llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-backend-hexagon Author: Matt Arsenault (arsenm) <details> <summary>Changes</summary> --- Patch is 44.74 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/147474.diff 1 Files Affected: - (added) llvm/test/CodeGen/Hexagon/llvm.sincos.ll (+1487) ``````````diff diff --git a/llvm/test/CodeGen/Hexagon/llvm.sincos.ll b/llvm/test/CodeGen/Hexagon/llvm.sincos.ll new file mode 100644 index 0000000000000..f02ac2ca8480f --- /dev/null +++ b/llvm/test/CodeGen/Hexagon/llvm.sincos.ll @@ -0,0 +1,1487 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5 +; RUN: llc -mtriple=hexagon < %s | FileCheck -check-prefix=BASE %s +; RUN: llc -mtriple=hexagon-unknown-linux-gnu < %s | FileCheck -check-prefix=GNU %s +; RUN: llc -mtriple=hexagon-unknown-linux-musl < %s | FileCheck -check-prefix=MUSL %s + +define { half, half } @test_sincos_f16(half %a) #0 { +; BASE-LABEL: test_sincos_f16: +; BASE: // %bb.0: +; BASE-NEXT: { +; BASE-NEXT: call __extendhfsf2 +; BASE-NEXT: memd(r29+#-16) = r17:16 +; BASE-NEXT: allocframe(#8) +; BASE-NEXT: } // 8-byte Folded Spill +; BASE-NEXT: { +; BASE-NEXT: call sinf +; BASE-NEXT: r16 = r0 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __truncsfhf2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call cosf +; BASE-NEXT: r17 = r0 +; BASE-NEXT: r0 = r16 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __truncsfhf2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: r1:0 = combine(r0,r17) +; BASE-NEXT: r17:16 = memd(r29+#0) +; BASE-NEXT: dealloc_return +; BASE-NEXT: } // 8-byte Folded Reload +; +; GNU-LABEL: test_sincos_f16: +; GNU: // %bb.0: +; GNU-NEXT: { +; GNU-NEXT: call __extendhfsf2 +; GNU-NEXT: memd(r29+#-16) = r17:16 +; GNU-NEXT: allocframe(#16) +; GNU-NEXT: } // 8-byte Folded Spill +; GNU-NEXT: { +; GNU-NEXT: call sincosf +; GNU-NEXT: r1 = add(r29,#0) +; GNU-NEXT: r2 = add(r29,#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __truncsfhf2 +; GNU-NEXT: r0 = memw(r29+#0) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __truncsfhf2 +; GNU-NEXT: r16 = r0 +; GNU-NEXT: r0 = memw(r29+#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: r1:0 = combine(r0,r16) +; GNU-NEXT: r17:16 = memd(r29+#8) +; GNU-NEXT: dealloc_return +; GNU-NEXT: } // 8-byte Folded Reload +; +; MUSL-LABEL: test_sincos_f16: +; MUSL: // %bb.0: +; MUSL-NEXT: { +; MUSL-NEXT: call __extendhfsf2 +; MUSL-NEXT: memd(r29+#-16) = r17:16 +; MUSL-NEXT: allocframe(#8) +; MUSL-NEXT: } // 8-byte Folded Spill +; MUSL-NEXT: { +; MUSL-NEXT: call sinf +; MUSL-NEXT: r16 = r0 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __truncsfhf2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call cosf +; MUSL-NEXT: r17 = r0 +; MUSL-NEXT: r0 = r16 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __truncsfhf2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: r1:0 = combine(r0,r17) +; MUSL-NEXT: r17:16 = memd(r29+#0) +; MUSL-NEXT: dealloc_return +; MUSL-NEXT: } // 8-byte Folded Reload + %result = call { half, half } @llvm.sincos.f16(half %a) + ret { half, half } %result +} + +define half @test_sincos_f16_only_use_sin(half %a) #0 { +; BASE-LABEL: test_sincos_f16_only_use_sin: +; BASE: // %bb.0: +; BASE-NEXT: { +; BASE-NEXT: call __extendhfsf2 +; BASE-NEXT: allocframe(r29,#0):raw +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call sinf +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __truncsfhf2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: r31:30 = dealloc_return(r30):raw +; BASE-NEXT: } +; +; GNU-LABEL: test_sincos_f16_only_use_sin: +; GNU: // %bb.0: +; GNU-NEXT: { +; GNU-NEXT: call __extendhfsf2 +; GNU-NEXT: allocframe(r29,#8):raw +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call sincosf +; GNU-NEXT: r1 = add(r29,#0) +; GNU-NEXT: r2 = add(r29,#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __truncsfhf2 +; GNU-NEXT: r0 = memw(r29+#0) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: r31:30 = dealloc_return(r30):raw +; GNU-NEXT: } +; +; MUSL-LABEL: test_sincos_f16_only_use_sin: +; MUSL: // %bb.0: +; MUSL-NEXT: { +; MUSL-NEXT: call __extendhfsf2 +; MUSL-NEXT: allocframe(r29,#0):raw +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call sinf +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __truncsfhf2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: r31:30 = dealloc_return(r30):raw +; MUSL-NEXT: } + %result = call { half, half } @llvm.sincos.f16(half %a) + %result.0 = extractvalue { half, half } %result, 0 + ret half %result.0 +} + +define half @test_sincos_f16_only_use_cos(half %a) #0 { +; BASE-LABEL: test_sincos_f16_only_use_cos: +; BASE: // %bb.0: +; BASE-NEXT: { +; BASE-NEXT: call __extendhfsf2 +; BASE-NEXT: allocframe(r29,#0):raw +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call cosf +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __truncsfhf2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: r31:30 = dealloc_return(r30):raw +; BASE-NEXT: } +; +; GNU-LABEL: test_sincos_f16_only_use_cos: +; GNU: // %bb.0: +; GNU-NEXT: { +; GNU-NEXT: call __extendhfsf2 +; GNU-NEXT: allocframe(r29,#8):raw +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call sincosf +; GNU-NEXT: r1 = add(r29,#0) +; GNU-NEXT: r2 = add(r29,#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __truncsfhf2 +; GNU-NEXT: r0 = memw(r29+#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: r31:30 = dealloc_return(r30):raw +; GNU-NEXT: } +; +; MUSL-LABEL: test_sincos_f16_only_use_cos: +; MUSL: // %bb.0: +; MUSL-NEXT: { +; MUSL-NEXT: call __extendhfsf2 +; MUSL-NEXT: allocframe(r29,#0):raw +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call cosf +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __truncsfhf2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: r31:30 = dealloc_return(r30):raw +; MUSL-NEXT: } + %result = call { half, half } @llvm.sincos.f16(half %a) + %result.1 = extractvalue { half, half } %result, 1 + ret half %result.1 +} + +define { <2 x half>, <2 x half> } @test_sincos_v2f16(<2 x half> %a) #0 { +; BASE-LABEL: test_sincos_v2f16: +; BASE: // %bb.0: +; BASE-NEXT: { +; BASE-NEXT: r17:16 = combine(r3,r0) +; BASE-NEXT: r0 = r2 +; BASE-NEXT: memd(r29+#-16) = r17:16 +; BASE-NEXT: allocframe(#24) +; BASE-NEXT: } // 8-byte Folded Spill +; BASE-NEXT: { +; BASE-NEXT: call __extendhfsf2 +; BASE-NEXT: memd(r29+#8) = r19:18 +; BASE-NEXT: memd(r29+#0) = r21:20 +; BASE-NEXT: } // 8-byte Folded Spill +; BASE-NEXT: { +; BASE-NEXT: call sinf +; BASE-NEXT: r18 = r0 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __truncsfhf2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __extendhfsf2 +; BASE-NEXT: r19 = r0 +; BASE-NEXT: r0 = r17 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call sinf +; BASE-NEXT: r17 = r0 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __truncsfhf2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call cosf +; BASE-NEXT: r20 = r0 +; BASE-NEXT: r0 = r18 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __truncsfhf2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call cosf +; BASE-NEXT: r18 = r0 +; BASE-NEXT: r0 = r17 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call __truncsfhf2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: memh(r16+#6) = r0 +; BASE-NEXT: memh(r16+#4) = r18 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: memh(r16+#2) = r20 +; BASE-NEXT: memh(r16+#0) = r19 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: r17:16 = memd(r29+#16) +; BASE-NEXT: r19:18 = memd(r29+#8) +; BASE-NEXT: } // 8-byte Folded Reload +; BASE-NEXT: { +; BASE-NEXT: r21:20 = memd(r29+#0) +; BASE-NEXT: dealloc_return +; BASE-NEXT: } // 8-byte Folded Reload +; +; GNU-LABEL: test_sincos_v2f16: +; GNU: // %bb.0: +; GNU-NEXT: { +; GNU-NEXT: r17:16 = combine(r3,r0) +; GNU-NEXT: r0 = r2 +; GNU-NEXT: memd(r29+#-16) = r17:16 +; GNU-NEXT: allocframe(#32) +; GNU-NEXT: } // 8-byte Folded Spill +; GNU-NEXT: { +; GNU-NEXT: call __extendhfsf2 +; GNU-NEXT: memd(r29+#16) = r19:18 +; GNU-NEXT: } // 8-byte Folded Spill +; GNU-NEXT: { +; GNU-NEXT: call sincosf +; GNU-NEXT: r1 = add(r29,#8) +; GNU-NEXT: r2 = add(r29,#12) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __extendhfsf2 +; GNU-NEXT: r0 = r17 +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call sincosf +; GNU-NEXT: r1 = add(r29,#0) +; GNU-NEXT: r2 = add(r29,#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __truncsfhf2 +; GNU-NEXT: r0 = memw(r29+#8) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __truncsfhf2 +; GNU-NEXT: r17 = r0 +; GNU-NEXT: r0 = memw(r29+#0) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __truncsfhf2 +; GNU-NEXT: r18 = r0 +; GNU-NEXT: r0 = memw(r29+#12) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call __truncsfhf2 +; GNU-NEXT: r19 = r0 +; GNU-NEXT: r0 = memw(r29+#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: memh(r16+#6) = r0 +; GNU-NEXT: memh(r16+#4) = r19 +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: memh(r16+#2) = r18 +; GNU-NEXT: memh(r16+#0) = r17 +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: r17:16 = memd(r29+#24) +; GNU-NEXT: r19:18 = memd(r29+#16) +; GNU-NEXT: } // 8-byte Folded Reload +; GNU-NEXT: { +; GNU-NEXT: r31:30 = dealloc_return(r30):raw +; GNU-NEXT: } +; +; MUSL-LABEL: test_sincos_v2f16: +; MUSL: // %bb.0: +; MUSL-NEXT: { +; MUSL-NEXT: r17:16 = combine(r3,r0) +; MUSL-NEXT: r0 = r2 +; MUSL-NEXT: memd(r29+#-16) = r17:16 +; MUSL-NEXT: allocframe(#24) +; MUSL-NEXT: } // 8-byte Folded Spill +; MUSL-NEXT: { +; MUSL-NEXT: call __extendhfsf2 +; MUSL-NEXT: memd(r29+#8) = r19:18 +; MUSL-NEXT: memd(r29+#0) = r21:20 +; MUSL-NEXT: } // 8-byte Folded Spill +; MUSL-NEXT: { +; MUSL-NEXT: call sinf +; MUSL-NEXT: r18 = r0 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __truncsfhf2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __extendhfsf2 +; MUSL-NEXT: r19 = r0 +; MUSL-NEXT: r0 = r17 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call sinf +; MUSL-NEXT: r17 = r0 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __truncsfhf2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call cosf +; MUSL-NEXT: r20 = r0 +; MUSL-NEXT: r0 = r18 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __truncsfhf2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call cosf +; MUSL-NEXT: r18 = r0 +; MUSL-NEXT: r0 = r17 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call __truncsfhf2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: memh(r16+#6) = r0 +; MUSL-NEXT: memh(r16+#4) = r18 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: memh(r16+#2) = r20 +; MUSL-NEXT: memh(r16+#0) = r19 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: r17:16 = memd(r29+#16) +; MUSL-NEXT: r19:18 = memd(r29+#8) +; MUSL-NEXT: } // 8-byte Folded Reload +; MUSL-NEXT: { +; MUSL-NEXT: r21:20 = memd(r29+#0) +; MUSL-NEXT: dealloc_return +; MUSL-NEXT: } // 8-byte Folded Reload + %result = call { <2 x half>, <2 x half> } @llvm.sincos.v2f16(<2 x half> %a) + ret { <2 x half>, <2 x half> } %result +} + +define { float, float } @test_sincos_f32(float %a) #0 { +; BASE-LABEL: test_sincos_f32: +; BASE: // %bb.0: +; BASE-NEXT: { +; BASE-NEXT: call sinf +; BASE-NEXT: r16 = r0 +; BASE-NEXT: memd(r29+#-16) = r17:16 +; BASE-NEXT: allocframe(#8) +; BASE-NEXT: } // 8-byte Folded Spill +; BASE-NEXT: { +; BASE-NEXT: call cosf +; BASE-NEXT: r17 = r0 +; BASE-NEXT: r0 = r16 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: r1:0 = combine(r0,r17) +; BASE-NEXT: r17:16 = memd(r29+#0) +; BASE-NEXT: dealloc_return +; BASE-NEXT: } // 8-byte Folded Reload +; +; GNU-LABEL: test_sincos_f32: +; GNU: // %bb.0: +; GNU-NEXT: { +; GNU-NEXT: allocframe(r29,#8):raw +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call sincosf +; GNU-NEXT: r1 = add(r29,#0) +; GNU-NEXT: r2 = add(r29,#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: r0 = memw(r29+#0) +; GNU-NEXT: r1 = memw(r29+#4) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: r31:30 = dealloc_return(r30):raw +; GNU-NEXT: } +; +; MUSL-LABEL: test_sincos_f32: +; MUSL: // %bb.0: +; MUSL-NEXT: { +; MUSL-NEXT: call sinf +; MUSL-NEXT: r16 = r0 +; MUSL-NEXT: memd(r29+#-16) = r17:16 +; MUSL-NEXT: allocframe(#8) +; MUSL-NEXT: } // 8-byte Folded Spill +; MUSL-NEXT: { +; MUSL-NEXT: call cosf +; MUSL-NEXT: r17 = r0 +; MUSL-NEXT: r0 = r16 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: r1:0 = combine(r0,r17) +; MUSL-NEXT: r17:16 = memd(r29+#0) +; MUSL-NEXT: dealloc_return +; MUSL-NEXT: } // 8-byte Folded Reload + %result = call { float, float } @llvm.sincos.f32(float %a) + ret { float, float } %result +} + +define { <2 x float>, <2 x float> } @test_sincos_v2f32(<2 x float> %a) #0 { +; CHECKR2-LABEL: test_sincos_v2f32: +; CHECKR2: # %bb.0: +; CHECKR2-NEXT: daddiu $sp, $sp, -32 +; CHECKR2-NEXT: sd $ra, 24($sp) # 8-byte Folded Spill +; CHECKR2-NEXT: sd $16, 16($sp) # 8-byte Folded Spill +; CHECKR2-NEXT: move $16, $4 +; CHECKR2-NEXT: dsrl $1, $4, 32 +; CHECKR2-NEXT: sll $1, $1, 0 +; CHECKR2-NEXT: mtc1 $1, $f12 +; CHECKR2-NEXT: daddiu $5, $sp, 12 +; CHECKR2-NEXT: jal sincosf +; CHECKR2-NEXT: daddiu $6, $sp, 8 +; CHECKR2-NEXT: sll $1, $16, 0 +; CHECKR2-NEXT: mtc1 $1, $f12 +; CHECKR2-NEXT: daddiu $5, $sp, 4 +; CHECKR2-NEXT: jal sincosf +; CHECKR2-NEXT: daddiu $6, $sp, 0 +; CHECKR2-NEXT: lwc1 $f0, 12($sp) +; CHECKR2-NEXT: mfc1 $1, $f0 +; CHECKR2-NEXT: dsll $1, $1, 32 +; CHECKR2-NEXT: lwc1 $f0, 4($sp) +; CHECKR2-NEXT: mfc1 $2, $f0 +; CHECKR2-NEXT: dext $2, $2, 0, 32 +; CHECKR2-NEXT: lwc1 $f0, 8($sp) +; CHECKR2-NEXT: or $2, $2, $1 +; CHECKR2-NEXT: mfc1 $1, $f0 +; CHECKR2-NEXT: dsll $1, $1, 32 +; CHECKR2-NEXT: lwc1 $f0, 0($sp) +; CHECKR2-NEXT: mfc1 $3, $f0 +; CHECKR2-NEXT: dext $3, $3, 0, 32 +; CHECKR2-NEXT: or $3, $3, $1 +; CHECKR2-NEXT: ld $16, 16($sp) # 8-byte Folded Reload +; CHECKR2-NEXT: ld $ra, 24($sp) # 8-byte Folded Reload +; CHECKR2-NEXT: jr $ra +; CHECKR2-NEXT: daddiu $sp, $sp, 32 +; BASE-LABEL: test_sincos_v2f32: +; BASE: // %bb.0: +; BASE-NEXT: { +; BASE-NEXT: r17:16 = combine(r0,r2) +; BASE-NEXT: r0 = r2 +; BASE-NEXT: memd(r29+#-16) = r17:16 +; BASE-NEXT: allocframe(#24) +; BASE-NEXT: } // 8-byte Folded Spill +; BASE-NEXT: { +; BASE-NEXT: call sinf +; BASE-NEXT: r18 = r3 +; BASE-NEXT: memd(r29+#8) = r19:18 +; BASE-NEXT: memd(r29+#0) = r21:20 +; BASE-NEXT: } // 8-byte Folded Spill +; BASE-NEXT: { +; BASE-NEXT: call sinf +; BASE-NEXT: r19 = r0 +; BASE-NEXT: r0 = r18 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call cosf +; BASE-NEXT: r20 = r0 +; BASE-NEXT: r0 = r16 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: call cosf +; BASE-NEXT: r16 = r0 +; BASE-NEXT: r0 = r18 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: r1:0 = combine(r0,r16) +; BASE-NEXT: r3:2 = combine(r20,r19) +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: memd(r17+#8) = r1:0 +; BASE-NEXT: memd(r17+#0) = r3:2 +; BASE-NEXT: } +; BASE-NEXT: { +; BASE-NEXT: r17:16 = memd(r29+#16) +; BASE-NEXT: r19:18 = memd(r29+#8) +; BASE-NEXT: } // 8-byte Folded Reload +; BASE-NEXT: { +; BASE-NEXT: r21:20 = memd(r29+#0) +; BASE-NEXT: dealloc_return +; BASE-NEXT: } // 8-byte Folded Reload +; +; GNU-LABEL: test_sincos_v2f32: +; GNU: // %bb.0: +; GNU-NEXT: { +; GNU-NEXT: r17:16 = combine(r0,r2) +; GNU-NEXT: r1 = add(r0,#4) +; GNU-NEXT: memd(r29+#-16) = r17:16 +; GNU-NEXT: allocframe(#8) +; GNU-NEXT: } // 8-byte Folded Spill +; GNU-NEXT: { +; GNU-NEXT: call sincosf +; GNU-NEXT: r2 = add(r0,#12) +; GNU-NEXT: r0 = r3 +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: call sincosf +; GNU-NEXT: r2 = add(r17,#8) +; GNU-NEXT: r1:0 = combine(r17,r16) +; GNU-NEXT: } +; GNU-NEXT: { +; GNU-NEXT: r17:16 = memd(r29+#0) +; GNU-NEXT: dealloc_return +; GNU-NEXT: } // 8-byte Folded Reload +; +; MUSL-LABEL: test_sincos_v2f32: +; MUSL: // %bb.0: +; MUSL-NEXT: { +; MUSL-NEXT: r17:16 = combine(r0,r2) +; MUSL-NEXT: r0 = r2 +; MUSL-NEXT: memd(r29+#-16) = r17:16 +; MUSL-NEXT: allocframe(#24) +; MUSL-NEXT: } // 8-byte Folded Spill +; MUSL-NEXT: { +; MUSL-NEXT: call sinf +; MUSL-NEXT: r18 = r3 +; MUSL-NEXT: memd(r29+#8) = r19:18 +; MUSL-NEXT: memd(r29+#0) = r21:20 +; MUSL-NEXT: } // 8-byte Folded Spill +; MUSL-NEXT: { +; MUSL-NEXT: call sinf +; MUSL-NEXT: r19 = r0 +; MUSL-NEXT: r0 = r18 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call cosf +; MUSL-NEXT: r20 = r0 +; MUSL-NEXT: r0 = r16 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: call cosf +; MUSL-NEXT: r16 = r0 +; MUSL-NEXT: r0 = r18 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: r1:0 = combine(r0,r16) +; MUSL-NEXT: r3:2 = combine(r20,r19) +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: memd(r17+#8) = r1:0 +; MUSL-NEXT: memd(r17+#0) = r3:2 +; MUSL-NEXT: } +; MUSL-NEXT: { +; MUSL-NEXT: r17:16 = memd(r29+#16) +; MUSL-NEXT: r19:18 = memd(r29+#8) +; MUSL-NEXT: } // 8-byte Folded Reload +; MUSL-NEXT: { +; MUSL-NEXT: r21:20 = memd(r29+#0) +; MUSL-NEXT: dealloc_return +; MUSL-NEXT: } // 8-byte Folded Reload + %result = call { <2 x float>, <2 x float> } @llvm.sincos.v2f32(<2 x float> %a) + ret { <2 x float>, <2 x float> } %result +} + +define { <3 x float>, <3 x float> } @test_sincos_v3f32(<3 x float> %a) #0 { +; CHECKR2-LABEL: test_sincos_v3f32: +; CHECKR2: # %bb.0: +; CHECKR2-NEXT: daddiu $sp, $sp, -48 +; CHECKR2-NEXT: sdc1 $f25, 40($sp) # 8-byte Folded Spill +; CHECKR2-NEXT: sdc1 $f24, 32($sp) # 8-byte Folded Spill +; CHECKR2-NEXT: sd $ra, 24($sp) # 8-byte Folded Spill +; CHECKR2-NEXT: sd $16, 16($sp) # 8-byte Folded Spill +; CHECKR2-NEXT: mov.s $f24, $f15 +; CHECKR2-NEXT: mov.s $f25, $f14 +; CHECKR2-NEXT: mov.s $f12, $f13 +; CHECKR2-NEXT: move $16, $4 +; CHECKR2-NEXT: daddiu $5, $sp, 4 +; CHECKR2-NEXT: jal sincosf +; CHECKR2-NEXT: daddiu $6, $sp, 0 +; CHECKR2-NEXT: daddiu $5, $sp, 12 +; CHECKR2-NEXT: daddiu $6, $sp, 8 +; CHECKR2-NEXT: jal sincosf +; CHECKR2-NEXT: mov.s $f12, $f25 +; CHECKR2-NEXT: daddiu $5, $16, 8 +; CHECKR2-NEXT: daddiu $6, $16, 24 +; CHECKR2-NEXT: jal sincosf +; CHECKR2-NEXT: mov.s $f12, $f24 +; CHECKR2-NEXT: lwc1 $f0, 0($sp) +; CHECKR2-NEXT: mfc1 $1, $f0 +; CHECKR2-NEXT: dsll $1, $1, 32 +; CHECKR2-NEXT: lwc1 $f0, 8($sp) +; CHECKR2-NEXT: mfc1 $2, $f0 +; CHECKR2-NEXT: dext $2, $2, 0, 32 +; CHECKR2-NEXT: or $1, $2, $1 +; CHECKR2-NEXT: lwc1 $f0, 4($sp) +; CHECKR2-NEXT: mfc1 $2, $f0 +; CHECKR2-NEXT: sd $1, 16($16) +; CHECKR2-NEXT: dsll $1, $2, 32 +; CHECKR2-NEXT: lwc1 $f0, 12($sp) +; CHECKR2-NEXT: mfc1 $2, $f0 +; CHECKR2-NEXT: dext $2, $2, 0, 32 +; CHECKR2-NEXT: or $1, $2, $1 +; CHECKR2-NEXT: sd $1, 0($16) +; CHECKR2-NEXT: ld $16, 16($sp) # 8-byte Folded Reload +; CHECKR2-NEXT: ld $ra, 24($sp) # 8-byte Folded Reload +; CHECKR2-NEXT: ldc1 $f24, 32($sp) # 8-byte Folded Reload +; CHECKR2-NEXT: ldc1 $f25, 40($sp) # 8-byte Folded Reload +; CHECKR2-NEXT: jr $ra +; CHECKR2-NEXT: daddiu $sp, $sp, 48 +; BASE-LABEL: test_sincos_v3f32: +; BASE: // %bb.0: +; BASE-NEXT: { +; BASE-NEXT: memd(r29+#-16) = r17:16 +; BASE-NEXT: allocframe(#32) +; BASE-NEXT: } // 8-byte Folded Spill +; BASE-NEXT: { +; BASE-NEXT: r19:18 = combine(r0,r2) +; BASE-NEXT: r0 = r2 +; BASE-NEXT: memd(r29+#16) = r19:18 +; BASE-NEXT: memd(r29+#8) = r21:20 +; BASE-NEXT: } // 8-byte Folded Spill +; BASE-NEXT: { +; BASE-NEXT: call sinf +; BAS... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/147474 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
