT: mv a1, a2 +; RV32IZbbNOZbt-NEXT: ret +; RV32IZbbNOZbt-NEXT: .LBB1_4: +; RV32IZbbNOZbt-NEXT: srai a0, a2, 31 +; RV32IZbbNOZbt-NEXT: ret ; -; RV64IZbb-LABEL: func2: -; RV64IZbb: # %bb.0: -; RV64IZbb-NEXT: mv a2, a0 -; RV64IZbb-NEXT: add a3, a0, a1 -; RV64IZbb-NEXT: addi a0, zero, -1 -; RV64IZbb-NEXT: slli a0, a0, 63 -; RV64IZbb-NEXT: bgez a3, .LBB1_2 -; RV64IZbb-NEXT: # %bb.1: -; RV64IZbb-NEXT: addi a0, a0, -1 -; RV64IZbb-NEXT: .LBB1_2: -; RV64IZbb-NEXT: slt a2, a3, a2 -; RV64IZbb-NEXT: slti a1, a1, 0 -; RV64IZbb-NEXT: bne a1, a2, .LBB1_4 -; RV64IZbb-NEXT: # %bb.3: -; RV64IZbb-NEXT: mv a0, a3 -; RV64IZbb-NEXT: .LBB1_4: -; RV64IZbb-NEXT: ret +; RV64IZbbNOZbt-LABEL: func2: +; RV64IZbbNOZbt: # %bb.0: +; RV64IZbbNOZbt-NEXT: mv a2, a0 +; RV64IZbbNOZbt-NEXT: add a3, a0, a1 +; RV64IZbbNOZbt-NEXT: addi a0, zero, -1 +; RV64IZbbNOZbt-NEXT: slli a0, a0, 63 +; RV64IZbbNOZbt-NEXT: bgez a3, .LBB1_2 +; RV64IZbbNOZbt-NEXT: # %bb.1: +; RV64IZbbNOZbt-NEXT: addi a0, a0, -1 +; RV64IZbbNOZbt-NEXT: .LBB1_2: +; RV64IZbbNOZbt-NEXT: slt a2, a3, a2 +; RV64IZbbNOZbt-NEXT: slti a1, a1, 0 +; RV64IZbbNOZbt-NEXT: bne a1, a2, .LBB1_4 +; RV64IZbbNOZbt-NEXT: # %bb.3: +; RV64IZbbNOZbt-NEXT: mv a0, a3 +; RV64IZbbNOZbt-NEXT: .LBB1_4: +; RV64IZbbNOZbt-NEXT: ret +; +; RV32IZbbZbt-LABEL: func2: +; RV32IZbbZbt: # %bb.0: +; RV32IZbbZbt-NEXT: add a4, a1, a3 +; RV32IZbbZbt-NEXT: add a2, a0, a2 +; RV32IZbbZbt-NEXT: sltu a0, a2, a0 +; RV32IZbbZbt-NEXT: add a0, a4, a0 +; RV32IZbbZbt-NEXT: slti a4, a0, 0 +; RV32IZbbZbt-NEXT: lui a6, 524288 +; RV32IZbbZbt-NEXT: addi a5, a6, -1 +; RV32IZbbZbt-NEXT: cmov a4, a4, a5, a6 +; RV32IZbbZbt-NEXT: xor a5, a1, a0 +; RV32IZbbZbt-NEXT: xor a1, a1, a3 +; RV32IZbbZbt-NEXT: andn a1, a5, a1 +; RV32IZbbZbt-NEXT: slti a3, a1, 0 +; RV32IZbbZbt-NEXT: cmov a1, a3, a4, a0 +; RV32IZbbZbt-NEXT: srai a0, a0, 31 +; RV32IZbbZbt-NEXT: cmov a0, a3, a0, a2 +; RV32IZbbZbt-NEXT: ret +; +; RV64IZbbZbt-LABEL: func2: +; RV64IZbbZbt: # %bb.0: +; RV64IZbbZbt-NEXT: add a2, a0, a1 +; RV64IZbbZbt-NEXT: slti a3, a2, 0 +; RV64IZbbZbt-NEXT: addi a4, zero, -1 +; RV64IZbbZbt-NEXT: slli a4, a4, 63 +; RV64IZbbZbt-NEXT: addi a5, a4, -1 +; RV64IZbbZbt-NEXT: cmov a3, a3, a5, a4 +; RV64IZbbZbt-NEXT: slt a0, a2, a0 +; RV64IZbbZbt-NEXT: slti a1, a1, 0 +; RV64IZbbZbt-NEXT: xor a0, a1, a0 +; RV64IZbbZbt-NEXT: cmov a0, a0, a3, a2 +; RV64IZbbZbt-NEXT: ret %tmp = call i64 @llvm.sadd.sat.i64(i64 %x, i64 %y); ret i64 %tmp; } diff --git a/llvm/test/CodeGen/RISCV/sadd_sat_plus.ll b/llvm/test/CodeGen/RISCV/sadd_sat_plus.ll index 1767701e6eaf..69240024025b 100644 --- a/llvm/test/CodeGen/RISCV/sadd_sat_plus.ll +++ b/llvm/test/CodeGen/RISCV/sadd_sat_plus.ll @@ -1,8 +1,10 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=riscv32 -mattr=+m | FileCheck %s --check-prefix=RV32I ; RUN: llc < %s -mtriple=riscv64 -mattr=+m | FileCheck %s --check-prefix=RV64I -; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefix=RV32IZbb -; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefix=RV64IZbb +; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbNOZbt +; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbNOZbt +; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbZbt +; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbZbt declare i4 @llvm.sadd.sat.i4(i4, i4) declare i8 @llvm.sadd.sat.i8(i8, i8) @@ -48,23 +50,23 @@ define i32 @func32(i32 %x, i32 %y, i32 %z) nounwind { ; RV64I-NEXT: lui a0, 524288 ; RV64I-NEXT: ret ; -; RV32IZbb-LABEL: func32: -; RV32IZbb: # %bb.0: -; RV32IZbb-NEXT: mv a3, a0 -; RV32IZbb-NEXT: mul a2, a1, a2 -; RV32IZbb-NEXT: add a1, a0, a2 -; RV32IZbb-NEXT: lui a0, 524288 -; RV32IZbb-NEXT: bgez a1, .LBB0_2 -; RV32IZbb-NEXT: # %bb.1: -; RV32IZbb-NEXT: addi a0, a0, -1 -; RV32IZbb-NEXT: .LBB0_2: -; RV32IZbb-NEXT: slt a3, a1, a3 -; RV32IZbb-NEXT: slti a2, a2, 0 -; RV32IZbb-NEXT: bne a2, a3, .LBB0_4 -; RV32IZbb-NEXT: # %bb.3: -; RV32IZbb-NEXT: mv a0, a1 -; RV32IZbb-NEXT: .LBB0_4: -; RV32IZbb-NEXT: ret +; RV32IZbbNOZbt-LABEL: func32: +; RV32IZbbNOZbt: # %bb.0: +; RV32IZbbNOZbt-NEXT: mv a3, a0 +; RV32IZbbNOZbt-NEXT: mul a2, a1, a2 +; RV32IZbbNOZbt-NEXT: add a1, a0, a2 +; RV32IZbbNOZbt-NEXT: lui a0, 524288 +; RV32IZbbNOZbt-NEXT: bgez a1, .LBB0_2 +; RV32IZbbNOZbt-NEXT: # %bb.1: +; RV32IZbbNOZbt-NEXT: addi a0, a0, -1 +; RV32IZbbNOZbt-NEXT: .LBB0_2: +; RV32IZbbNOZbt-NEXT: slt a3, a1, a3 +; RV32IZbbNOZbt-NEXT: slti a2, a2, 0 +; RV32IZbbNOZbt-NEXT: bne a2, a3, .LBB0_4 +; RV32IZbbNOZbt-NEXT: # %bb.3: +; RV32IZbbNOZbt-NEXT: mv a0, a1 +; RV32IZbbNOZbt-NEXT: .LBB0_4: +; RV32IZbbNOZbt-NEXT: ret ; ; RV64IZbb-LABEL: func32: ; RV64IZbb: # %bb.0: @@ -76,6 +78,20 @@ define i32 @func32(i32 %x, i32 %y, i32 %z) nounwind { ; RV64IZbb-NEXT: min a0, a0, a2 ; RV64IZbb-NEXT: max a0, a0, a1 ; RV64IZbb-NEXT: ret +; +; RV32IZbbZbt-LABEL: func32: +; RV32IZbbZbt: # %bb.0: +; RV32IZbbZbt-NEXT: mul a1, a1, a2 +; RV32IZbbZbt-NEXT: add a2, a0, a1 +; RV32IZbbZbt-NEXT: slt a0, a2, a0 +; RV32IZbbZbt-NEXT: slti a1, a1, 0 +; RV32IZbbZbt-NEXT: xor a0, a1, a0 +; RV32IZbbZbt-NEXT: slti a1, a2, 0 +; RV32IZbbZbt-NEXT: lui a3, 524288 +; RV32IZbbZbt-NEXT: addi a4, a3, -1 +; RV32IZbbZbt-NEXT: cmov a1, a1, a4, a3 +; RV32IZbbZbt-NEXT: cmov a0, a0, a1, a2 +; RV32IZbbZbt-NEXT: ret %a = mul i32 %y, %z %tmp = call i32 @llvm.sadd.sat.i32(i32 %x, i32 %a) ret i32 %tmp @@ -125,47 +141,80 @@ define i64 @func64(i64 %x, i64 %y, i64 %z) nounwind { ; RV64I-NEXT: .LBB1_4: ; RV64I-NEXT: ret ; -; RV32IZbb-LABEL: func64: -; RV32IZbb: # %bb.0: -; RV32IZbb-NEXT: mv a2, a1 -; RV32IZbb-NEXT: mv a1, a0 -; RV32IZbb-NEXT: add a3, a2, a5 -; RV32IZbb-NEXT: add a0, a0, a4 -; RV32IZbb-NEXT: sltu a1, a0, a1 -; RV32IZbb-NEXT: add a3, a3, a1 -; RV32IZbb-NEXT: lui a1, 524288 -; RV32IZbb-NEXT: bgez a3, .LBB1_2 -; RV32IZbb-NEXT: # %bb.1: -; RV32IZbb-NEXT: addi a1, a1, -1 -; RV32IZbb-NEXT: .LBB1_2: -; RV32IZbb-NEXT: xor a4, a2, a3 -; RV32IZbb-NEXT: xor a2, a2, a5 -; RV32IZbb-NEXT: andn a2, a4, a2 -; RV32IZbb-NEXT: bltz a2, .LBB1_4 -; RV32IZbb-NEXT: # %bb.3: -; RV32IZbb-NEXT: mv a1, a3 -; RV32IZbb-NEXT: ret -; RV32IZbb-NEXT: .LBB1_4: -; RV32IZbb-NEXT: srai a0, a3, 31 -; RV32IZbb-NEXT: ret +; RV32IZbbNOZbt-LABEL: func64: +; RV32IZbbNOZbt: # %bb.0: +; RV32IZbbNOZbt-NEXT: mv a2, a1 +; RV32IZbbNOZbt-NEXT: mv a1, a0 +; RV32IZbbNOZbt-NEXT: add a3, a2, a5 +; RV32IZbbNOZbt-NEXT: add a0, a0, a4 +; RV32IZbbNOZbt-NEXT: sltu a1, a0, a1 +; RV32IZbbNOZbt-NEXT: add a3, a3, a1 +; RV32IZbbNOZbt-NEXT: lui a1, 524288 +; RV32IZbbNOZbt-NEXT: bgez a3, .LBB1_2 +; RV32IZbbNOZbt-NEXT: # %bb.1: +; RV32IZbbNOZbt-NEXT: addi a1, a1, -1 +; RV32IZbbNOZbt-NEXT: .LBB1_2: +; RV32IZbbNOZbt-NEXT: xor a4, a2, a3 +; RV32IZbbNOZbt-NEXT: xor a2, a2, a5 +; RV32IZbbNOZbt-NEXT: andn a2, a4, a2 +; RV32IZbbNOZbt-NEXT: bltz a2, .LBB1_4 +; RV32IZbbNOZbt-NEXT: # %bb.3: +; RV32IZbbNOZbt-NEXT: mv a1, a3 +; RV32IZbbNOZbt-NEXT: ret +; RV32IZbbNOZbt-NEXT: .LBB1_4: +; RV32IZbbNOZbt-NEXT: srai a0, a3, 31 +; RV32IZbbNOZbt-NEXT: ret ; -; RV64IZbb-LABEL: func64: -; RV64IZbb: # %bb.0: -; RV64IZbb-NEXT: mv a1, a0 -; RV64IZbb-NEXT: add a3, a0, a2 -; RV64IZbb-NEXT: addi a0, zero, -1 -; RV64IZbb-NEXT: slli a0, a0, 63 -; RV64IZbb-NEXT: bgez a3, .LBB1_2 -; RV64IZbb-NEXT: # %bb.1: -; RV64IZbb-NEXT: addi a0, a0, -1 -; RV64IZbb-NEXT: .LBB1_2: -; RV64IZbb-NEXT: slt a1, a3, a1 -; RV64IZbb-NEXT: slti a2, a2, 0 -; RV64IZbb-NEXT: bne a2, a1, .LBB1_4 -; RV64IZbb-NEXT: # %bb.3: -; RV64IZbb-NEXT: mv a0, a3 -; RV64IZbb-NEXT: .LBB1_4: -; RV64IZbb-NEXT: ret +; RV64IZbbNOZbt-LABEL: func64: +; RV64IZbbNOZbt: # %bb.0: +; RV64IZbbNOZbt-NEXT: mv a1, a0 +; RV64IZbbNOZbt-NEXT: add a3, a0, a2 +; RV64IZbbNOZbt-NEXT: addi a0, zero, -1 +; RV64IZbbNOZbt-NEXT: slli a0, a0, 63 +; RV64IZbbNOZbt-NEXT: bgez a3, .LBB1_2 +; RV64IZbbNOZbt-NEXT: # %bb.1: +; RV64IZbbNOZbt-NEXT: addi a0, a0, -1 +; RV64IZbbNOZbt-NEXT: .LBB1_2: +; RV64IZbbNOZbt-NEXT: slt a1, a3, a1 +; RV64IZbbNOZbt-NEXT: slti a2, a2, 0 +; RV64IZbbNOZbt-NEXT: bne a2, a1, .LBB1_4 +; RV64IZbbNOZbt-NEXT: # %bb.3: +; RV64IZbbNOZbt-NEXT: mv a0, a3 +; RV64IZbbNOZbt-NEXT: .LBB1_4: +; RV64IZbbNOZbt-NEXT: ret +; +; RV32IZbbZbt-LABEL: func64: +; RV32IZbbZbt: # %bb.0: +; RV32IZbbZbt-NEXT: add a2, a1, a5 +; RV32IZbbZbt-NEXT: add a3, a0, a4 +; RV32IZbbZbt-NEXT: sltu a0, a3, a0 +; RV32IZbbZbt-NEXT: add a0, a2, a0 +; RV32IZbbZbt-NEXT: slti a2, a0, 0 +; RV32IZbbZbt-NEXT: lui a6, 524288 +; RV32IZbbZbt-NEXT: addi a4, a6, -1 +; RV32IZbbZbt-NEXT: cmov a2, a2, a4, a6 +; RV32IZbbZbt-NEXT: xor a4, a1, a0 +; RV32IZbbZbt-NEXT: xor a1, a1, a5 +; RV32IZbbZbt-NEXT: andn a1, a4, a1 +; RV32IZbbZbt-NEXT: slti a4, a1, 0 +; RV32IZbbZbt-NEXT: cmov a1, a4, a2, a0 +; RV32IZbbZbt-NEXT: srai a0, a0, 31 +; RV32IZbbZbt-NEXT: cmov a0, a4, a0, a3 +; RV32IZbbZbt-NEXT: ret +; +; RV64IZbbZbt-LABEL: func64: +; RV64IZbbZbt: # %bb.0: +; RV64IZbbZbt-NEXT: add a1, a0, a2 +; RV64IZbbZbt-NEXT: slti a3, a1, 0 +; RV64IZbbZbt-NEXT: addi a4, zero, -1 +; RV64IZbbZbt-NEXT: slli a4, a4, 63 +; RV64IZbbZbt-NEXT: addi a5, a4, -1 +; RV64IZbbZbt-NEXT: cmov a3, a3, a5, a4 +; RV64IZbbZbt-NEXT: slt a0, a1, a0 +; RV64IZbbZbt-NEXT: slti a2, a2, 0 +; RV64IZbbZbt-NEXT: xor a0, a2, a0 +; RV64IZbbZbt-NEXT: cmov a0, a0, a3, a1 +; RV64IZbbZbt-NEXT: ret %a = mul i64 %y, %z %tmp = call i64 @llvm.sadd.sat.i64(i64 %x, i64 %z) ret i64 %tmp diff --git a/llvm/test/CodeGen/RISCV/ssub_sat.ll b/llvm/test/CodeGen/RISCV/ssub_sat.ll index 61d5a4833ba9..008a3d0cf8ad 100644 --- a/llvm/test/CodeGen/RISCV/ssub_sat.ll +++ b/llvm/test/CodeGen/RISCV/ssub_sat.ll @@ -1,8 +1,10 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=riscv32 -mattr=+m | FileCheck %s --check-prefix=RV32I ; RUN: llc < %s -mtriple=riscv64 -mattr=+m | FileCheck %s --check-prefix=RV64I -; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefix=RV32IZbb -; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefix=RV64IZbb +; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbNOZbt +; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbNOZbt +; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbZbt +; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbZbt declare i4 @llvm.ssub.sat.i4(i4, i4) declare i8 @llvm.ssub.sat.i8(i8, i8) @@ -45,22 +47,22 @@ define signext i32 @func(i32 signext %x, i32 signext %y) nounwind { ; RV64I-NEXT: lui a0, 524288 ; RV64I-NEXT: ret ; -; RV32IZbb-LABEL: func: -; RV32IZbb: # %bb.0: -; RV32IZbb-NEXT: mv a2, a0 -; RV32IZbb-NEXT: sub a3, a0, a1 -; RV32IZbb-NEXT: lui a0, 524288 -; RV32IZbb-NEXT: bgez a3, .LBB0_2 -; RV32IZbb-NEXT: # %bb.1: -; RV32IZbb-NEXT: addi a0, a0, -1 -; RV32IZbb-NEXT: .LBB0_2: -; RV32IZbb-NEXT: sgtz a1, a1 -; RV32IZbb-NEXT: slt a2, a3, a2 -; RV32IZbb-NEXT: bne a1, a2, .LBB0_4 -; RV32IZbb-NEXT: # %bb.3: -; RV32IZbb-NEXT: mv a0, a3 -; RV32IZbb-NEXT: .LBB0_4: -; RV32IZbb-NEXT: ret +; RV32IZbbNOZbt-LABEL: func: +; RV32IZbbNOZbt: # %bb.0: +; RV32IZbbNOZbt-NEXT: mv a2, a0 +; RV32IZbbNOZbt-NEXT: sub a3, a0, a1 +; RV32IZbbNOZbt-NEXT: lui a0, 524288 +; RV32IZbbNOZbt-NEXT: bgez a3, .LBB0_2 +; RV32IZbbNOZbt-NEXT: # %bb.1: +; RV32IZbbNOZbt-NEXT: addi a0, a0, -1 +; RV32IZbbNOZbt-NEXT: .LBB0_2: +; RV32IZbbNOZbt-NEXT: sgtz a1, a1 +; RV32IZbbNOZbt-NEXT: slt a2, a3, a2 +; RV32IZbbNOZbt-NEXT: bne a1, a2, .LBB0_4 +; RV32IZbbNOZbt-NEXT: # %bb.3: +; RV32IZbbNOZbt-NEXT: mv a0, a3 +; RV32IZbbNOZbt-NEXT: .LBB0_4: +; RV32IZbbNOZbt-NEXT: ret ; ; RV64IZbb-LABEL: func: ; RV64IZbb: # %bb.0: @@ -70,6 +72,19 @@ define signext i32 @func(i32 signext %x, i32 signext %y) nounwind { ; RV64IZbb-NEXT: min a0, a0, a2 ; RV64IZbb-NEXT: max a0, a0, a1 ; RV64IZbb-NEXT: ret +; +; RV32IZbbZbt-LABEL: func: +; RV32IZbbZbt: # %bb.0: +; RV32IZbbZbt-NEXT: sgtz a2, a1 +; RV32IZbbZbt-NEXT: sub a1, a0, a1 +; RV32IZbbZbt-NEXT: slt a0, a1, a0 +; RV32IZbbZbt-NEXT: xor a0, a2, a0 +; RV32IZbbZbt-NEXT: slti a2, a1, 0 +; RV32IZbbZbt-NEXT: lui a3, 524288 +; RV32IZbbZbt-NEXT: addi a4, a3, -1 +; RV32IZbbZbt-NEXT: cmov a2, a2, a4, a3 +; RV32IZbbZbt-NEXT: cmov a0, a0, a2, a1 +; RV32IZbbZbt-NEXT: ret %tmp = call i32 @llvm.ssub.sat.i32(i32 %x, i32 %y); ret i32 %tmp; } @@ -116,46 +131,79 @@ define i64 @func2(i64 %x, i64 %y) nounwind { ; RV64I-NEXT: .LBB1_4: ; RV64I-NEXT: ret ; -; RV32IZbb-LABEL: func2: -; RV32IZbb: # %bb.0: -; RV32IZbb-NEXT: mv a4, a1 -; RV32IZbb-NEXT: sltu a1, a0, a2 -; RV32IZbb-NEXT: sub a5, a4, a3 -; RV32IZbb-NEXT: sub a5, a5, a1 -; RV32IZbb-NEXT: lui a1, 524288 -; RV32IZbb-NEXT: bgez a5, .LBB1_2 -; RV32IZbb-NEXT: # %bb.1: -; RV32IZbb-NEXT: addi a1, a1, -1 -; RV32IZbb-NEXT: .LBB1_2: -; RV32IZbb-NEXT: xor a6, a4, a5 -; RV32IZbb-NEXT: xor a3, a4, a3 -; RV32IZbb-NEXT: and a3, a3, a6 -; RV32IZbb-NEXT: bltz a3, .LBB1_4 -; RV32IZbb-NEXT: # %bb.3: -; RV32IZbb-NEXT: sub a0, a0, a2 -; RV32IZbb-NEXT: mv a1, a5 -; RV32IZbb-NEXT: ret -; RV32IZbb-NEXT: .LBB1_4: -; RV32IZbb-NEXT: srai a0, a5, 31 -; RV32IZbb-NEXT: ret +; RV32IZbbNOZbt-LABEL: func2: +; RV32IZbbNOZbt: # %bb.0: +; RV32IZbbNOZbt-NEXT: mv a4, a1 +; RV32IZbbNOZbt-NEXT: sltu a1, a0, a2 +; RV32IZbbNOZbt-NEXT: sub a5, a4, a3 +; RV32IZbbNOZbt-NEXT: sub a5, a5, a1 +; RV32IZbbNOZbt-NEXT: lui a1, 524288 +; RV32IZbbNOZbt-NEXT: bgez a5, .LBB1_2 +; RV32IZbbNOZbt-NEXT: # %bb.1: +; RV32IZbbNOZbt-NEXT: addi a1, a1, -1 +; RV32IZbbNOZbt-NEXT: .LBB1_2: +; RV32IZbbNOZbt-NEXT: xor a6, a4, a5 +; RV32IZbbNOZbt-NEXT: xor a3, a4, a3 +; RV32IZbbNOZbt-NEXT: and a3, a3, a6 +; RV32IZbbNOZbt-NEXT: bltz a3, .LBB1_4 +; RV32IZbbNOZbt-NEXT: # %bb.3: +; RV32IZbbNOZbt-NEXT: sub a0, a0, a2 +; RV32IZbbNOZbt-NEXT: mv a1, a5 +; RV32IZbbNOZbt-NEXT: ret +; RV32IZbbNOZbt-NEXT: .LBB1_4: +; RV32IZbbNOZbt-NEXT: srai a0, a5, 31 +; RV32IZbbNOZbt-NEXT: ret ; -; RV64IZbb-LABEL: func2: -; RV64IZbb: # %bb.0: -; RV64IZbb-NEXT: mv a2, a0 -; RV64IZbb-NEXT: sub a3, a0, a1 -; RV64IZbb-NEXT: addi a0, zero, -1 -; RV64IZbb-NEXT: slli a0, a0, 63 -; RV64IZbb-NEXT: bgez a3, .LBB1_2 -; RV64IZbb-NEXT: # %bb.1: -; RV64IZbb-NEXT: addi a0, a0, -1 -; RV64IZbb-NEXT: .LBB1_2: -; RV64IZbb-NEXT: sgtz a1, a1 -; RV64IZbb-NEXT: slt a2, a3, a2 -; RV64IZbb-NEXT: bne a1, a2, .LBB1_4 -; RV64IZbb-NEXT: # %bb.3: -; RV64IZbb-NEXT: mv a0, a3 -; RV64IZbb-NEXT: .LBB1_4: -; RV64IZbb-NEXT: ret +; RV64IZbbNOZbt-LABEL: func2: +; RV64IZbbNOZbt: # %bb.0: +; RV64IZbbNOZbt-NEXT: mv a2, a0 +; RV64IZbbNOZbt-NEXT: sub a3, a0, a1 +; RV64IZbbNOZbt-NEXT: addi a0, zero, -1 +; RV64IZbbNOZbt-NEXT: slli a0, a0, 63 +; RV64IZbbNOZbt-NEXT: bgez a3, .LBB1_2 +; RV64IZbbNOZbt-NEXT: # %bb.1: +; RV64IZbbNOZbt-NEXT: addi a0, a0, -1 +; RV64IZbbNOZbt-NEXT: .LBB1_2: +; RV64IZbbNOZbt-NEXT: sgtz a1, a1 +; RV64IZbbNOZbt-NEXT: slt a2, a3, a2 +; RV64IZbbNOZbt-NEXT: bne a1, a2, .LBB1_4 +; RV64IZbbNOZbt-NEXT: # %bb.3: +; RV64IZbbNOZbt-NEXT: mv a0, a3 +; RV64IZbbNOZbt-NEXT: .LBB1_4: +; RV64IZbbNOZbt-NEXT: ret +; +; RV32IZbbZbt-LABEL: func2: +; RV32IZbbZbt: # %bb.0: +; RV32IZbbZbt-NEXT: sltu a4, a0, a2 +; RV32IZbbZbt-NEXT: sub a5, a1, a3 +; RV32IZbbZbt-NEXT: sub a4, a5, a4 +; RV32IZbbZbt-NEXT: slti a7, a4, 0 +; RV32IZbbZbt-NEXT: lui a6, 524288 +; RV32IZbbZbt-NEXT: addi a5, a6, -1 +; RV32IZbbZbt-NEXT: cmov a6, a7, a5, a6 +; RV32IZbbZbt-NEXT: xor a5, a1, a4 +; RV32IZbbZbt-NEXT: xor a1, a1, a3 +; RV32IZbbZbt-NEXT: and a1, a1, a5 +; RV32IZbbZbt-NEXT: slti a3, a1, 0 +; RV32IZbbZbt-NEXT: cmov a1, a3, a6, a4 +; RV32IZbbZbt-NEXT: srai a4, a4, 31 +; RV32IZbbZbt-NEXT: sub a0, a0, a2 +; RV32IZbbZbt-NEXT: cmov a0, a3, a4, a0 +; RV32IZbbZbt-NEXT: ret +; +; RV64IZbbZbt-LABEL: func2: +; RV64IZbbZbt: # %bb.0: +; RV64IZbbZbt-NEXT: sgtz a2, a1 +; RV64IZbbZbt-NEXT: sub a1, a0, a1 +; RV64IZbbZbt-NEXT: slt a0, a1, a0 +; RV64IZbbZbt-NEXT: xor a0, a2, a0 +; RV64IZbbZbt-NEXT: slti a2, a1, 0 +; RV64IZbbZbt-NEXT: addi a3, zero, -1 +; RV64IZbbZbt-NEXT: slli a3, a3, 63 +; RV64IZbbZbt-NEXT: addi a4, a3, -1 +; RV64IZbbZbt-NEXT: cmov a2, a2, a4, a3 +; RV64IZbbZbt-NEXT: cmov a0, a0, a2, a1 +; RV64IZbbZbt-NEXT: ret %tmp = call i64 @llvm.ssub.sat.i64(i64 %x, i64 %y); ret i64 %tmp; } diff --git a/llvm/test/CodeGen/RISCV/ssub_sat_plus.ll b/llvm/test/CodeGen/RISCV/ssub_sat_plus.ll index 7f2e1595a98d..a30ad68631c4 100644 --- a/llvm/test/CodeGen/RISCV/ssub_sat_plus.ll +++ b/llvm/test/CodeGen/RISCV/ssub_sat_plus.ll @@ -1,8 +1,10 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=riscv32 -mattr=+m | FileCheck %s --check-prefix=RV32I ; RUN: llc < %s -mtriple=riscv64 -mattr=+m | FileCheck %s --check-prefix=RV64I -; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefix=RV32IZbb -; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefix=RV64IZbb +; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbNOZbt +; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbNOZbt +; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+experimental-zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbZbt +; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+experimental-zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbZbt declare i4 @llvm.ssub.sat.i4(i4, i4) declare i8 @llvm.ssub.sat.i8(i8, i8) @@ -48,23 +50,23 @@ define i32 @func32(i32 %x, i32 %y, i32 %z) nounwind { ; RV64I-NEXT: lui a0, 524288 ; RV64I-NEXT: ret ; -; RV32IZbb-LABEL: func32: -; RV32IZbb: # %bb.0: -; RV32IZbb-NEXT: mv a3, a0 -; RV32IZbb-NEXT: mul a2, a1, a2 -; RV32IZbb-NEXT: sub a1, a0, a2 -; RV32IZbb-NEXT: lui a0, 524288 -; RV32IZbb-NEXT: bgez a1, .LBB0_2 -; RV32IZbb-NEXT: # %bb.1: -; RV32IZbb-NEXT: addi a0, a0, -1 -; RV32IZbb-NEXT: .LBB0_2: -; RV32IZbb-NEXT: sgtz a2, a2 -; RV32IZbb-NEXT: slt a3, a1, a3 -; RV32IZbb-NEXT: bne a2, a3, .LBB0_4 -; RV32IZbb-NEXT: # %bb.3: -; RV32IZbb-NEXT: mv a0, a1 -; RV32IZbb-NEXT: .LBB0_4: -; RV32IZbb-NEXT: ret +; RV32IZbbNOZbt-LABEL: func32: +; RV32IZbbNOZbt: # %bb.0: +; RV32IZbbNOZbt-NEXT: mv a3, a0 +; RV32IZbbNOZbt-NEXT: mul a2, a1, a2 +; RV32IZbbNOZbt-NEXT: sub a1, a0, a2 +; RV32IZbbNOZbt-NEXT: lui a0, 524288 +; RV32IZbbNOZbt-NEXT: bgez a1, .LBB0_2 +; RV32IZbbNOZbt-NEXT: # %bb.1: +; RV32IZbbNOZbt-NEXT: addi a0, a0, -1 +; RV32IZbbNOZbt-NEXT: .LBB0_2: +; RV32IZbbNOZbt-NEXT: sgtz a2, a2 +; RV32IZbbNOZbt-NEXT: slt a3, a1, a3 +; RV32IZbbNOZbt-NEXT: bne a2, a3, .LBB0_4 +; RV32IZbbNOZbt-NEXT: # %bb.3: +; RV32IZbbNOZbt-NEXT: mv a0, a1 +; RV32IZbbNOZbt-NEXT: .LBB0_4: +; RV32IZbbNOZbt-NEXT: ret ; ; RV64IZbb-LABEL: func32: ; RV64IZbb: # %bb.0: @@ -76,6 +78,20 @@ define i32 @func32(i32 %x, i32 %y, i32 %z) nounwind { ; RV64IZbb-NEXT: min a0, a0, a2 ; RV64IZbb-NEXT: max a0, a0, a1 ; RV64IZbb-NEXT: ret +; +; RV32IZbbZbt-LABEL: func32: +; RV32IZbbZbt: # %bb.0: +; RV32IZbbZbt-NEXT: mul a1, a1, a2 +; RV32IZbbZbt-NEXT: sgtz a2, a1 +; RV32IZbbZbt-NEXT: sub a1, a0, a1 +; RV32IZbbZbt-NEXT: slt a0, a1, a0 +; RV32IZbbZbt-NEXT: xor a0, a2, a0 +; RV32IZbbZbt-NEXT: slti a2, a1, 0 +; RV32IZbbZbt-NEXT: lui a3, 524288 +; RV32IZbbZbt-NEXT: addi a4, a3, -1 +; RV32IZbbZbt-NEXT: cmov a2, a2, a4, a3 +; RV32IZbbZbt-NEXT: cmov a0, a0, a2, a1 +; RV32IZbbZbt-NEXT: ret %a = mul i32 %y, %z %tmp = call i32 @llvm.ssub.sat.i32(i32 %x, i32 %a) ret i32 %tmp @@ -123,46 +139,79 @@ define i64 @func64(i64 %x, i64 %y, i64 %z) nounwind { ; RV64I-NEXT: .LBB1_4: ; RV64I-NEXT: ret ; -; RV32IZbb-LABEL: func64: -; RV32IZbb: # %bb.0: -; RV32IZbb-NEXT: mv a2, a1 -; RV32IZbb-NEXT: sltu a1, a0, a4 -; RV32IZbb-NEXT: sub a3, a2, a5 -; RV32IZbb-NEXT: sub a3, a3, a1 -; RV32IZbb-NEXT: lui a1, 524288 -; RV32IZbb-NEXT: bgez a3, .LBB1_2 -; RV32IZbb-NEXT: # %bb.1: -; RV32IZbb-NEXT: addi a1, a1, -1 -; RV32IZbb-NEXT: .LBB1_2: -; RV32IZbb-NEXT: xor a6, a2, a3 -; RV32IZbb-NEXT: xor a2, a2, a5 -; RV32IZbb-NEXT: and a2, a2, a6 -; RV32IZbb-NEXT: bltz a2, .LBB1_4 -; RV32IZbb-NEXT: # %bb.3: -; RV32IZbb-NEXT: sub a0, a0, a4 -; RV32IZbb-NEXT: mv a1, a3 -; RV32IZbb-NEXT: ret -; RV32IZbb-NEXT: .LBB1_4: -; RV32IZbb-NEXT: srai a0, a3, 31 -; RV32IZbb-NEXT: ret +; RV32IZbbNOZbt-LABEL: func64: +; RV32IZbbNOZbt: # %bb.0: +; RV32IZbbNOZbt-NEXT: mv a2, a1 +; RV32IZbbNOZbt-NEXT: sltu a1, a0, a4 +; RV32IZbbNOZbt-NEXT: sub a3, a2, a5 +; RV32IZbbNOZbt-NEXT: sub a3, a3, a1 +; RV32IZbbNOZbt-NEXT: lui a1, 524288 +; RV32IZbbNOZbt-NEXT: bgez a3, .LBB1_2 +; RV32IZbbNOZbt-NEXT: # %bb.1: +; RV32IZbbNOZbt-NEXT: addi a1, a1, -1 +; RV32IZbbNOZbt-NEXT: .LBB1_2: +; RV32IZbbNOZbt-NEXT: xor a6, a2, a3 +; RV32IZbbNOZbt-NEXT: xor a2, a2, a5 +; RV32IZbbNOZbt-NEXT: and a2, a2, a6 +; RV32IZbbNOZbt-NEXT: bltz a2, .LBB1_4 +; RV32IZbbNOZbt-NEXT: # %bb.3: +; RV32IZbbNOZbt-NEXT: sub a0, a0, a4 +; RV32IZbbNOZbt-NEXT: mv a1, a3 +; RV32IZbbNOZbt-NEXT: ret +; RV32IZbbNOZbt-NEXT: .LBB1_4: +; RV32IZbbNOZbt-NEXT: srai a0, a3, 31 +; RV32IZbbNOZbt-NEXT: ret ; -; RV64IZbb-LABEL: func64: -; RV64IZbb: # %bb.0: -; RV64IZbb-NEXT: mv a1, a0 -; RV64IZbb-NEXT: sub a3, a0, a2 -; RV64IZbb-NEXT: addi a0, zero, -1 -; RV64IZbb-NEXT: slli a0, a0, 63 -; RV64IZbb-NEXT: bgez a3, .LBB1_2 -; RV64IZbb-NEXT: # %bb.1: -; RV64IZbb-NEXT: addi a0, a0, -1 -; RV64IZbb-NEXT: .LBB1_2: -; RV64IZbb-NEXT: sgtz a2, a2 -; RV64IZbb-NEXT: slt a1, a3, a1 -; RV64IZbb-NEXT: bne a2, a1, .LBB1_4 -; RV64IZbb-NEXT: # %bb.3: -; RV64IZbb-NEXT: mv a0, a3 -; RV64IZbb-NEXT: .LBB1_4: -; RV64IZbb-NEXT: ret +; RV64IZbbNOZbt-LABEL: func64: +; RV64IZbbNOZbt: # %bb.0: +; RV64IZbbNOZbt-NEXT: mv a1, a0 +; RV64IZbbNOZbt-NEXT: sub a3, a0, a2 +; RV64IZbbNOZbt-NEXT: addi a0, zero, -1 +; RV64IZbbNOZbt-NEXT: slli a0, a0, 63 +; RV64IZbbNOZbt-NEXT: bgez a3, .LBB1_2 +; RV64IZbbNOZbt-NEXT: # %bb.1: +; RV64IZbbNOZbt-NEXT: addi a0, a0, -1 +; RV64IZbbNOZbt-NEXT: .LBB1_2: +; RV64IZbbNOZbt-NEXT: sgtz a2, a2 +; RV64IZbbNOZbt-NEXT: slt a1, a3, a1 +; RV64IZbbNOZbt-NEXT: bne a2, a1, .LBB1_4 +; RV64IZbbNOZbt-NEXT: # %bb.3: +; RV64IZbbNOZbt-NEXT: mv a0, a3 +; RV64IZbbNOZbt-NEXT: .LBB1_4: +; RV64IZbbNOZbt-NEXT: ret +; +; RV32IZbbZbt-LABEL: func64: +; RV32IZbbZbt: # %bb.0: +; RV32IZbbZbt-NEXT: sltu a2, a0, a4 +; RV32IZbbZbt-NEXT: sub a3, a1, a5 +; RV32IZbbZbt-NEXT: sub a2, a3, a2 +; RV32IZbbZbt-NEXT: slti a7, a2, 0 +; RV32IZbbZbt-NEXT: lui a6, 524288 +; RV32IZbbZbt-NEXT: addi a3, a6, -1 +; RV32IZbbZbt-NEXT: cmov a6, a7, a3, a6 +; RV32IZbbZbt-NEXT: xor a3, a1, a2 +; RV32IZbbZbt-NEXT: xor a1, a1, a5 +; RV32IZbbZbt-NEXT: and a1, a1, a3 +; RV32IZbbZbt-NEXT: slti a3, a1, 0 +; RV32IZbbZbt-NEXT: cmov a1, a3, a6, a2 +; RV32IZbbZbt-NEXT: srai a2, a2, 31 +; RV32IZbbZbt-NEXT: sub a0, a0, a4 +; RV32IZbbZbt-NEXT: cmov a0, a3, a2, a0 +; RV32IZbbZbt-NEXT: ret +; +; RV64IZbbZbt-LABEL: func64: +; RV64IZbbZbt: # %bb.0: +; RV64IZbbZbt-NEXT: sgtz a1, a2 +; RV64IZbbZbt-NEXT: sub a2, a0, a2 +; RV64IZbbZbt-NEXT: slt a0, a2, a0 +; RV64IZbbZbt-NEXT: xor a0, a1, a0 +; RV64IZbbZbt-NEXT: slti a1, a2, 0 +; RV64IZbbZbt-NEXT: addi a3, zero, -1 +; RV64IZbbZbt-NEXT: slli a3, a3, 63 +; RV64IZbbZbt-NEXT: addi a4, a3, -1 +; RV64IZbbZbt-NEXT: cmov a1, a1, a4, a3 +; RV64IZbbZbt-NEXT: cmov a0, a0, a1, a2 +; RV64IZbbZbt-NEXT: ret %a = mul i64 %y, %z %tmp = call i64 @llvm.ssub.sat.i64(i64 %x, i64 %z) ret i64 %tmp